Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the glaive_toolcall_100k and the bespoke_reasoning_17k datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3492
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 7
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 14
+- total_eval_batch_size: 7
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4468        | 0.2307 | 500  | 0.3987          |
+| 0.4457        | 0.4614 | 1000 | 0.3861          |
+| 0.4197        | 0.6920 | 1500 | 0.3745          |
+| 0.4264        | 0.9227 | 2000 | 0.3640          |
+| 0.3188        | 1.1532 | 2500 | 0.3638          |
+| 0.2938        | 1.3839 | 3000 | 0.3572          |
+| 0.2891        | 1.6145 | 3500 | 0.3523          |
+| 0.3013        | 1.8452 | 4000 | 0.3492          |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9993079584775086,
+    "eval_loss": 0.34922918677330017,
+    "eval_runtime": 406.3236,
+    "eval_samples_per_second": 8.296,
+    "eval_steps_per_second": 1.186,
+    "total_flos": 545751381377024.0,
+    "train_loss": 0.3850643413100971,
+    "train_runtime": 89295.2192,
+    "train_samples_per_second": 0.68,
+    "train_steps_per_second": 0.049
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9993079584775086,
+    "eval_loss": 0.34922918677330017,
+    "eval_runtime": 406.3236,
+    "eval_samples_per_second": 8.296,
+    "eval_steps_per_second": 1.186
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3b8768bc10b761a7a4575b1ac3ffa13161905c550ac2db14c74b8d0013d4e3
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308c8609d61a72ca4edc885f187c1d1bce9b316a4b905c4b259e031fe2e99bd4
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30322a456c3788404054447192b0ab7b41db914977f2eaf8556d9b7185aed566
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822b21fcc05e49bb75fe35d3a492fefaddbaaa57180f0fe7915f2610a6fce3f4
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af82f754565ca632c05f62309b4387d134a2eeb09e4c059eff39764ee40e0ee0
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93d19b22e526c724ab8813dce36dcb797c733e74766344de222629ad136a86f
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9993079584775086,
+    "total_flos": 545751381377024.0,
+    "train_loss": 0.3850643413100971,
+    "train_runtime": 89295.2192,
+    "train_samples_per_second": 0.68,
+    "train_steps_per_second": 0.049
+}

trainer_log.jsonl

@@ -0,0 +1,442 @@
+{"current_steps": 10, "total_steps": 4334, "loss": 0.806, "lr": 2.3041474654377884e-07, "epoch": 0.00461361014994233, "percentage": 0.23, "elapsed_time": "0:03:36", "remaining_time": "1 day, 2:02:31"}
+{"current_steps": 20, "total_steps": 4334, "loss": 0.8251, "lr": 4.608294930875577e-07, "epoch": 0.00922722029988466, "percentage": 0.46, "elapsed_time": "0:06:52", "remaining_time": "1 day, 0:42:21"}
+{"current_steps": 30, "total_steps": 4334, "loss": 0.7555, "lr": 6.912442396313365e-07, "epoch": 0.01384083044982699, "percentage": 0.69, "elapsed_time": "0:10:09", "remaining_time": "1 day, 0:17:09"}
+{"current_steps": 40, "total_steps": 4334, "loss": 0.7218, "lr": 9.216589861751154e-07, "epoch": 0.01845444059976932, "percentage": 0.92, "elapsed_time": "0:13:21", "remaining_time": "23:54:37"}
+{"current_steps": 50, "total_steps": 4334, "loss": 0.6751, "lr": 1.1520737327188942e-06, "epoch": 0.02306805074971165, "percentage": 1.15, "elapsed_time": "0:17:02", "remaining_time": "1 day, 0:20:17"}
+{"current_steps": 60, "total_steps": 4334, "loss": 0.6197, "lr": 1.382488479262673e-06, "epoch": 0.02768166089965398, "percentage": 1.38, "elapsed_time": "0:20:16", "remaining_time": "1 day, 0:04:06"}
+{"current_steps": 70, "total_steps": 4334, "loss": 0.5083, "lr": 1.6129032258064516e-06, "epoch": 0.03229527104959631, "percentage": 1.62, "elapsed_time": "0:23:33", "remaining_time": "23:54:33"}
+{"current_steps": 80, "total_steps": 4334, "loss": 0.5326, "lr": 1.8433179723502307e-06, "epoch": 0.03690888119953864, "percentage": 1.85, "elapsed_time": "0:26:49", "remaining_time": "23:45:58"}
+{"current_steps": 90, "total_steps": 4334, "loss": 0.5463, "lr": 2.0737327188940094e-06, "epoch": 0.04152249134948097, "percentage": 2.08, "elapsed_time": "0:30:04", "remaining_time": "23:38:30"}
+{"current_steps": 100, "total_steps": 4334, "loss": 0.5445, "lr": 2.3041474654377884e-06, "epoch": 0.0461361014994233, "percentage": 2.31, "elapsed_time": "0:33:23", "remaining_time": "23:33:31"}
+{"current_steps": 110, "total_steps": 4334, "loss": 0.4972, "lr": 2.5345622119815673e-06, "epoch": 0.05074971164936563, "percentage": 2.54, "elapsed_time": "0:36:59", "remaining_time": "23:40:17"}
+{"current_steps": 120, "total_steps": 4334, "loss": 0.519, "lr": 2.764976958525346e-06, "epoch": 0.05536332179930796, "percentage": 2.77, "elapsed_time": "0:40:23", "remaining_time": "23:38:08"}
+{"current_steps": 130, "total_steps": 4334, "loss": 0.453, "lr": 2.9953917050691243e-06, "epoch": 0.05997693194925029, "percentage": 3.0, "elapsed_time": "0:43:24", "remaining_time": "23:23:45"}
+{"current_steps": 140, "total_steps": 4334, "loss": 0.4799, "lr": 3.225806451612903e-06, "epoch": 0.06459054209919261, "percentage": 3.23, "elapsed_time": "0:46:35", "remaining_time": "23:15:56"}
+{"current_steps": 150, "total_steps": 4334, "loss": 0.4896, "lr": 3.4562211981566825e-06, "epoch": 0.06920415224913495, "percentage": 3.46, "elapsed_time": "0:49:52", "remaining_time": "23:11:06"}
+{"current_steps": 160, "total_steps": 4334, "loss": 0.5167, "lr": 3.6866359447004615e-06, "epoch": 0.07381776239907728, "percentage": 3.69, "elapsed_time": "0:53:28", "remaining_time": "23:15:09"}
+{"current_steps": 170, "total_steps": 4334, "loss": 0.5127, "lr": 3.91705069124424e-06, "epoch": 0.0784313725490196, "percentage": 3.92, "elapsed_time": "0:56:46", "remaining_time": "23:10:32"}
+{"current_steps": 180, "total_steps": 4334, "loss": 0.4465, "lr": 4.147465437788019e-06, "epoch": 0.08304498269896193, "percentage": 4.15, "elapsed_time": "1:00:28", "remaining_time": "23:15:49"}
+{"current_steps": 190, "total_steps": 4334, "loss": 0.4761, "lr": 4.377880184331797e-06, "epoch": 0.08765859284890427, "percentage": 4.38, "elapsed_time": "1:03:45", "remaining_time": "23:10:31"}
+{"current_steps": 200, "total_steps": 4334, "loss": 0.5055, "lr": 4.608294930875577e-06, "epoch": 0.0922722029988466, "percentage": 4.61, "elapsed_time": "1:06:56", "remaining_time": "23:03:37"}
+{"current_steps": 210, "total_steps": 4334, "loss": 0.4557, "lr": 4.838709677419355e-06, "epoch": 0.09688581314878893, "percentage": 4.85, "elapsed_time": "1:10:10", "remaining_time": "22:58:15"}
+{"current_steps": 220, "total_steps": 4334, "loss": 0.4686, "lr": 5.0691244239631346e-06, "epoch": 0.10149942329873125, "percentage": 5.08, "elapsed_time": "1:13:34", "remaining_time": "22:55:50"}
+{"current_steps": 230, "total_steps": 4334, "loss": 0.4843, "lr": 5.299539170506913e-06, "epoch": 0.1061130334486736, "percentage": 5.31, "elapsed_time": "1:16:46", "remaining_time": "22:50:01"}
+{"current_steps": 240, "total_steps": 4334, "loss": 0.5015, "lr": 5.529953917050692e-06, "epoch": 0.11072664359861592, "percentage": 5.54, "elapsed_time": "1:19:58", "remaining_time": "22:44:06"}
+{"current_steps": 250, "total_steps": 4334, "loss": 0.4622, "lr": 5.76036866359447e-06, "epoch": 0.11534025374855825, "percentage": 5.77, "elapsed_time": "1:23:19", "remaining_time": "22:41:15"}
+{"current_steps": 260, "total_steps": 4334, "loss": 0.4642, "lr": 5.9907834101382485e-06, "epoch": 0.11995386389850057, "percentage": 6.0, "elapsed_time": "1:26:41", "remaining_time": "22:38:26"}
+{"current_steps": 270, "total_steps": 4334, "loss": 0.4357, "lr": 6.221198156682028e-06, "epoch": 0.1245674740484429, "percentage": 6.23, "elapsed_time": "1:29:49", "remaining_time": "22:32:08"}
+{"current_steps": 280, "total_steps": 4334, "loss": 0.4547, "lr": 6.451612903225806e-06, "epoch": 0.12918108419838523, "percentage": 6.46, "elapsed_time": "1:33:16", "remaining_time": "22:30:25"}
+{"current_steps": 290, "total_steps": 4334, "loss": 0.4464, "lr": 6.682027649769586e-06, "epoch": 0.13379469434832755, "percentage": 6.69, "elapsed_time": "1:36:50", "remaining_time": "22:30:31"}
+{"current_steps": 300, "total_steps": 4334, "loss": 0.4957, "lr": 6.912442396313365e-06, "epoch": 0.1384083044982699, "percentage": 6.92, "elapsed_time": "1:40:13", "remaining_time": "22:27:44"}
+{"current_steps": 310, "total_steps": 4334, "loss": 0.4473, "lr": 7.1428571428571436e-06, "epoch": 0.14302191464821223, "percentage": 7.15, "elapsed_time": "1:43:28", "remaining_time": "22:23:06"}
+{"current_steps": 320, "total_steps": 4334, "loss": 0.4831, "lr": 7.373271889400923e-06, "epoch": 0.14763552479815456, "percentage": 7.38, "elapsed_time": "1:46:48", "remaining_time": "22:19:43"}
+{"current_steps": 330, "total_steps": 4334, "loss": 0.4996, "lr": 7.603686635944701e-06, "epoch": 0.1522491349480969, "percentage": 7.61, "elapsed_time": "1:50:32", "remaining_time": "22:21:12"}
+{"current_steps": 340, "total_steps": 4334, "loss": 0.4861, "lr": 7.83410138248848e-06, "epoch": 0.1568627450980392, "percentage": 7.84, "elapsed_time": "1:53:43", "remaining_time": "22:15:56"}
+{"current_steps": 350, "total_steps": 4334, "loss": 0.4774, "lr": 8.064516129032258e-06, "epoch": 0.16147635524798154, "percentage": 8.08, "elapsed_time": "1:56:59", "remaining_time": "22:11:36"}
+{"current_steps": 360, "total_steps": 4334, "loss": 0.505, "lr": 8.294930875576038e-06, "epoch": 0.16608996539792387, "percentage": 8.31, "elapsed_time": "2:00:25", "remaining_time": "22:09:22"}
+{"current_steps": 370, "total_steps": 4334, "loss": 0.5116, "lr": 8.525345622119815e-06, "epoch": 0.1707035755478662, "percentage": 8.54, "elapsed_time": "2:03:39", "remaining_time": "22:04:45"}
+{"current_steps": 380, "total_steps": 4334, "loss": 0.4307, "lr": 8.755760368663595e-06, "epoch": 0.17531718569780855, "percentage": 8.77, "elapsed_time": "2:07:02", "remaining_time": "22:01:52"}
+{"current_steps": 390, "total_steps": 4334, "loss": 0.4525, "lr": 8.986175115207374e-06, "epoch": 0.17993079584775087, "percentage": 9.0, "elapsed_time": "2:10:23", "remaining_time": "21:58:41"}
+{"current_steps": 400, "total_steps": 4334, "loss": 0.4557, "lr": 9.216589861751153e-06, "epoch": 0.1845444059976932, "percentage": 9.23, "elapsed_time": "2:13:57", "remaining_time": "21:57:29"}
+{"current_steps": 410, "total_steps": 4334, "loss": 0.4927, "lr": 9.447004608294931e-06, "epoch": 0.18915801614763553, "percentage": 9.46, "elapsed_time": "2:17:12", "remaining_time": "21:53:15"}
+{"current_steps": 420, "total_steps": 4334, "loss": 0.4926, "lr": 9.67741935483871e-06, "epoch": 0.19377162629757785, "percentage": 9.69, "elapsed_time": "2:20:26", "remaining_time": "21:48:46"}
+{"current_steps": 430, "total_steps": 4334, "loss": 0.4373, "lr": 9.90783410138249e-06, "epoch": 0.19838523644752018, "percentage": 9.92, "elapsed_time": "2:23:35", "remaining_time": "21:43:40"}
+{"current_steps": 440, "total_steps": 4334, "loss": 0.4877, "lr": 9.999941600087643e-06, "epoch": 0.2029988465974625, "percentage": 10.15, "elapsed_time": "2:26:42", "remaining_time": "21:38:23"}
+{"current_steps": 450, "total_steps": 4334, "loss": 0.4628, "lr": 9.999584716674727e-06, "epoch": 0.20761245674740483, "percentage": 10.38, "elapsed_time": "2:30:08", "remaining_time": "21:35:52"}
+{"current_steps": 460, "total_steps": 4334, "loss": 0.4757, "lr": 9.998903417374228e-06, "epoch": 0.2122260668973472, "percentage": 10.61, "elapsed_time": "2:33:39", "remaining_time": "21:34:07"}
+{"current_steps": 470, "total_steps": 4334, "loss": 0.486, "lr": 9.997897746394684e-06, "epoch": 0.21683967704728951, "percentage": 10.84, "elapsed_time": "2:36:41", "remaining_time": "21:28:13"}
+{"current_steps": 480, "total_steps": 4334, "loss": 0.4862, "lr": 9.996567768992642e-06, "epoch": 0.22145328719723184, "percentage": 11.08, "elapsed_time": "2:39:42", "remaining_time": "21:22:20"}
+{"current_steps": 490, "total_steps": 4334, "loss": 0.486, "lr": 9.994913571468432e-06, "epoch": 0.22606689734717417, "percentage": 11.31, "elapsed_time": "2:43:11", "remaining_time": "21:20:09"}
+{"current_steps": 500, "total_steps": 4334, "loss": 0.4468, "lr": 9.992935261160559e-06, "epoch": 0.2306805074971165, "percentage": 11.54, "elapsed_time": "2:46:31", "remaining_time": "21:16:58"}
+{"current_steps": 500, "total_steps": 4334, "eval_loss": 0.39874735474586487, "epoch": 0.2306805074971165, "percentage": 11.54, "elapsed_time": "2:53:12", "remaining_time": "22:08:12"}
+{"current_steps": 510, "total_steps": 4334, "loss": 0.4171, "lr": 9.990632966438743e-06, "epoch": 0.23529411764705882, "percentage": 11.77, "elapsed_time": "2:58:43", "remaining_time": "22:20:08"}
+{"current_steps": 520, "total_steps": 4334, "loss": 0.4764, "lr": 9.988006836695593e-06, "epoch": 0.23990772779700115, "percentage": 12.0, "elapsed_time": "3:01:43", "remaining_time": "22:12:51"}
+{"current_steps": 530, "total_steps": 4334, "loss": 0.4678, "lr": 9.985057042336898e-06, "epoch": 0.24452133794694347, "percentage": 12.23, "elapsed_time": "3:04:55", "remaining_time": "22:07:18"}
+{"current_steps": 540, "total_steps": 4334, "loss": 0.4524, "lr": 9.981783774770595e-06, "epoch": 0.2491349480968858, "percentage": 12.46, "elapsed_time": "3:08:05", "remaining_time": "22:01:27"}
+{"current_steps": 550, "total_steps": 4334, "loss": 0.4399, "lr": 9.97818724639432e-06, "epoch": 0.2537485582468281, "percentage": 12.69, "elapsed_time": "3:11:06", "remaining_time": "21:54:49"}
+{"current_steps": 560, "total_steps": 4334, "loss": 0.4897, "lr": 9.974267690581646e-06, "epoch": 0.25836216839677045, "percentage": 12.92, "elapsed_time": "3:14:24", "remaining_time": "21:50:10"}
+{"current_steps": 570, "total_steps": 4334, "loss": 0.4497, "lr": 9.970025361666934e-06, "epoch": 0.2629757785467128, "percentage": 13.15, "elapsed_time": "3:17:40", "remaining_time": "21:45:23"}
+{"current_steps": 580, "total_steps": 4334, "loss": 0.4832, "lr": 9.965460534928827e-06, "epoch": 0.2675893886966551, "percentage": 13.38, "elapsed_time": "3:20:45", "remaining_time": "21:39:20"}
+{"current_steps": 590, "total_steps": 4334, "loss": 0.4788, "lr": 9.960573506572391e-06, "epoch": 0.2722029988465975, "percentage": 13.61, "elapsed_time": "3:24:04", "remaining_time": "21:35:01"}
+{"current_steps": 600, "total_steps": 4334, "loss": 0.4484, "lr": 9.95536459370989e-06, "epoch": 0.2768166089965398, "percentage": 13.84, "elapsed_time": "3:27:08", "remaining_time": "21:29:08"}
+{"current_steps": 610, "total_steps": 4334, "loss": 0.4799, "lr": 9.949834134340219e-06, "epoch": 0.28143021914648214, "percentage": 14.07, "elapsed_time": "3:30:16", "remaining_time": "21:23:45"}
+{"current_steps": 620, "total_steps": 4334, "loss": 0.4506, "lr": 9.94398248732696e-06, "epoch": 0.28604382929642447, "percentage": 14.31, "elapsed_time": "3:33:17", "remaining_time": "21:17:40"}
+{"current_steps": 630, "total_steps": 4334, "loss": 0.5108, "lr": 9.9378100323751e-06, "epoch": 0.2906574394463668, "percentage": 14.54, "elapsed_time": "3:36:25", "remaining_time": "21:12:28"}
+{"current_steps": 640, "total_steps": 4334, "loss": 0.4607, "lr": 9.931317170006398e-06, "epoch": 0.2952710495963091, "percentage": 14.77, "elapsed_time": "3:39:35", "remaining_time": "21:07:26"}
+{"current_steps": 650, "total_steps": 4334, "loss": 0.4564, "lr": 9.924504321533387e-06, "epoch": 0.29988465974625145, "percentage": 15.0, "elapsed_time": "3:42:53", "remaining_time": "21:03:19"}
+{"current_steps": 660, "total_steps": 4334, "loss": 0.447, "lr": 9.91737192903204e-06, "epoch": 0.3044982698961938, "percentage": 15.23, "elapsed_time": "3:46:03", "remaining_time": "20:58:22"}
+{"current_steps": 670, "total_steps": 4334, "loss": 0.4712, "lr": 9.909920455313087e-06, "epoch": 0.3091118800461361, "percentage": 15.46, "elapsed_time": "3:49:32", "remaining_time": "20:55:19"}
+{"current_steps": 680, "total_steps": 4334, "loss": 0.4831, "lr": 9.902150383891979e-06, "epoch": 0.3137254901960784, "percentage": 15.69, "elapsed_time": "3:52:35", "remaining_time": "20:49:52"}
+{"current_steps": 690, "total_steps": 4334, "loss": 0.499, "lr": 9.894062218957517e-06, "epoch": 0.31833910034602075, "percentage": 15.92, "elapsed_time": "3:55:42", "remaining_time": "20:44:49"}
+{"current_steps": 700, "total_steps": 4334, "loss": 0.4482, "lr": 9.885656485339129e-06, "epoch": 0.3229527104959631, "percentage": 16.15, "elapsed_time": "3:58:55", "remaining_time": "20:40:19"}
+{"current_steps": 710, "total_steps": 4334, "loss": 0.4763, "lr": 9.876933728472826e-06, "epoch": 0.3275663206459054, "percentage": 16.38, "elapsed_time": "4:02:10", "remaining_time": "20:36:04"}
+{"current_steps": 720, "total_steps": 4334, "loss": 0.4707, "lr": 9.867894514365802e-06, "epoch": 0.33217993079584773, "percentage": 16.61, "elapsed_time": "4:05:09", "remaining_time": "20:30:33"}
+{"current_steps": 730, "total_steps": 4334, "loss": 0.472, "lr": 9.858539429559705e-06, "epoch": 0.33679354094579006, "percentage": 16.84, "elapsed_time": "4:08:24", "remaining_time": "20:26:25"}
+{"current_steps": 740, "total_steps": 4334, "loss": 0.497, "lr": 9.848869081092581e-06, "epoch": 0.3414071510957324, "percentage": 17.07, "elapsed_time": "4:11:43", "remaining_time": "20:22:33"}
+{"current_steps": 750, "total_steps": 4334, "loss": 0.4271, "lr": 9.838884096459486e-06, "epoch": 0.3460207612456747, "percentage": 17.31, "elapsed_time": "4:15:08", "remaining_time": "20:19:15"}
+{"current_steps": 760, "total_steps": 4334, "loss": 0.4977, "lr": 9.828585123571763e-06, "epoch": 0.3506343713956171, "percentage": 17.54, "elapsed_time": "4:18:29", "remaining_time": "20:15:34"}
+{"current_steps": 770, "total_steps": 4334, "loss": 0.4605, "lr": 9.817972830715003e-06, "epoch": 0.3552479815455594, "percentage": 17.77, "elapsed_time": "4:21:27", "remaining_time": "20:10:12"}
+{"current_steps": 780, "total_steps": 4334, "loss": 0.4414, "lr": 9.807047906505683e-06, "epoch": 0.35986159169550175, "percentage": 18.0, "elapsed_time": "4:24:42", "remaining_time": "20:06:05"}
+{"current_steps": 790, "total_steps": 4334, "loss": 0.4372, "lr": 9.795811059846476e-06, "epoch": 0.3644752018454441, "percentage": 18.23, "elapsed_time": "4:27:45", "remaining_time": "20:01:09"}
+{"current_steps": 800, "total_steps": 4334, "loss": 0.486, "lr": 9.78426301988026e-06, "epoch": 0.3690888119953864, "percentage": 18.46, "elapsed_time": "4:30:50", "remaining_time": "19:56:28"}
+{"current_steps": 810, "total_steps": 4334, "loss": 0.4645, "lr": 9.772404535942802e-06, "epoch": 0.3737024221453287, "percentage": 18.69, "elapsed_time": "4:34:12", "remaining_time": "19:52:57"}
+{"current_steps": 820, "total_steps": 4334, "loss": 0.4503, "lr": 9.760236377514128e-06, "epoch": 0.37831603229527105, "percentage": 18.92, "elapsed_time": "4:37:17", "remaining_time": "19:48:16"}
+{"current_steps": 830, "total_steps": 4334, "loss": 0.4602, "lr": 9.747759334168602e-06, "epoch": 0.3829296424452134, "percentage": 19.15, "elapsed_time": "4:40:22", "remaining_time": "19:43:40"}
+{"current_steps": 840, "total_steps": 4334, "loss": 0.4535, "lr": 9.734974215523684e-06, "epoch": 0.3875432525951557, "percentage": 19.38, "elapsed_time": "4:43:41", "remaining_time": "19:40:02"}
+{"current_steps": 850, "total_steps": 4334, "loss": 0.4569, "lr": 9.721881851187406e-06, "epoch": 0.39215686274509803, "percentage": 19.61, "elapsed_time": "4:46:50", "remaining_time": "19:35:43"}
+{"current_steps": 860, "total_steps": 4334, "loss": 0.4359, "lr": 9.708483090704524e-06, "epoch": 0.39677047289504036, "percentage": 19.84, "elapsed_time": "4:50:03", "remaining_time": "19:31:42"}
+{"current_steps": 870, "total_steps": 4334, "loss": 0.4573, "lr": 9.694778803501404e-06, "epoch": 0.4013840830449827, "percentage": 20.07, "elapsed_time": "4:53:09", "remaining_time": "19:27:16"}
+{"current_steps": 880, "total_steps": 4334, "loss": 0.4737, "lr": 9.680769878829606e-06, "epoch": 0.405997693194925, "percentage": 20.3, "elapsed_time": "4:56:13", "remaining_time": "19:22:41"}
+{"current_steps": 890, "total_steps": 4334, "loss": 0.4532, "lr": 9.666457225708175e-06, "epoch": 0.41061130334486734, "percentage": 20.54, "elapsed_time": "4:59:32", "remaining_time": "19:19:07"}
+{"current_steps": 900, "total_steps": 4334, "loss": 0.4475, "lr": 9.65184177286466e-06, "epoch": 0.41522491349480967, "percentage": 20.77, "elapsed_time": "5:02:46", "remaining_time": "19:15:15"}
+{"current_steps": 910, "total_steps": 4334, "loss": 0.4866, "lr": 9.636924468674856e-06, "epoch": 0.419838523644752, "percentage": 21.0, "elapsed_time": "5:05:52", "remaining_time": "19:10:54"}
+{"current_steps": 920, "total_steps": 4334, "loss": 0.4437, "lr": 9.62170628110125e-06, "epoch": 0.4244521337946944, "percentage": 21.23, "elapsed_time": "5:09:14", "remaining_time": "19:07:31"}
+{"current_steps": 930, "total_steps": 4334, "loss": 0.4349, "lr": 9.606188197630224e-06, "epoch": 0.4290657439446367, "percentage": 21.46, "elapsed_time": "5:12:31", "remaining_time": "19:03:56"}
+{"current_steps": 940, "total_steps": 4334, "loss": 0.4917, "lr": 9.590371225207981e-06, "epoch": 0.43367935409457903, "percentage": 21.69, "elapsed_time": "5:15:49", "remaining_time": "19:00:19"}
+{"current_steps": 950, "total_steps": 4334, "loss": 0.4682, "lr": 9.574256390175192e-06, "epoch": 0.43829296424452135, "percentage": 21.92, "elapsed_time": "5:19:05", "remaining_time": "18:56:37"}
+{"current_steps": 960, "total_steps": 4334, "loss": 0.4912, "lr": 9.557844738200408e-06, "epoch": 0.4429065743944637, "percentage": 22.15, "elapsed_time": "5:22:33", "remaining_time": "18:53:38"}
+{"current_steps": 970, "total_steps": 4334, "loss": 0.461, "lr": 9.541137334212212e-06, "epoch": 0.447520184544406, "percentage": 22.38, "elapsed_time": "5:25:46", "remaining_time": "18:49:49"}
+{"current_steps": 980, "total_steps": 4334, "loss": 0.4414, "lr": 9.524135262330098e-06, "epoch": 0.45213379469434833, "percentage": 22.61, "elapsed_time": "5:29:14", "remaining_time": "18:46:49"}
+{"current_steps": 990, "total_steps": 4334, "loss": 0.4457, "lr": 9.506839625794152e-06, "epoch": 0.45674740484429066, "percentage": 22.84, "elapsed_time": "5:32:45", "remaining_time": "18:44:00"}
+{"current_steps": 1000, "total_steps": 4334, "loss": 0.4457, "lr": 9.489251546893441e-06, "epoch": 0.461361014994233, "percentage": 23.07, "elapsed_time": "5:35:59", "remaining_time": "18:40:10"}
+{"current_steps": 1000, "total_steps": 4334, "eval_loss": 0.386065274477005, "epoch": 0.461361014994233, "percentage": 23.07, "elapsed_time": "5:42:39", "remaining_time": "19:02:26"}
+{"current_steps": 1010, "total_steps": 4334, "loss": 0.4457, "lr": 9.4713721668932e-06, "epoch": 0.4659746251441753, "percentage": 23.3, "elapsed_time": "5:48:22", "remaining_time": "19:06:31"}
+{"current_steps": 1020, "total_steps": 4334, "loss": 0.4343, "lr": 9.453202645960775e-06, "epoch": 0.47058823529411764, "percentage": 23.53, "elapsed_time": "5:51:32", "remaining_time": "19:02:11"}
+{"current_steps": 1030, "total_steps": 4334, "loss": 0.402, "lr": 9.434744163090341e-06, "epoch": 0.47520184544405997, "percentage": 23.77, "elapsed_time": "5:54:42", "remaining_time": "18:57:49"}
+{"current_steps": 1040, "total_steps": 4334, "loss": 0.4742, "lr": 9.415997916026401e-06, "epoch": 0.4798154555940023, "percentage": 24.0, "elapsed_time": "5:58:08", "remaining_time": "18:54:19"}
+{"current_steps": 1050, "total_steps": 4334, "loss": 0.4487, "lr": 9.396965121186058e-06, "epoch": 0.4844290657439446, "percentage": 24.23, "elapsed_time": "6:01:12", "remaining_time": "18:49:41"}
+{"current_steps": 1060, "total_steps": 4334, "loss": 0.449, "lr": 9.377647013580102e-06, "epoch": 0.48904267589388695, "percentage": 24.46, "elapsed_time": "6:04:22", "remaining_time": "18:45:26"}
+{"current_steps": 1070, "total_steps": 4334, "loss": 0.4591, "lr": 9.358044846732848e-06, "epoch": 0.4936562860438293, "percentage": 24.69, "elapsed_time": "6:07:37", "remaining_time": "18:41:24"}
+{"current_steps": 1080, "total_steps": 4334, "loss": 0.457, "lr": 9.338159892600809e-06, "epoch": 0.4982698961937716, "percentage": 24.92, "elapsed_time": "6:11:04", "remaining_time": "18:38:01"}
+{"current_steps": 1090, "total_steps": 4334, "loss": 0.4863, "lr": 9.317993441490163e-06, "epoch": 0.5028835063437139, "percentage": 25.15, "elapsed_time": "6:14:13", "remaining_time": "18:33:44"}
+{"current_steps": 1100, "total_steps": 4334, "loss": 0.4863, "lr": 9.297546801973027e-06, "epoch": 0.5074971164936563, "percentage": 25.38, "elapsed_time": "6:17:25", "remaining_time": "18:29:38"}
+{"current_steps": 1110, "total_steps": 4334, "loss": 0.4445, "lr": 9.276821300802535e-06, "epoch": 0.5121107266435986, "percentage": 25.61, "elapsed_time": "6:20:47", "remaining_time": "18:26:01"}
+{"current_steps": 1120, "total_steps": 4334, "loss": 0.4654, "lr": 9.255818282826755e-06, "epoch": 0.5167243367935409, "percentage": 25.84, "elapsed_time": "6:23:59", "remaining_time": "18:21:56"}
+{"current_steps": 1130, "total_steps": 4334, "loss": 0.4164, "lr": 9.23453911090143e-06, "epoch": 0.5213379469434832, "percentage": 26.07, "elapsed_time": "6:27:09", "remaining_time": "18:17:44"}
+{"current_steps": 1140, "total_steps": 4334, "loss": 0.4471, "lr": 9.21298516580153e-06, "epoch": 0.5259515570934256, "percentage": 26.3, "elapsed_time": "6:30:26", "remaining_time": "18:13:54"}
+{"current_steps": 1150, "total_steps": 4334, "loss": 0.438, "lr": 9.191157846131662e-06, "epoch": 0.5305651672433679, "percentage": 26.53, "elapsed_time": "6:33:37", "remaining_time": "18:09:48"}
+{"current_steps": 1160, "total_steps": 4334, "loss": 0.4754, "lr": 9.169058568235324e-06, "epoch": 0.5351787773933102, "percentage": 26.77, "elapsed_time": "6:36:45", "remaining_time": "18:05:35"}
+{"current_steps": 1170, "total_steps": 4334, "loss": 0.4622, "lr": 9.146688766102985e-06, "epoch": 0.5397923875432526, "percentage": 27.0, "elapsed_time": "6:39:43", "remaining_time": "18:00:58"}
+{"current_steps": 1180, "total_steps": 4334, "loss": 0.4778, "lr": 9.124049891279052e-06, "epoch": 0.544405997693195, "percentage": 27.23, "elapsed_time": "6:42:43", "remaining_time": "17:56:26"}
+{"current_steps": 1190, "total_steps": 4334, "loss": 0.43, "lr": 9.101143412767665e-06, "epoch": 0.5490196078431373, "percentage": 27.46, "elapsed_time": "6:45:57", "remaining_time": "17:52:33"}
+{"current_steps": 1200, "total_steps": 4334, "loss": 0.4398, "lr": 9.077970816937394e-06, "epoch": 0.5536332179930796, "percentage": 27.69, "elapsed_time": "6:49:14", "remaining_time": "17:48:48"}
+{"current_steps": 1210, "total_steps": 4334, "loss": 0.4509, "lr": 9.05453360742477e-06, "epoch": 0.558246828143022, "percentage": 27.92, "elapsed_time": "6:52:38", "remaining_time": "17:45:21"}
+{"current_steps": 1220, "total_steps": 4334, "loss": 0.4322, "lr": 9.030833305036732e-06, "epoch": 0.5628604382929643, "percentage": 28.15, "elapsed_time": "6:55:53", "remaining_time": "17:41:33"}
+{"current_steps": 1230, "total_steps": 4334, "loss": 0.4463, "lr": 9.006871447651941e-06, "epoch": 0.5674740484429066, "percentage": 28.38, "elapsed_time": "6:59:08", "remaining_time": "17:37:42"}
+{"current_steps": 1240, "total_steps": 4334, "loss": 0.4744, "lr": 8.982649590120982e-06, "epoch": 0.5720876585928489, "percentage": 28.61, "elapsed_time": "7:02:31", "remaining_time": "17:34:16"}
+{"current_steps": 1250, "total_steps": 4334, "loss": 0.4506, "lr": 8.95816930416548e-06, "epoch": 0.5767012687427913, "percentage": 28.84, "elapsed_time": "7:05:42", "remaining_time": "17:30:18"}
+{"current_steps": 1260, "total_steps": 4334, "loss": 0.5047, "lr": 8.933432178276108e-06, "epoch": 0.5813148788927336, "percentage": 29.07, "elapsed_time": "7:09:05", "remaining_time": "17:26:49"}
+{"current_steps": 1270, "total_steps": 4334, "loss": 0.4331, "lr": 8.908439817609514e-06, "epoch": 0.5859284890426759, "percentage": 29.3, "elapsed_time": "7:12:23", "remaining_time": "17:23:10"}
+{"current_steps": 1280, "total_steps": 4334, "loss": 0.4869, "lr": 8.883193843884169e-06, "epoch": 0.5905420991926182, "percentage": 29.53, "elapsed_time": "7:15:44", "remaining_time": "17:19:39"}
+{"current_steps": 1290, "total_steps": 4334, "loss": 0.4568, "lr": 8.857695895275127e-06, "epoch": 0.5951557093425606, "percentage": 29.76, "elapsed_time": "7:18:47", "remaining_time": "17:15:25"}
+{"current_steps": 1300, "total_steps": 4334, "loss": 0.4291, "lr": 8.831947626307735e-06, "epoch": 0.5997693194925029, "percentage": 30.0, "elapsed_time": "7:21:54", "remaining_time": "17:11:19"}
+{"current_steps": 1310, "total_steps": 4334, "loss": 0.4864, "lr": 8.805950707750268e-06, "epoch": 0.6043829296424452, "percentage": 30.23, "elapsed_time": "7:25:20", "remaining_time": "17:08:00"}
+{"current_steps": 1320, "total_steps": 4334, "loss": 0.4755, "lr": 8.779706826505513e-06, "epoch": 0.6089965397923875, "percentage": 30.46, "elapsed_time": "7:28:46", "remaining_time": "17:04:42"}
+{"current_steps": 1330, "total_steps": 4334, "loss": 0.4429, "lr": 8.753217685501317e-06, "epoch": 0.6136101499423299, "percentage": 30.69, "elapsed_time": "7:32:05", "remaining_time": "17:01:06"}
+{"current_steps": 1340, "total_steps": 4334, "loss": 0.4799, "lr": 8.72648500358008e-06, "epoch": 0.6182237600922722, "percentage": 30.92, "elapsed_time": "7:35:13", "remaining_time": "16:57:08"}
+{"current_steps": 1350, "total_steps": 4334, "loss": 0.4238, "lr": 8.699510515387222e-06, "epoch": 0.6228373702422145, "percentage": 31.15, "elapsed_time": "7:38:34", "remaining_time": "16:53:36"}
+{"current_steps": 1360, "total_steps": 4334, "loss": 0.4621, "lr": 8.672295971258624e-06, "epoch": 0.6274509803921569, "percentage": 31.38, "elapsed_time": "7:41:43", "remaining_time": "16:49:40"}
+{"current_steps": 1370, "total_steps": 4334, "loss": 0.482, "lr": 8.644843137107058e-06, "epoch": 0.6320645905420992, "percentage": 31.61, "elapsed_time": "7:45:08", "remaining_time": "16:46:19"}
+{"current_steps": 1380, "total_steps": 4334, "loss": 0.4138, "lr": 8.617153794307588e-06, "epoch": 0.6366782006920415, "percentage": 31.84, "elapsed_time": "7:48:25", "remaining_time": "16:42:42"}
+{"current_steps": 1390, "total_steps": 4334, "loss": 0.4808, "lr": 8.58922973958199e-06, "epoch": 0.6412918108419838, "percentage": 32.07, "elapsed_time": "7:51:51", "remaining_time": "16:39:24"}
+{"current_steps": 1400, "total_steps": 4334, "loss": 0.4196, "lr": 8.561072784882156e-06, "epoch": 0.6459054209919262, "percentage": 32.3, "elapsed_time": "7:54:59", "remaining_time": "16:35:26"}
+{"current_steps": 1410, "total_steps": 4334, "loss": 0.4675, "lr": 8.532684757272527e-06, "epoch": 0.6505190311418685, "percentage": 32.53, "elapsed_time": "7:58:17", "remaining_time": "16:31:51"}
+{"current_steps": 1420, "total_steps": 4334, "loss": 0.4585, "lr": 8.504067498811533e-06, "epoch": 0.6551326412918108, "percentage": 32.76, "elapsed_time": "8:01:34", "remaining_time": "16:28:14"}
+{"current_steps": 1430, "total_steps": 4334, "loss": 0.4557, "lr": 8.475222866432065e-06, "epoch": 0.6597462514417531, "percentage": 32.99, "elapsed_time": "8:04:56", "remaining_time": "16:24:49"}
+{"current_steps": 1440, "total_steps": 4334, "loss": 0.4378, "lr": 8.446152731820984e-06, "epoch": 0.6643598615916955, "percentage": 33.23, "elapsed_time": "8:08:20", "remaining_time": "16:21:26"}
+{"current_steps": 1450, "total_steps": 4334, "loss": 0.482, "lr": 8.416858981297663e-06, "epoch": 0.6689734717416378, "percentage": 33.46, "elapsed_time": "8:11:53", "remaining_time": "16:18:20"}
+{"current_steps": 1460, "total_steps": 4334, "loss": 0.4153, "lr": 8.387343515691594e-06, "epoch": 0.6735870818915801, "percentage": 33.69, "elapsed_time": "8:15:16", "remaining_time": "16:14:57"}
+{"current_steps": 1470, "total_steps": 4334, "loss": 0.4619, "lr": 8.357608250219046e-06, "epoch": 0.6782006920415224, "percentage": 33.92, "elapsed_time": "8:18:40", "remaining_time": "16:11:34"}
+{"current_steps": 1480, "total_steps": 4334, "loss": 0.4327, "lr": 8.327655114358782e-06, "epoch": 0.6828143021914648, "percentage": 34.15, "elapsed_time": "8:21:55", "remaining_time": "16:07:54"}
+{"current_steps": 1490, "total_steps": 4334, "loss": 0.4713, "lr": 8.297486051726864e-06, "epoch": 0.6874279123414071, "percentage": 34.38, "elapsed_time": "8:25:06", "remaining_time": "16:04:05"}
+{"current_steps": 1500, "total_steps": 4334, "loss": 0.4197, "lr": 8.267103019950529e-06, "epoch": 0.6920415224913494, "percentage": 34.61, "elapsed_time": "8:28:22", "remaining_time": "16:00:28"}
+{"current_steps": 1500, "total_steps": 4334, "eval_loss": 0.3744993507862091, "epoch": 0.6920415224913494, "percentage": 34.61, "elapsed_time": "8:35:11", "remaining_time": "16:13:22"}
+{"current_steps": 1510, "total_steps": 4334, "loss": 0.4525, "lr": 8.23650799054117e-06, "epoch": 0.6966551326412919, "percentage": 34.84, "elapsed_time": "8:40:54", "remaining_time": "16:14:11"}
+{"current_steps": 1520, "total_steps": 4334, "loss": 0.4344, "lr": 8.2057029487664e-06, "epoch": 0.7012687427912342, "percentage": 35.07, "elapsed_time": "8:44:14", "remaining_time": "16:10:32"}
+{"current_steps": 1530, "total_steps": 4334, "loss": 0.4456, "lr": 8.174689893521239e-06, "epoch": 0.7058823529411765, "percentage": 35.3, "elapsed_time": "8:47:41", "remaining_time": "16:07:06"}
+{"current_steps": 1540, "total_steps": 4334, "loss": 0.4342, "lr": 8.143470837198394e-06, "epoch": 0.7104959630911188, "percentage": 35.53, "elapsed_time": "8:51:04", "remaining_time": "16:03:30"}
+{"current_steps": 1550, "total_steps": 4334, "loss": 0.4407, "lr": 8.112047805557693e-06, "epoch": 0.7151095732410612, "percentage": 35.76, "elapsed_time": "8:54:27", "remaining_time": "15:59:58"}
+{"current_steps": 1560, "total_steps": 4334, "loss": 0.4188, "lr": 8.080422837594627e-06, "epoch": 0.7197231833910035, "percentage": 35.99, "elapsed_time": "8:57:39", "remaining_time": "15:56:04"}
+{"current_steps": 1570, "total_steps": 4334, "loss": 0.4594, "lr": 8.048597985408047e-06, "epoch": 0.7243367935409458, "percentage": 36.23, "elapsed_time": "9:00:59", "remaining_time": "15:52:25"}
+{"current_steps": 1580, "total_steps": 4334, "loss": 0.4549, "lr": 8.016575314067005e-06, "epoch": 0.7289504036908881, "percentage": 36.46, "elapsed_time": "9:04:10", "remaining_time": "15:48:31"}
+{"current_steps": 1590, "total_steps": 4334, "loss": 0.4548, "lr": 7.984356901476755e-06, "epoch": 0.7335640138408305, "percentage": 36.69, "elapsed_time": "9:07:27", "remaining_time": "15:44:48"}
+{"current_steps": 1600, "total_steps": 4334, "loss": 0.4452, "lr": 7.951944838243916e-06, "epoch": 0.7381776239907728, "percentage": 36.92, "elapsed_time": "9:10:40", "remaining_time": "15:40:58"}
+{"current_steps": 1610, "total_steps": 4334, "loss": 0.4491, "lr": 7.919341227540828e-06, "epoch": 0.7427912341407151, "percentage": 37.15, "elapsed_time": "9:13:54", "remaining_time": "15:37:10"}
+{"current_steps": 1620, "total_steps": 4334, "loss": 0.4731, "lr": 7.886548184969063e-06, "epoch": 0.7474048442906575, "percentage": 37.38, "elapsed_time": "9:17:25", "remaining_time": "15:33:51"}
+{"current_steps": 1630, "total_steps": 4334, "loss": 0.432, "lr": 7.85356783842216e-06, "epoch": 0.7520184544405998, "percentage": 37.61, "elapsed_time": "9:20:44", "remaining_time": "15:30:12"}
+{"current_steps": 1640, "total_steps": 4334, "loss": 0.461, "lr": 7.820402327947543e-06, "epoch": 0.7566320645905421, "percentage": 37.84, "elapsed_time": "9:24:02", "remaining_time": "15:26:33"}
+{"current_steps": 1650, "total_steps": 4334, "loss": 0.4118, "lr": 7.78705380560766e-06, "epoch": 0.7612456747404844, "percentage": 38.07, "elapsed_time": "9:27:34", "remaining_time": "15:23:16"}
+{"current_steps": 1660, "total_steps": 4334, "loss": 0.445, "lr": 7.753524435340334e-06, "epoch": 0.7658592848904268, "percentage": 38.3, "elapsed_time": "9:31:08", "remaining_time": "15:20:00"}
+{"current_steps": 1670, "total_steps": 4334, "loss": 0.453, "lr": 7.719816392818354e-06, "epoch": 0.7704728950403691, "percentage": 38.53, "elapsed_time": "9:34:37", "remaining_time": "15:16:38"}
+{"current_steps": 1680, "total_steps": 4334, "loss": 0.4424, "lr": 7.685931865308293e-06, "epoch": 0.7750865051903114, "percentage": 38.76, "elapsed_time": "9:38:04", "remaining_time": "15:13:12"}
+{"current_steps": 1690, "total_steps": 4334, "loss": 0.4164, "lr": 7.651873051528582e-06, "epoch": 0.7797001153402537, "percentage": 38.99, "elapsed_time": "9:41:19", "remaining_time": "15:09:28"}
+{"current_steps": 1700, "total_steps": 4334, "loss": 0.4345, "lr": 7.617642161506837e-06, "epoch": 0.7843137254901961, "percentage": 39.22, "elapsed_time": "9:44:23", "remaining_time": "15:05:27"}
+{"current_steps": 1710, "total_steps": 4334, "loss": 0.4373, "lr": 7.583241416436462e-06, "epoch": 0.7889273356401384, "percentage": 39.46, "elapsed_time": "9:47:35", "remaining_time": "15:01:39"}
+{"current_steps": 1720, "total_steps": 4334, "loss": 0.4146, "lr": 7.548673048532504e-06, "epoch": 0.7935409457900807, "percentage": 39.69, "elapsed_time": "9:50:49", "remaining_time": "14:57:55"}
+{"current_steps": 1730, "total_steps": 4334, "loss": 0.4008, "lr": 7.513939300886816e-06, "epoch": 0.798154555940023, "percentage": 39.92, "elapsed_time": "9:53:50", "remaining_time": "14:53:50"}
+{"current_steps": 1740, "total_steps": 4334, "loss": 0.4401, "lr": 7.479042427322509e-06, "epoch": 0.8027681660899654, "percentage": 40.15, "elapsed_time": "9:56:59", "remaining_time": "14:49:59"}
+{"current_steps": 1750, "total_steps": 4334, "loss": 0.4565, "lr": 7.443984692247701e-06, "epoch": 0.8073817762399077, "percentage": 40.38, "elapsed_time": "10:00:04", "remaining_time": "14:46:02"}
+{"current_steps": 1760, "total_steps": 4334, "loss": 0.432, "lr": 7.408768370508577e-06, "epoch": 0.81199538638985, "percentage": 40.61, "elapsed_time": "10:03:28", "remaining_time": "14:42:35"}
+{"current_steps": 1770, "total_steps": 4334, "loss": 0.3847, "lr": 7.373395747241792e-06, "epoch": 0.8166089965397924, "percentage": 40.84, "elapsed_time": "10:06:52", "remaining_time": "14:39:06"}
+{"current_steps": 1780, "total_steps": 4334, "loss": 0.412, "lr": 7.337869117726176e-06, "epoch": 0.8212226066897347, "percentage": 41.07, "elapsed_time": "10:10:13", "remaining_time": "14:35:34"}
+{"current_steps": 1790, "total_steps": 4334, "loss": 0.4462, "lr": 7.302190787233808e-06, "epoch": 0.825836216839677, "percentage": 41.3, "elapsed_time": "10:13:28", "remaining_time": "14:31:53"}
+{"current_steps": 1800, "total_steps": 4334, "loss": 0.4321, "lr": 7.266363070880424e-06, "epoch": 0.8304498269896193, "percentage": 41.53, "elapsed_time": "10:16:40", "remaining_time": "14:28:08"}
+{"current_steps": 1810, "total_steps": 4334, "loss": 0.4477, "lr": 7.2303882934751965e-06, "epoch": 0.8350634371395617, "percentage": 41.76, "elapsed_time": "10:19:58", "remaining_time": "14:24:32"}
+{"current_steps": 1820, "total_steps": 4334, "loss": 0.4028, "lr": 7.194268789369875e-06, "epoch": 0.839677047289504, "percentage": 41.99, "elapsed_time": "10:23:15", "remaining_time": "14:20:55"}
+{"current_steps": 1830, "total_steps": 4334, "loss": 0.457, "lr": 7.158006902307322e-06, "epoch": 0.8442906574394463, "percentage": 42.22, "elapsed_time": "10:26:25", "remaining_time": "14:17:07"}
+{"current_steps": 1840, "total_steps": 4334, "loss": 0.4248, "lr": 7.121604985269423e-06, "epoch": 0.8489042675893888, "percentage": 42.46, "elapsed_time": "10:29:30", "remaining_time": "14:13:15"}
+{"current_steps": 1850, "total_steps": 4334, "loss": 0.4731, "lr": 7.085065400324407e-06, "epoch": 0.8535178777393311, "percentage": 42.69, "elapsed_time": "10:32:40", "remaining_time": "14:09:29"}
+{"current_steps": 1860, "total_steps": 4334, "loss": 0.3925, "lr": 7.048390518473579e-06, "epoch": 0.8581314878892734, "percentage": 42.92, "elapsed_time": "10:35:53", "remaining_time": "14:05:47"}
+{"current_steps": 1870, "total_steps": 4334, "loss": 0.4481, "lr": 7.011582719497466e-06, "epoch": 0.8627450980392157, "percentage": 43.15, "elapsed_time": "10:39:11", "remaining_time": "14:02:14"}
+{"current_steps": 1880, "total_steps": 4334, "loss": 0.4487, "lr": 6.974644391801395e-06, "epoch": 0.8673587081891581, "percentage": 43.38, "elapsed_time": "10:42:18", "remaining_time": "13:58:24"}
+{"current_steps": 1890, "total_steps": 4334, "loss": 0.4424, "lr": 6.9375779322605154e-06, "epoch": 0.8719723183391004, "percentage": 43.61, "elapsed_time": "10:45:26", "remaining_time": "13:54:37"}
+{"current_steps": 1900, "total_steps": 4334, "loss": 0.4628, "lr": 6.900385746064268e-06, "epoch": 0.8765859284890427, "percentage": 43.84, "elapsed_time": "10:48:39", "remaining_time": "13:50:57"}
+{"current_steps": 1910, "total_steps": 4334, "loss": 0.4194, "lr": 6.863070246560319e-06, "epoch": 0.881199538638985, "percentage": 44.07, "elapsed_time": "10:51:57", "remaining_time": "13:47:24"}
+{"current_steps": 1920, "total_steps": 4334, "loss": 0.4404, "lr": 6.825633855097954e-06, "epoch": 0.8858131487889274, "percentage": 44.3, "elapsed_time": "10:55:19", "remaining_time": "13:43:56"}
+{"current_steps": 1930, "total_steps": 4334, "loss": 0.4654, "lr": 6.788079000870966e-06, "epoch": 0.8904267589388697, "percentage": 44.53, "elapsed_time": "10:58:42", "remaining_time": "13:40:29"}
+{"current_steps": 1940, "total_steps": 4334, "loss": 0.4849, "lr": 6.7504081207600295e-06, "epoch": 0.895040369088812, "percentage": 44.76, "elapsed_time": "11:02:10", "remaining_time": "13:37:08"}
+{"current_steps": 1950, "total_steps": 4334, "loss": 0.4286, "lr": 6.712623659174569e-06, "epoch": 0.8996539792387543, "percentage": 44.99, "elapsed_time": "11:05:27", "remaining_time": "13:33:33"}
+{"current_steps": 1960, "total_steps": 4334, "loss": 0.4271, "lr": 6.674728067894149e-06, "epoch": 0.9042675893886967, "percentage": 45.22, "elapsed_time": "11:08:58", "remaining_time": "13:30:16"}
+{"current_steps": 1970, "total_steps": 4334, "loss": 0.4384, "lr": 6.636723805909384e-06, "epoch": 0.908881199538639, "percentage": 45.45, "elapsed_time": "11:12:18", "remaining_time": "13:26:46"}
+{"current_steps": 1980, "total_steps": 4334, "loss": 0.4058, "lr": 6.598613339262369e-06, "epoch": 0.9134948096885813, "percentage": 45.69, "elapsed_time": "11:15:27", "remaining_time": "13:23:02"}
+{"current_steps": 1990, "total_steps": 4334, "loss": 0.4047, "lr": 6.560399140886673e-06, "epoch": 0.9181084198385236, "percentage": 45.92, "elapsed_time": "11:18:52", "remaining_time": "13:19:38"}
+{"current_steps": 2000, "total_steps": 4334, "loss": 0.4264, "lr": 6.522083690446863e-06, "epoch": 0.922722029988466, "percentage": 46.15, "elapsed_time": "11:22:19", "remaining_time": "13:16:16"}
+{"current_steps": 2000, "total_steps": 4334, "eval_loss": 0.3640458583831787, "epoch": 0.922722029988466, "percentage": 46.15, "elapsed_time": "11:29:04", "remaining_time": "13:24:09"}
+{"current_steps": 2010, "total_steps": 4334, "loss": 0.4309, "lr": 6.483669474177609e-06, "epoch": 0.9273356401384083, "percentage": 46.38, "elapsed_time": "11:35:08", "remaining_time": "13:23:44"}
+{"current_steps": 2020, "total_steps": 4334, "loss": 0.4321, "lr": 6.445158984722358e-06, "epoch": 0.9319492502883506, "percentage": 46.61, "elapsed_time": "11:38:39", "remaining_time": "13:20:20"}
+{"current_steps": 2030, "total_steps": 4334, "loss": 0.4118, "lr": 6.406554720971583e-06, "epoch": 0.936562860438293, "percentage": 46.84, "elapsed_time": "11:41:54", "remaining_time": "13:16:38"}
+{"current_steps": 2040, "total_steps": 4334, "loss": 0.4508, "lr": 6.367859187900635e-06, "epoch": 0.9411764705882353, "percentage": 47.07, "elapsed_time": "11:45:06", "remaining_time": "13:12:53"}
+{"current_steps": 2050, "total_steps": 4334, "loss": 0.4088, "lr": 6.329074896407202e-06, "epoch": 0.9457900807381776, "percentage": 47.3, "elapsed_time": "11:48:15", "remaining_time": "13:09:06"}
+{"current_steps": 2060, "total_steps": 4334, "loss": 0.4, "lr": 6.29020436314838e-06, "epoch": 0.9504036908881199, "percentage": 47.53, "elapsed_time": "11:51:42", "remaining_time": "13:05:38"}
+{"current_steps": 2070, "total_steps": 4334, "loss": 0.4122, "lr": 6.251250110377368e-06, "epoch": 0.9550173010380623, "percentage": 47.76, "elapsed_time": "11:55:12", "remaining_time": "13:02:14"}
+{"current_steps": 2080, "total_steps": 4334, "loss": 0.4449, "lr": 6.212214665779805e-06, "epoch": 0.9596309111880046, "percentage": 47.99, "elapsed_time": "11:58:37", "remaining_time": "12:58:44"}
+{"current_steps": 2090, "total_steps": 4334, "loss": 0.4229, "lr": 6.173100562309751e-06, "epoch": 0.9642445213379469, "percentage": 48.22, "elapsed_time": "12:01:49", "remaining_time": "12:55:00"}
+{"current_steps": 2100, "total_steps": 4334, "loss": 0.4389, "lr": 6.133910338025329e-06, "epoch": 0.9688581314878892, "percentage": 48.45, "elapsed_time": "12:05:22", "remaining_time": "12:51:39"}
+{"current_steps": 2110, "total_steps": 4334, "loss": 0.4459, "lr": 6.094646535924026e-06, "epoch": 0.9734717416378316, "percentage": 48.68, "elapsed_time": "12:08:47", "remaining_time": "12:48:10"}
+{"current_steps": 2120, "total_steps": 4334, "loss": 0.4556, "lr": 6.055311703777699e-06, "epoch": 0.9780853517877739, "percentage": 48.92, "elapsed_time": "12:11:52", "remaining_time": "12:44:19"}
+{"current_steps": 2130, "total_steps": 4334, "loss": 0.4837, "lr": 6.0159083939672326e-06, "epoch": 0.9826989619377162, "percentage": 49.15, "elapsed_time": "12:14:59", "remaining_time": "12:40:31"}
+{"current_steps": 2140, "total_steps": 4334, "loss": 0.4119, "lr": 5.976439163316936e-06, "epoch": 0.9873125720876585, "percentage": 49.38, "elapsed_time": "12:18:20", "remaining_time": "12:36:58"}
+{"current_steps": 2150, "total_steps": 4334, "loss": 0.4391, "lr": 5.936906572928625e-06, "epoch": 0.9919261822376009, "percentage": 49.61, "elapsed_time": "12:21:46", "remaining_time": "12:33:30"}
+{"current_steps": 2160, "total_steps": 4334, "loss": 0.4175, "lr": 5.897313188015433e-06, "epoch": 0.9965397923875432, "percentage": 49.84, "elapsed_time": "12:25:00", "remaining_time": "12:29:50"}
+{"current_steps": 2170, "total_steps": 4334, "loss": 0.4176, "lr": 5.8576615777353725e-06, "epoch": 1.0009227220299886, "percentage": 50.07, "elapsed_time": "12:28:05", "remaining_time": "12:26:01"}
+{"current_steps": 2180, "total_steps": 4334, "loss": 0.3182, "lr": 5.81795431502461e-06, "epoch": 1.0055363321799309, "percentage": 50.3, "elapsed_time": "12:31:27", "remaining_time": "12:22:30"}
+{"current_steps": 2190, "total_steps": 4334, "loss": 0.3412, "lr": 5.778193976430518e-06, "epoch": 1.0101499423298732, "percentage": 50.53, "elapsed_time": "12:34:43", "remaining_time": "12:18:51"}
+{"current_steps": 2200, "total_steps": 4334, "loss": 0.3254, "lr": 5.738383141944493e-06, "epoch": 1.0147635524798155, "percentage": 50.76, "elapsed_time": "12:37:52", "remaining_time": "12:15:08"}
+{"current_steps": 2210, "total_steps": 4334, "loss": 0.3121, "lr": 5.698524394834531e-06, "epoch": 1.0193771626297579, "percentage": 50.99, "elapsed_time": "12:41:08", "remaining_time": "12:11:31"}
+{"current_steps": 2220, "total_steps": 4334, "loss": 0.309, "lr": 5.658620321477613e-06, "epoch": 1.0239907727797002, "percentage": 51.22, "elapsed_time": "12:44:23", "remaining_time": "12:07:53"}
+{"current_steps": 2230, "total_steps": 4334, "loss": 0.2945, "lr": 5.6186735111918735e-06, "epoch": 1.0286043829296425, "percentage": 51.45, "elapsed_time": "12:47:40", "remaining_time": "12:04:17"}
+{"current_steps": 2240, "total_steps": 4334, "loss": 0.3277, "lr": 5.5786865560685855e-06, "epoch": 1.0332179930795848, "percentage": 51.68, "elapsed_time": "12:50:51", "remaining_time": "12:00:36"}
+{"current_steps": 2250, "total_steps": 4334, "loss": 0.3337, "lr": 5.538662050803965e-06, "epoch": 1.0378316032295272, "percentage": 51.92, "elapsed_time": "12:54:19", "remaining_time": "11:57:11"}
+{"current_steps": 2260, "total_steps": 4334, "loss": 0.3145, "lr": 5.498602592530799e-06, "epoch": 1.0424452133794695, "percentage": 52.15, "elapsed_time": "12:57:33", "remaining_time": "11:53:33"}
+{"current_steps": 2270, "total_steps": 4334, "loss": 0.3016, "lr": 5.458510780649932e-06, "epoch": 1.0470588235294118, "percentage": 52.38, "elapsed_time": "13:00:53", "remaining_time": "11:50:01"}
+{"current_steps": 2280, "total_steps": 4334, "loss": 0.3107, "lr": 5.41838921666158e-06, "epoch": 1.0516724336793541, "percentage": 52.61, "elapsed_time": "13:04:04", "remaining_time": "11:46:21"}
+{"current_steps": 2290, "total_steps": 4334, "loss": 0.313, "lr": 5.378240503996531e-06, "epoch": 1.0562860438292965, "percentage": 52.84, "elapsed_time": "13:07:15", "remaining_time": "11:42:40"}
+{"current_steps": 2300, "total_steps": 4334, "loss": 0.3186, "lr": 5.338067247847219e-06, "epoch": 1.0608996539792388, "percentage": 53.07, "elapsed_time": "13:10:42", "remaining_time": "11:39:15"}
+{"current_steps": 2310, "total_steps": 4334, "loss": 0.3198, "lr": 5.297872054998663e-06, "epoch": 1.0655132641291811, "percentage": 53.3, "elapsed_time": "13:14:08", "remaining_time": "11:35:48"}
+{"current_steps": 2320, "total_steps": 4334, "loss": 0.3181, "lr": 5.257657533659326e-06, "epoch": 1.0701268742791235, "percentage": 53.53, "elapsed_time": "13:17:24", "remaining_time": "11:32:13"}
+{"current_steps": 2330, "total_steps": 4334, "loss": 0.3369, "lr": 5.217426293291869e-06, "epoch": 1.0747404844290658, "percentage": 53.76, "elapsed_time": "13:20:38", "remaining_time": "11:28:37"}
+{"current_steps": 2340, "total_steps": 4334, "loss": 0.311, "lr": 5.177180944443821e-06, "epoch": 1.079354094579008, "percentage": 53.99, "elapsed_time": "13:23:57", "remaining_time": "11:25:04"}
+{"current_steps": 2350, "total_steps": 4334, "loss": 0.3109, "lr": 5.136924098578201e-06, "epoch": 1.0839677047289504, "percentage": 54.22, "elapsed_time": "13:27:13", "remaining_time": "11:21:29"}
+{"current_steps": 2360, "total_steps": 4334, "loss": 0.2808, "lr": 5.096658367904043e-06, "epoch": 1.0885813148788928, "percentage": 54.45, "elapsed_time": "13:30:35", "remaining_time": "11:18:01"}
+{"current_steps": 2370, "total_steps": 4334, "loss": 0.3435, "lr": 5.056386365206908e-06, "epoch": 1.093194925028835, "percentage": 54.68, "elapsed_time": "13:33:46", "remaining_time": "11:14:22"}
+{"current_steps": 2380, "total_steps": 4334, "loss": 0.3141, "lr": 5.016110703679341e-06, "epoch": 1.0978085351787774, "percentage": 54.91, "elapsed_time": "13:37:14", "remaining_time": "11:10:57"}
+{"current_steps": 2390, "total_steps": 4334, "loss": 0.3074, "lr": 4.9758339967512995e-06, "epoch": 1.1024221453287197, "percentage": 55.15, "elapsed_time": "13:40:43", "remaining_time": "11:07:34"}
+{"current_steps": 2400, "total_steps": 4334, "loss": 0.3255, "lr": 4.935558857920576e-06, "epoch": 1.107035755478662, "percentage": 55.38, "elapsed_time": "13:44:10", "remaining_time": "11:04:09"}
+{"current_steps": 2410, "total_steps": 4334, "loss": 0.3007, "lr": 4.895287900583216e-06, "epoch": 1.1116493656286044, "percentage": 55.61, "elapsed_time": "13:47:20", "remaining_time": "11:00:29"}
+{"current_steps": 2420, "total_steps": 4334, "loss": 0.3383, "lr": 4.855023737863927e-06, "epoch": 1.1162629757785467, "percentage": 55.84, "elapsed_time": "13:50:37", "remaining_time": "10:56:57"}
+{"current_steps": 2430, "total_steps": 4334, "loss": 0.3207, "lr": 4.814768982446532e-06, "epoch": 1.120876585928489, "percentage": 56.07, "elapsed_time": "13:53:56", "remaining_time": "10:53:25"}
+{"current_steps": 2440, "total_steps": 4334, "loss": 0.3069, "lr": 4.774526246404417e-06, "epoch": 1.1254901960784314, "percentage": 56.3, "elapsed_time": "13:57:01", "remaining_time": "10:49:43"}
+{"current_steps": 2450, "total_steps": 4334, "loss": 0.2949, "lr": 4.734298141031057e-06, "epoch": 1.1301038062283737, "percentage": 56.53, "elapsed_time": "14:00:12", "remaining_time": "10:46:06"}
+{"current_steps": 2460, "total_steps": 4334, "loss": 0.3602, "lr": 4.69408727667056e-06, "epoch": 1.134717416378316, "percentage": 56.76, "elapsed_time": "14:03:22", "remaining_time": "10:42:28"}
+{"current_steps": 2470, "total_steps": 4334, "loss": 0.2999, "lr": 4.653896262548291e-06, "epoch": 1.1393310265282584, "percentage": 56.99, "elapsed_time": "14:06:36", "remaining_time": "10:38:53"}
+{"current_steps": 2480, "total_steps": 4334, "loss": 0.3186, "lr": 4.613727706601558e-06, "epoch": 1.1439446366782007, "percentage": 57.22, "elapsed_time": "14:10:04", "remaining_time": "10:35:29"}
+{"current_steps": 2490, "total_steps": 4334, "loss": 0.2857, "lr": 4.573584215310394e-06, "epoch": 1.148558246828143, "percentage": 57.45, "elapsed_time": "14:13:34", "remaining_time": "10:32:07"}
+{"current_steps": 2500, "total_steps": 4334, "loss": 0.3188, "lr": 4.533468393528421e-06, "epoch": 1.1531718569780853, "percentage": 57.68, "elapsed_time": "14:17:00", "remaining_time": "10:28:41"}
+{"current_steps": 2500, "total_steps": 4334, "eval_loss": 0.36377301812171936, "epoch": 1.1531718569780853, "percentage": 57.68, "elapsed_time": "14:24:12", "remaining_time": "10:33:58"}
+{"current_steps": 2510, "total_steps": 4334, "loss": 0.3255, "lr": 4.493382844313826e-06, "epoch": 1.1577854671280277, "percentage": 57.91, "elapsed_time": "14:30:19", "remaining_time": "10:32:27"}
+{"current_steps": 2520, "total_steps": 4334, "loss": 0.3408, "lr": 4.453330168760451e-06, "epoch": 1.16239907727797, "percentage": 58.14, "elapsed_time": "14:33:37", "remaining_time": "10:28:52"}
+{"current_steps": 2530, "total_steps": 4334, "loss": 0.3562, "lr": 4.41331296582902e-06, "epoch": 1.1670126874279123, "percentage": 58.38, "elapsed_time": "14:37:00", "remaining_time": "10:25:20"}
+{"current_steps": 2540, "total_steps": 4334, "loss": 0.3049, "lr": 4.373333832178478e-06, "epoch": 1.1716262975778546, "percentage": 58.61, "elapsed_time": "14:40:23", "remaining_time": "10:21:49"}
+{"current_steps": 2550, "total_steps": 4334, "loss": 0.3223, "lr": 4.333395361997521e-06, "epoch": 1.176239907727797, "percentage": 58.84, "elapsed_time": "14:43:30", "remaining_time": "10:18:06"}
+{"current_steps": 2560, "total_steps": 4334, "loss": 0.2913, "lr": 4.293500146836241e-06, "epoch": 1.1808535178777393, "percentage": 59.07, "elapsed_time": "14:46:56", "remaining_time": "10:14:37"}
+{"current_steps": 2570, "total_steps": 4334, "loss": 0.2823, "lr": 4.25365077543798e-06, "epoch": 1.1854671280276816, "percentage": 59.3, "elapsed_time": "14:50:16", "remaining_time": "10:11:03"}
+{"current_steps": 2580, "total_steps": 4334, "loss": 0.3583, "lr": 4.213849833571341e-06, "epoch": 1.190080738177624, "percentage": 59.53, "elapsed_time": "14:53:43", "remaining_time": "10:07:35"}
+{"current_steps": 2590, "total_steps": 4334, "loss": 0.3101, "lr": 4.174099903862403e-06, "epoch": 1.1946943483275663, "percentage": 59.76, "elapsed_time": "14:57:02", "remaining_time": "10:04:02"}
+{"current_steps": 2600, "total_steps": 4334, "loss": 0.3311, "lr": 4.134403565627144e-06, "epoch": 1.1993079584775086, "percentage": 59.99, "elapsed_time": "15:00:22", "remaining_time": "10:00:28"}
+{"current_steps": 2610, "total_steps": 4334, "loss": 0.3437, "lr": 4.0947633947040616e-06, "epoch": 1.203921568627451, "percentage": 60.22, "elapsed_time": "15:03:31", "remaining_time": "9:56:48"}
+{"current_steps": 2620, "total_steps": 4334, "loss": 0.2788, "lr": 4.055181963287044e-06, "epoch": 1.2085351787773932, "percentage": 60.45, "elapsed_time": "15:07:06", "remaining_time": "9:53:25"}
+{"current_steps": 2630, "total_steps": 4334, "loss": 0.3188, "lr": 4.01566183975845e-06, "epoch": 1.2131487889273356, "percentage": 60.68, "elapsed_time": "15:10:23", "remaining_time": "9:49:51"}
+{"current_steps": 2640, "total_steps": 4334, "loss": 0.2936, "lr": 3.9762055885224614e-06, "epoch": 1.217762399077278, "percentage": 60.91, "elapsed_time": "15:13:35", "remaining_time": "9:46:13"}
+{"current_steps": 2650, "total_steps": 4334, "loss": 0.266, "lr": 3.936815769838682e-06, "epoch": 1.2223760092272202, "percentage": 61.14, "elapsed_time": "15:16:39", "remaining_time": "9:42:30"}
+{"current_steps": 2660, "total_steps": 4334, "loss": 0.315, "lr": 3.897494939655996e-06, "epoch": 1.2269896193771626, "percentage": 61.38, "elapsed_time": "15:19:39", "remaining_time": "9:38:45"}
+{"current_steps": 2670, "total_steps": 4334, "loss": 0.3161, "lr": 3.8582456494467214e-06, "epoch": 1.2316032295271049, "percentage": 61.61, "elapsed_time": "15:23:04", "remaining_time": "9:35:16"}
+{"current_steps": 2680, "total_steps": 4334, "loss": 0.3216, "lr": 3.819070446041059e-06, "epoch": 1.2362168396770472, "percentage": 61.84, "elapsed_time": "15:26:08", "remaining_time": "9:31:34"}
+{"current_steps": 2690, "total_steps": 4334, "loss": 0.3184, "lr": 3.779971871461813e-06, "epoch": 1.2408304498269895, "percentage": 62.07, "elapsed_time": "15:29:15", "remaining_time": "9:27:55"}
+{"current_steps": 2700, "total_steps": 4334, "loss": 0.3097, "lr": 3.7409524627594607e-06, "epoch": 1.2454440599769319, "percentage": 62.3, "elapsed_time": "15:32:38", "remaining_time": "9:24:25"}
+{"current_steps": 2710, "total_steps": 4334, "loss": 0.2805, "lr": 3.702014751847514e-06, "epoch": 1.2500576701268744, "percentage": 62.53, "elapsed_time": "15:35:42", "remaining_time": "9:20:44"}
+{"current_steps": 2720, "total_steps": 4334, "loss": 0.3199, "lr": 3.6631612653382354e-06, "epoch": 1.2546712802768165, "percentage": 62.76, "elapsed_time": "15:39:02", "remaining_time": "9:17:12"}
+{"current_steps": 2730, "total_steps": 4334, "loss": 0.3204, "lr": 3.624394524378684e-06, "epoch": 1.259284890426759, "percentage": 62.99, "elapsed_time": "15:42:21", "remaining_time": "9:13:40"}
+{"current_steps": 2740, "total_steps": 4334, "loss": 0.3378, "lr": 3.585717044487126e-06, "epoch": 1.2638985005767012, "percentage": 63.22, "elapsed_time": "15:45:30", "remaining_time": "9:10:02"}
+{"current_steps": 2750, "total_steps": 4334, "loss": 0.3073, "lr": 3.5471313353898056e-06, "epoch": 1.2685121107266437, "percentage": 63.45, "elapsed_time": "15:48:32", "remaining_time": "9:06:21"}
+{"current_steps": 2760, "total_steps": 4334, "loss": 0.3255, "lr": 3.5086399008580885e-06, "epoch": 1.2731257208765858, "percentage": 63.68, "elapsed_time": "15:51:39", "remaining_time": "9:02:43"}
+{"current_steps": 2770, "total_steps": 4334, "loss": 0.3108, "lr": 3.470245238546002e-06, "epoch": 1.2777393310265284, "percentage": 63.91, "elapsed_time": "15:54:37", "remaining_time": "8:59:00"}
+{"current_steps": 2780, "total_steps": 4334, "loss": 0.2944, "lr": 3.4319498398281638e-06, "epoch": 1.2823529411764705, "percentage": 64.14, "elapsed_time": "15:57:43", "remaining_time": "8:55:21"}
+{"current_steps": 2790, "total_steps": 4334, "loss": 0.3167, "lr": 3.393756189638115e-06, "epoch": 1.286966551326413, "percentage": 64.37, "elapsed_time": "16:00:49", "remaining_time": "8:51:43"}
+{"current_steps": 2800, "total_steps": 4334, "loss": 0.3009, "lr": 3.355666766307084e-06, "epoch": 1.2915801614763551, "percentage": 64.61, "elapsed_time": "16:03:54", "remaining_time": "8:48:04"}
+{"current_steps": 2810, "total_steps": 4334, "loss": 0.2878, "lr": 3.3176840414031653e-06, "epoch": 1.2961937716262977, "percentage": 64.84, "elapsed_time": "16:06:57", "remaining_time": "8:44:25"}
+{"current_steps": 2820, "total_steps": 4334, "loss": 0.2743, "lr": 3.2798104795709484e-06, "epoch": 1.3008073817762398, "percentage": 65.07, "elapsed_time": "16:10:16", "remaining_time": "8:40:55"}
+{"current_steps": 2830, "total_steps": 4334, "loss": 0.3117, "lr": 3.242048538371585e-06, "epoch": 1.3054209919261823, "percentage": 65.3, "elapsed_time": "16:13:17", "remaining_time": "8:37:15"}
+{"current_steps": 2840, "total_steps": 4334, "loss": 0.3065, "lr": 3.2044006681233226e-06, "epoch": 1.3100346020761244, "percentage": 65.53, "elapsed_time": "16:16:27", "remaining_time": "8:33:40"}
+{"current_steps": 2850, "total_steps": 4334, "loss": 0.3182, "lr": 3.1668693117425128e-06, "epoch": 1.314648212226067, "percentage": 65.76, "elapsed_time": "16:19:44", "remaining_time": "8:30:09"}
+{"current_steps": 2860, "total_steps": 4334, "loss": 0.3362, "lr": 3.1294569045850844e-06, "epoch": 1.3192618223760093, "percentage": 65.99, "elapsed_time": "16:22:53", "remaining_time": "8:26:33"}
+{"current_steps": 2870, "total_steps": 4334, "loss": 0.3202, "lr": 3.092165874288525e-06, "epoch": 1.3238754325259516, "percentage": 66.22, "elapsed_time": "16:26:05", "remaining_time": "8:23:00"}
+{"current_steps": 2880, "total_steps": 4334, "loss": 0.3061, "lr": 3.05499864061435e-06, "epoch": 1.328489042675894, "percentage": 66.45, "elapsed_time": "16:29:20", "remaining_time": "8:19:28"}
+{"current_steps": 2890, "total_steps": 4334, "loss": 0.2937, "lr": 3.017957615291088e-06, "epoch": 1.3331026528258363, "percentage": 66.68, "elapsed_time": "16:32:48", "remaining_time": "8:16:03"}
+{"current_steps": 2900, "total_steps": 4334, "loss": 0.3056, "lr": 2.981045201857796e-06, "epoch": 1.3377162629757786, "percentage": 66.91, "elapsed_time": "16:36:02", "remaining_time": "8:12:31"}
+{"current_steps": 2910, "total_steps": 4334, "loss": 0.2964, "lr": 2.9442637955080787e-06, "epoch": 1.342329873125721, "percentage": 67.14, "elapsed_time": "16:39:20", "remaining_time": "8:09:01"}
+{"current_steps": 2920, "total_steps": 4334, "loss": 0.322, "lr": 2.9076157829346883e-06, "epoch": 1.3469434832756633, "percentage": 67.37, "elapsed_time": "16:42:26", "remaining_time": "8:05:25"}
+{"current_steps": 2930, "total_steps": 4334, "loss": 0.3186, "lr": 2.871103542174637e-06, "epoch": 1.3515570934256056, "percentage": 67.6, "elapsed_time": "16:45:28", "remaining_time": "8:01:48"}
+{"current_steps": 2940, "total_steps": 4334, "loss": 0.2989, "lr": 2.8347294424549075e-06, "epoch": 1.356170703575548, "percentage": 67.84, "elapsed_time": "16:48:39", "remaining_time": "7:58:15"}
+{"current_steps": 2950, "total_steps": 4334, "loss": 0.3095, "lr": 2.7984958440387045e-06, "epoch": 1.3607843137254902, "percentage": 68.07, "elapsed_time": "16:51:48", "remaining_time": "7:54:41"}
+{"current_steps": 2960, "total_steps": 4334, "loss": 0.3209, "lr": 2.7624050980723032e-06, "epoch": 1.3653979238754326, "percentage": 68.3, "elapsed_time": "16:54:56", "remaining_time": "7:51:07"}
+{"current_steps": 2970, "total_steps": 4334, "loss": 0.3238, "lr": 2.726459546432488e-06, "epoch": 1.370011534025375, "percentage": 68.53, "elapsed_time": "16:57:57", "remaining_time": "7:47:30"}
+{"current_steps": 2980, "total_steps": 4334, "loss": 0.2856, "lr": 2.690661521574596e-06, "epoch": 1.3746251441753172, "percentage": 68.76, "elapsed_time": "17:00:55", "remaining_time": "7:43:52"}
+{"current_steps": 2990, "total_steps": 4334, "loss": 0.3145, "lr": 2.655013346381158e-06, "epoch": 1.3792387543252596, "percentage": 68.99, "elapsed_time": "17:04:17", "remaining_time": "7:40:25"}
+{"current_steps": 3000, "total_steps": 4334, "loss": 0.2938, "lr": 2.6195173340111767e-06, "epoch": 1.3838523644752019, "percentage": 69.22, "elapsed_time": "17:07:25", "remaining_time": "7:36:51"}
+{"current_steps": 3000, "total_steps": 4334, "eval_loss": 0.3571609854698181, "epoch": 1.3838523644752019, "percentage": 69.22, "elapsed_time": "17:14:12", "remaining_time": "7:39:52"}
+{"current_steps": 3010, "total_steps": 4334, "loss": 0.2978, "lr": 2.5841757877500245e-06, "epoch": 1.3884659746251442, "percentage": 69.45, "elapsed_time": "17:19:48", "remaining_time": "7:37:22"}
+{"current_steps": 3020, "total_steps": 4334, "loss": 0.2824, "lr": 2.548991000859997e-06, "epoch": 1.3930795847750865, "percentage": 69.68, "elapsed_time": "17:22:59", "remaining_time": "7:33:48"}
+{"current_steps": 3030, "total_steps": 4334, "loss": 0.3256, "lr": 2.513965256431488e-06, "epoch": 1.3976931949250289, "percentage": 69.91, "elapsed_time": "17:26:07", "remaining_time": "7:30:12"}
+{"current_steps": 3040, "total_steps": 4334, "loss": 0.3297, "lr": 2.4791008272348656e-06, "epoch": 1.4023068050749712, "percentage": 70.14, "elapsed_time": "17:29:18", "remaining_time": "7:26:38"}
+{"current_steps": 3050, "total_steps": 4334, "loss": 0.3279, "lr": 2.444399975572974e-06, "epoch": 1.4069204152249135, "percentage": 70.37, "elapsed_time": "17:32:17", "remaining_time": "7:22:59"}
+{"current_steps": 3060, "total_steps": 4334, "loss": 0.3103, "lr": 2.40986495313435e-06, "epoch": 1.4115340253748558, "percentage": 70.6, "elapsed_time": "17:35:18", "remaining_time": "7:19:21"}
+{"current_steps": 3070, "total_steps": 4334, "loss": 0.3231, "lr": 2.3754980008471074e-06, "epoch": 1.4161476355247982, "percentage": 70.84, "elapsed_time": "17:38:29", "remaining_time": "7:15:48"}
+{"current_steps": 3080, "total_steps": 4334, "loss": 0.3138, "lr": 2.3413013487335332e-06, "epoch": 1.4207612456747405, "percentage": 71.07, "elapsed_time": "17:41:49", "remaining_time": "7:12:18"}
+{"current_steps": 3090, "total_steps": 4334, "loss": 0.2695, "lr": 2.307277215765377e-06, "epoch": 1.4253748558246828, "percentage": 71.3, "elapsed_time": "17:44:58", "remaining_time": "7:08:44"}
+{"current_steps": 3100, "total_steps": 4334, "loss": 0.2983, "lr": 2.273427809719867e-06, "epoch": 1.4299884659746251, "percentage": 71.53, "elapsed_time": "17:48:03", "remaining_time": "7:05:09"}
+{"current_steps": 3110, "total_steps": 4334, "loss": 0.3141, "lr": 2.2397553270364546e-06, "epoch": 1.4346020761245675, "percentage": 71.76, "elapsed_time": "17:51:12", "remaining_time": "7:01:35"}
+{"current_steps": 3120, "total_steps": 4334, "loss": 0.2959, "lr": 2.206261952674284e-06, "epoch": 1.4392156862745098, "percentage": 71.99, "elapsed_time": "17:54:23", "remaining_time": "6:58:02"}
+{"current_steps": 3130, "total_steps": 4334, "loss": 0.3348, "lr": 2.172949859970422e-06, "epoch": 1.4438292964244521, "percentage": 72.22, "elapsed_time": "17:57:21", "remaining_time": "6:54:25"}
+{"current_steps": 3140, "total_steps": 4334, "loss": 0.3098, "lr": 2.1398212104988273e-06, "epoch": 1.4484429065743945, "percentage": 72.45, "elapsed_time": "18:00:29", "remaining_time": "6:50:51"}
+{"current_steps": 3150, "total_steps": 4334, "loss": 0.2701, "lr": 2.1068781539300874e-06, "epoch": 1.4530565167243368, "percentage": 72.68, "elapsed_time": "18:03:42", "remaining_time": "6:47:20"}
+{"current_steps": 3160, "total_steps": 4334, "loss": 0.3135, "lr": 2.0741228278919347e-06, "epoch": 1.457670126874279, "percentage": 72.91, "elapsed_time": "18:06:57", "remaining_time": "6:43:49"}
+{"current_steps": 3170, "total_steps": 4334, "loss": 0.3234, "lr": 2.0415573578305343e-06, "epoch": 1.4622837370242214, "percentage": 73.14, "elapsed_time": "18:10:03", "remaining_time": "6:40:15"}
+{"current_steps": 3180, "total_steps": 4334, "loss": 0.3034, "lr": 2.0091838568725685e-06, "epoch": 1.4668973471741638, "percentage": 73.37, "elapsed_time": "18:13:17", "remaining_time": "6:36:44"}
+{"current_steps": 3190, "total_steps": 4334, "loss": 0.3403, "lr": 1.977004425688126e-06, "epoch": 1.471510957324106, "percentage": 73.6, "elapsed_time": "18:16:23", "remaining_time": "6:33:11"}
+{"current_steps": 3200, "total_steps": 4334, "loss": 0.3235, "lr": 1.945021152354379e-06, "epoch": 1.4761245674740484, "percentage": 73.83, "elapsed_time": "18:19:42", "remaining_time": "6:29:42"}
+{"current_steps": 3210, "total_steps": 4334, "loss": 0.2852, "lr": 1.913236112220101e-06, "epoch": 1.4807381776239907, "percentage": 74.07, "elapsed_time": "18:22:51", "remaining_time": "6:26:10"}
+{"current_steps": 3220, "total_steps": 4334, "loss": 0.3362, "lr": 1.8816513677709935e-06, "epoch": 1.485351787773933, "percentage": 74.3, "elapsed_time": "18:26:10", "remaining_time": "6:22:41"}
+{"current_steps": 3230, "total_steps": 4334, "loss": 0.2814, "lr": 1.8502689684958664e-06, "epoch": 1.4899653979238754, "percentage": 74.53, "elapsed_time": "18:29:11", "remaining_time": "6:19:07"}
+{"current_steps": 3240, "total_steps": 4334, "loss": 0.3092, "lr": 1.8190909507536326e-06, "epoch": 1.4945790080738177, "percentage": 74.76, "elapsed_time": "18:32:29", "remaining_time": "6:15:38"}
+{"current_steps": 3250, "total_steps": 4334, "loss": 0.2931, "lr": 1.7881193376411822e-06, "epoch": 1.49919261822376, "percentage": 74.99, "elapsed_time": "18:35:35", "remaining_time": "6:12:05"}
+{"current_steps": 3260, "total_steps": 4334, "loss": 0.2852, "lr": 1.7573561388621102e-06, "epoch": 1.5038062283737024, "percentage": 75.22, "elapsed_time": "18:38:53", "remaining_time": "6:08:36"}
+{"current_steps": 3270, "total_steps": 4334, "loss": 0.3252, "lr": 1.7268033505962972e-06, "epoch": 1.5084198385236447, "percentage": 75.45, "elapsed_time": "18:42:10", "remaining_time": "6:05:08"}
+{"current_steps": 3280, "total_steps": 4334, "loss": 0.2965, "lr": 1.6964629553703893e-06, "epoch": 1.5130334486735872, "percentage": 75.68, "elapsed_time": "18:45:40", "remaining_time": "6:01:43"}
+{"current_steps": 3290, "total_steps": 4334, "loss": 0.3256, "lr": 1.6663369219291558e-06, "epoch": 1.5176470588235293, "percentage": 75.91, "elapsed_time": "18:49:01", "remaining_time": "5:58:16"}
+{"current_steps": 3300, "total_steps": 4334, "loss": 0.3087, "lr": 1.6364272051077335e-06, "epoch": 1.522260668973472, "percentage": 76.14, "elapsed_time": "18:52:09", "remaining_time": "5:54:44"}
+{"current_steps": 3310, "total_steps": 4334, "loss": 0.3082, "lr": 1.606735745704784e-06, "epoch": 1.526874279123414, "percentage": 76.37, "elapsed_time": "18:55:26", "remaining_time": "5:51:16"}
+{"current_steps": 3320, "total_steps": 4334, "loss": 0.3089, "lr": 1.5772644703565564e-06, "epoch": 1.5314878892733566, "percentage": 76.6, "elapsed_time": "18:58:47", "remaining_time": "5:47:48"}
+{"current_steps": 3330, "total_steps": 4334, "loss": 0.312, "lr": 1.5480152914118784e-06, "epoch": 1.5361014994232987, "percentage": 76.83, "elapsed_time": "19:02:02", "remaining_time": "5:44:19"}
+{"current_steps": 3340, "total_steps": 4334, "loss": 0.2756, "lr": 1.5189901068080536e-06, "epoch": 1.5407151095732412, "percentage": 77.07, "elapsed_time": "19:05:10", "remaining_time": "5:40:48"}
+{"current_steps": 3350, "total_steps": 4334, "loss": 0.2931, "lr": 1.4901907999477167e-06, "epoch": 1.5453287197231833, "percentage": 77.3, "elapsed_time": "19:08:23", "remaining_time": "5:37:19"}
+{"current_steps": 3360, "total_steps": 4334, "loss": 0.3312, "lr": 1.4616192395766189e-06, "epoch": 1.5499423298731259, "percentage": 77.53, "elapsed_time": "19:11:30", "remaining_time": "5:33:48"}
+{"current_steps": 3370, "total_steps": 4334, "loss": 0.2877, "lr": 1.4332772796623655e-06, "epoch": 1.554555940023068, "percentage": 77.76, "elapsed_time": "19:14:29", "remaining_time": "5:30:14"}
+{"current_steps": 3380, "total_steps": 4334, "loss": 0.2865, "lr": 1.405166759274123e-06, "epoch": 1.5591695501730105, "percentage": 77.99, "elapsed_time": "19:17:53", "remaining_time": "5:26:48"}
+{"current_steps": 3390, "total_steps": 4334, "loss": 0.2772, "lr": 1.3772895024632753e-06, "epoch": 1.5637831603229526, "percentage": 78.22, "elapsed_time": "19:21:05", "remaining_time": "5:23:19"}
+{"current_steps": 3400, "total_steps": 4334, "loss": 0.2826, "lr": 1.349647318145067e-06, "epoch": 1.5683967704728952, "percentage": 78.45, "elapsed_time": "19:24:18", "remaining_time": "5:19:50"}
+{"current_steps": 3410, "total_steps": 4334, "loss": 0.2582, "lr": 1.3222419999812248e-06, "epoch": 1.5730103806228373, "percentage": 78.68, "elapsed_time": "19:27:37", "remaining_time": "5:16:23"}
+{"current_steps": 3420, "total_steps": 4334, "loss": 0.3361, "lr": 1.2950753262635712e-06, "epoch": 1.5776239907727798, "percentage": 78.91, "elapsed_time": "19:30:50", "remaining_time": "5:12:54"}
+{"current_steps": 3430, "total_steps": 4334, "loss": 0.305, "lr": 1.2681490597986313e-06, "epoch": 1.582237600922722, "percentage": 79.14, "elapsed_time": "19:34:01", "remaining_time": "5:09:25"}
+{"current_steps": 3440, "total_steps": 4334, "loss": 0.2935, "lr": 1.2414649477932511e-06, "epoch": 1.5868512110726645, "percentage": 79.37, "elapsed_time": "19:37:29", "remaining_time": "5:06:00"}
+{"current_steps": 3450, "total_steps": 4334, "loss": 0.3227, "lr": 1.2150247217412186e-06, "epoch": 1.5914648212226066, "percentage": 79.6, "elapsed_time": "19:40:53", "remaining_time": "5:02:34"}
+{"current_steps": 3460, "total_steps": 4334, "loss": 0.3037, "lr": 1.1888300973109112e-06, "epoch": 1.5960784313725491, "percentage": 79.83, "elapsed_time": "19:44:21", "remaining_time": "4:59:10"}
+{"current_steps": 3470, "total_steps": 4334, "loss": 0.3172, "lr": 1.1628827742339688e-06, "epoch": 1.6006920415224912, "percentage": 80.06, "elapsed_time": "19:47:39", "remaining_time": "4:55:42"}
+{"current_steps": 3480, "total_steps": 4334, "loss": 0.3046, "lr": 1.1371844361950045e-06, "epoch": 1.6053056516724338, "percentage": 80.3, "elapsed_time": "19:50:51", "remaining_time": "4:52:14"}
+{"current_steps": 3490, "total_steps": 4334, "loss": 0.3107, "lr": 1.1117367507223452e-06, "epoch": 1.6099192618223759, "percentage": 80.53, "elapsed_time": "19:54:06", "remaining_time": "4:48:46"}
+{"current_steps": 3500, "total_steps": 4334, "loss": 0.2891, "lr": 1.0865413690798321e-06, "epoch": 1.6145328719723184, "percentage": 80.76, "elapsed_time": "19:57:18", "remaining_time": "4:45:17"}
+{"current_steps": 3500, "total_steps": 4334, "eval_loss": 0.3522779047489166, "epoch": 1.6145328719723184, "percentage": 80.76, "elapsed_time": "20:04:03", "remaining_time": "4:46:54"}
+{"current_steps": 3510, "total_steps": 4334, "loss": 0.3177, "lr": 1.061599926159676e-06, "epoch": 1.6191464821222605, "percentage": 80.99, "elapsed_time": "20:09:43", "remaining_time": "4:43:59"}
+{"current_steps": 3520, "total_steps": 4334, "loss": 0.2951, "lr": 1.036914040376364e-06, "epoch": 1.623760092272203, "percentage": 81.22, "elapsed_time": "20:12:53", "remaining_time": "4:40:28"}
+{"current_steps": 3530, "total_steps": 4334, "loss": 0.273, "lr": 1.0124853135616475e-06, "epoch": 1.6283737024221452, "percentage": 81.45, "elapsed_time": "20:16:17", "remaining_time": "4:37:01"}
+{"current_steps": 3540, "total_steps": 4334, "loss": 0.307, "lr": 9.883153308606035e-07, "epoch": 1.6329873125720877, "percentage": 81.68, "elapsed_time": "20:19:31", "remaining_time": "4:33:31"}
+{"current_steps": 3550, "total_steps": 4334, "loss": 0.3031, "lr": 9.644056606287727e-07, "epoch": 1.6376009227220298, "percentage": 81.91, "elapsed_time": "20:22:56", "remaining_time": "4:30:04"}
+{"current_steps": 3560, "total_steps": 4334, "loss": 0.3121, "lr": 9.407578543303913e-07, "epoch": 1.6422145328719724, "percentage": 82.14, "elapsed_time": "20:26:04", "remaining_time": "4:26:34"}
+{"current_steps": 3570, "total_steps": 4334, "loss": 0.2709, "lr": 9.173734464377204e-07, "epoch": 1.6468281430219145, "percentage": 82.37, "elapsed_time": "20:29:16", "remaining_time": "4:23:04"}
+{"current_steps": 3580, "total_steps": 4334, "loss": 0.2877, "lr": 8.942539543314799e-07, "epoch": 1.651441753171857, "percentage": 82.6, "elapsed_time": "20:32:21", "remaining_time": "4:19:33"}
+{"current_steps": 3590, "total_steps": 4334, "loss": 0.306, "lr": 8.714008782023797e-07, "epoch": 1.6560553633217991, "percentage": 82.83, "elapsed_time": "20:35:31", "remaining_time": "4:16:03"}
+{"current_steps": 3600, "total_steps": 4334, "loss": 0.3156, "lr": 8.488157009537796e-07, "epoch": 1.6606689734717417, "percentage": 83.06, "elapsed_time": "20:38:51", "remaining_time": "4:12:35"}
+{"current_steps": 3610, "total_steps": 4334, "loss": 0.3164, "lr": 8.264998881054659e-07, "epoch": 1.665282583621684, "percentage": 83.29, "elapsed_time": "20:42:10", "remaining_time": "4:09:07"}
+{"current_steps": 3620, "total_steps": 4334, "loss": 0.2823, "lr": 8.044548876985531e-07, "epoch": 1.6698961937716263, "percentage": 83.53, "elapsed_time": "20:45:26", "remaining_time": "4:05:38"}
+{"current_steps": 3630, "total_steps": 4334, "loss": 0.3184, "lr": 7.826821302015275e-07, "epoch": 1.6745098039215687, "percentage": 83.76, "elapsed_time": "20:48:52", "remaining_time": "4:02:12"}
+{"current_steps": 3640, "total_steps": 4334, "loss": 0.2956, "lr": 7.61183028417422e-07, "epoch": 1.679123414071511, "percentage": 83.99, "elapsed_time": "20:52:02", "remaining_time": "3:58:42"}
+{"current_steps": 3650, "total_steps": 4334, "loss": 0.3187, "lr": 7.399589773921412e-07, "epoch": 1.6837370242214533, "percentage": 84.22, "elapsed_time": "20:55:15", "remaining_time": "3:55:13"}
+{"current_steps": 3660, "total_steps": 4334, "loss": 0.3194, "lr": 7.190113543239408e-07, "epoch": 1.6883506343713957, "percentage": 84.45, "elapsed_time": "20:58:19", "remaining_time": "3:51:43"}
+{"current_steps": 3670, "total_steps": 4334, "loss": 0.2958, "lr": 6.983415184740616e-07, "epoch": 1.692964244521338, "percentage": 84.68, "elapsed_time": "21:01:28", "remaining_time": "3:48:14"}
+{"current_steps": 3680, "total_steps": 4334, "loss": 0.2761, "lr": 6.779508110785332e-07, "epoch": 1.6975778546712803, "percentage": 84.91, "elapsed_time": "21:04:40", "remaining_time": "3:44:45"}
+{"current_steps": 3690, "total_steps": 4334, "loss": 0.2758, "lr": 6.578405552611361e-07, "epoch": 1.7021914648212226, "percentage": 85.14, "elapsed_time": "21:07:55", "remaining_time": "3:41:17"}
+{"current_steps": 3700, "total_steps": 4334, "loss": 0.3272, "lr": 6.380120559475505e-07, "epoch": 1.706805074971165, "percentage": 85.37, "elapsed_time": "21:11:00", "remaining_time": "3:37:47"}
+{"current_steps": 3710, "total_steps": 4334, "loss": 0.2947, "lr": 6.184665997806832e-07, "epoch": 1.7114186851211073, "percentage": 85.6, "elapsed_time": "21:14:15", "remaining_time": "3:34:19"}
+{"current_steps": 3720, "total_steps": 4334, "loss": 0.3304, "lr": 5.992054550371723e-07, "epoch": 1.7160322952710496, "percentage": 85.83, "elapsed_time": "21:17:40", "remaining_time": "3:30:53"}
+{"current_steps": 3730, "total_steps": 4334, "loss": 0.3214, "lr": 5.802298715451016e-07, "epoch": 1.720645905420992, "percentage": 86.06, "elapsed_time": "21:21:02", "remaining_time": "3:27:26"}
+{"current_steps": 3740, "total_steps": 4334, "loss": 0.2974, "lr": 5.615410806028875e-07, "epoch": 1.7252595155709343, "percentage": 86.29, "elapsed_time": "21:24:16", "remaining_time": "3:23:58"}
+{"current_steps": 3750, "total_steps": 4334, "loss": 0.2869, "lr": 5.431402948993947e-07, "epoch": 1.7298731257208766, "percentage": 86.53, "elapsed_time": "21:27:28", "remaining_time": "3:20:30"}
+{"current_steps": 3760, "total_steps": 4334, "loss": 0.329, "lr": 5.250287084352373e-07, "epoch": 1.734486735870819, "percentage": 86.76, "elapsed_time": "21:30:50", "remaining_time": "3:17:03"}
+{"current_steps": 3770, "total_steps": 4334, "loss": 0.3262, "lr": 5.072074964453055e-07, "epoch": 1.7391003460207612, "percentage": 86.99, "elapsed_time": "21:34:08", "remaining_time": "3:13:36"}
+{"current_steps": 3780, "total_steps": 4334, "loss": 0.2963, "lr": 4.896778153225062e-07, "epoch": 1.7437139561707036, "percentage": 87.22, "elapsed_time": "21:37:23", "remaining_time": "3:10:08"}
+{"current_steps": 3790, "total_steps": 4334, "loss": 0.3124, "lr": 4.7244080254272795e-07, "epoch": 1.748327566320646, "percentage": 87.45, "elapsed_time": "21:40:37", "remaining_time": "3:06:41"}
+{"current_steps": 3800, "total_steps": 4334, "loss": 0.293, "lr": 4.55497576591028e-07, "epoch": 1.7529411764705882, "percentage": 87.68, "elapsed_time": "21:43:47", "remaining_time": "3:03:13"}
+{"current_steps": 3810, "total_steps": 4334, "loss": 0.3092, "lr": 4.3884923688905676e-07, "epoch": 1.7575547866205306, "percentage": 87.91, "elapsed_time": "21:47:02", "remaining_time": "2:59:45"}
+{"current_steps": 3820, "total_steps": 4334, "loss": 0.2644, "lr": 4.224968637237198e-07, "epoch": 1.7621683967704729, "percentage": 88.14, "elapsed_time": "21:50:09", "remaining_time": "2:56:17"}
+{"current_steps": 3830, "total_steps": 4334, "loss": 0.2823, "lr": 4.064415181770787e-07, "epoch": 1.7667820069204152, "percentage": 88.37, "elapsed_time": "21:53:32", "remaining_time": "2:52:51"}
+{"current_steps": 3840, "total_steps": 4334, "loss": 0.3121, "lr": 3.90684242057498e-07, "epoch": 1.7713956170703575, "percentage": 88.6, "elapsed_time": "21:57:00", "remaining_time": "2:49:25"}
+{"current_steps": 3850, "total_steps": 4334, "loss": 0.3145, "lr": 3.752260578320427e-07, "epoch": 1.7760092272202999, "percentage": 88.83, "elapsed_time": "22:00:34", "remaining_time": "2:46:00"}
+{"current_steps": 3860, "total_steps": 4334, "loss": 0.3086, "lr": 3.600679685601349e-07, "epoch": 1.7806228373702422, "percentage": 89.06, "elapsed_time": "22:03:41", "remaining_time": "2:42:32"}
+{"current_steps": 3870, "total_steps": 4334, "loss": 0.2978, "lr": 3.4521095782846623e-07, "epoch": 1.7852364475201845, "percentage": 89.29, "elapsed_time": "22:06:57", "remaining_time": "2:39:05"}
+{"current_steps": 3880, "total_steps": 4334, "loss": 0.3016, "lr": 3.306559896871714e-07, "epoch": 1.7898500576701268, "percentage": 89.52, "elapsed_time": "22:10:15", "remaining_time": "2:35:39"}
+{"current_steps": 3890, "total_steps": 4334, "loss": 0.3066, "lr": 3.164040085872755e-07, "epoch": 1.7944636678200692, "percentage": 89.76, "elapsed_time": "22:13:30", "remaining_time": "2:32:12"}
+{"current_steps": 3900, "total_steps": 4334, "loss": 0.2851, "lr": 3.0245593931940766e-07, "epoch": 1.7990772779700115, "percentage": 89.99, "elapsed_time": "22:16:39", "remaining_time": "2:28:44"}
+{"current_steps": 3910, "total_steps": 4334, "loss": 0.2901, "lr": 2.8881268695379436e-07, "epoch": 1.8036908881199538, "percentage": 90.22, "elapsed_time": "22:20:02", "remaining_time": "2:25:18"}
+{"current_steps": 3920, "total_steps": 4334, "loss": 0.2997, "lr": 2.7547513678153005e-07, "epoch": 1.8083044982698961, "percentage": 90.45, "elapsed_time": "22:23:12", "remaining_time": "2:21:51"}
+{"current_steps": 3930, "total_steps": 4334, "loss": 0.3282, "lr": 2.624441542571327e-07, "epoch": 1.8129181084198385, "percentage": 90.68, "elapsed_time": "22:26:12", "remaining_time": "2:18:23"}
+{"current_steps": 3940, "total_steps": 4334, "loss": 0.2596, "lr": 2.497205849423834e-07, "epoch": 1.8175317185697808, "percentage": 90.91, "elapsed_time": "22:29:12", "remaining_time": "2:14:55"}
+{"current_steps": 3950, "total_steps": 4334, "loss": 0.3077, "lr": 2.3730525445146146e-07, "epoch": 1.8221453287197233, "percentage": 91.14, "elapsed_time": "22:32:19", "remaining_time": "2:11:27"}
+{"current_steps": 3960, "total_steps": 4334, "loss": 0.3411, "lr": 2.25198968397371e-07, "epoch": 1.8267589388696654, "percentage": 91.37, "elapsed_time": "22:35:35", "remaining_time": "2:08:01"}
+{"current_steps": 3970, "total_steps": 4334, "loss": 0.2816, "lr": 2.134025123396638e-07, "epoch": 1.831372549019608, "percentage": 91.6, "elapsed_time": "22:38:49", "remaining_time": "2:04:35"}
+{"current_steps": 3980, "total_steps": 4334, "loss": 0.3093, "lr": 2.019166517334703e-07, "epoch": 1.83598615916955, "percentage": 91.83, "elapsed_time": "22:41:53", "remaining_time": "2:01:08"}
+{"current_steps": 3990, "total_steps": 4334, "loss": 0.2848, "lr": 1.9074213187982416e-07, "epoch": 1.8405997693194927, "percentage": 92.06, "elapsed_time": "22:45:02", "remaining_time": "1:57:41"}
+{"current_steps": 4000, "total_steps": 4334, "loss": 0.3013, "lr": 1.7987967787730541e-07, "epoch": 1.8452133794694348, "percentage": 92.29, "elapsed_time": "22:47:59", "remaining_time": "1:54:13"}
+{"current_steps": 4000, "total_steps": 4334, "eval_loss": 0.3492071032524109, "epoch": 1.8452133794694348, "percentage": 92.29, "elapsed_time": "22:54:52", "remaining_time": "1:54:48"}
+{"current_steps": 4010, "total_steps": 4334, "loss": 0.2951, "lr": 1.6932999457498823e-07, "epoch": 1.8498269896193773, "percentage": 92.52, "elapsed_time": "23:00:20", "remaining_time": "1:51:31"}
+{"current_steps": 4020, "total_steps": 4334, "loss": 0.2518, "lr": 1.5909376652670283e-07, "epoch": 1.8544405997693194, "percentage": 92.75, "elapsed_time": "23:03:22", "remaining_time": "1:48:03"}
+{"current_steps": 4030, "total_steps": 4334, "loss": 0.3032, "lr": 1.4917165794661849e-07, "epoch": 1.859054209919262, "percentage": 92.99, "elapsed_time": "23:06:37", "remaining_time": "1:44:35"}
+{"current_steps": 4040, "total_steps": 4334, "loss": 0.2954, "lr": 1.395643126661428e-07, "epoch": 1.863667820069204, "percentage": 93.22, "elapsed_time": "23:09:48", "remaining_time": "1:41:08"}
+{"current_steps": 4050, "total_steps": 4334, "loss": 0.2756, "lr": 1.302723540921419e-07, "epoch": 1.8682814302191466, "percentage": 93.45, "elapsed_time": "23:13:14", "remaining_time": "1:37:41"}
+{"current_steps": 4060, "total_steps": 4334, "loss": 0.2792, "lr": 1.212963851664928e-07, "epoch": 1.8728950403690887, "percentage": 93.68, "elapsed_time": "23:16:34", "remaining_time": "1:34:15"}
+{"current_steps": 4070, "total_steps": 4334, "loss": 0.3286, "lr": 1.1263698832695513e-07, "epoch": 1.8775086505190313, "percentage": 93.91, "elapsed_time": "23:19:58", "remaining_time": "1:30:48"}
+{"current_steps": 4080, "total_steps": 4334, "loss": 0.2919, "lr": 1.0429472546938158e-07, "epoch": 1.8821222606689734, "percentage": 94.14, "elapsed_time": "23:23:08", "remaining_time": "1:27:21"}
+{"current_steps": 4090, "total_steps": 4334, "loss": 0.3285, "lr": 9.627013791125294e-08, "epoch": 1.886735870818916, "percentage": 94.37, "elapsed_time": "23:26:08", "remaining_time": "1:23:53"}
+{"current_steps": 4100, "total_steps": 4334, "loss": 0.3172, "lr": 8.856374635655696e-08, "epoch": 1.891349480968858, "percentage": 94.6, "elapsed_time": "23:29:22", "remaining_time": "1:20:26"}
+{"current_steps": 4110, "total_steps": 4334, "loss": 0.2838, "lr": 8.117605086199686e-08, "epoch": 1.8959630911188006, "percentage": 94.83, "elapsed_time": "23:32:32", "remaining_time": "1:16:59"}
+{"current_steps": 4120, "total_steps": 4334, "loss": 0.3001, "lr": 7.410753080454746e-08, "epoch": 1.9005767012687427, "percentage": 95.06, "elapsed_time": "23:35:46", "remaining_time": "1:13:32"}
+{"current_steps": 4130, "total_steps": 4334, "loss": 0.2853, "lr": 6.735864485034493e-08, "epoch": 1.9051903114186852, "percentage": 95.29, "elapsed_time": "23:38:54", "remaining_time": "1:10:05"}
+{"current_steps": 4140, "total_steps": 4334, "loss": 0.3221, "lr": 6.092983092492844e-08, "epoch": 1.9098039215686273, "percentage": 95.52, "elapsed_time": "23:42:24", "remaining_time": "1:06:39"}
+{"current_steps": 4150, "total_steps": 4334, "loss": 0.2815, "lr": 5.482150618481952e-08, "epoch": 1.9144175317185699, "percentage": 95.75, "elapsed_time": "23:45:39", "remaining_time": "1:03:12"}
+{"current_steps": 4160, "total_steps": 4334, "loss": 0.3051, "lr": 4.9034066990457094e-08, "epoch": 1.919031141868512, "percentage": 95.99, "elapsed_time": "23:48:54", "remaining_time": "0:59:45"}
+{"current_steps": 4170, "total_steps": 4334, "loss": 0.301, "lr": 4.356788888047747e-08, "epoch": 1.9236447520184545, "percentage": 96.22, "elapsed_time": "23:52:06", "remaining_time": "0:56:19"}
+{"current_steps": 4180, "total_steps": 4334, "loss": 0.297, "lr": 3.8423326547344376e-08, "epoch": 1.9282583621683966, "percentage": 96.45, "elapsed_time": "23:55:31", "remaining_time": "0:52:53"}
+{"current_steps": 4190, "total_steps": 4334, "loss": 0.309, "lr": 3.360071381433516e-08, "epoch": 1.9328719723183392, "percentage": 96.68, "elapsed_time": "23:58:57", "remaining_time": "0:49:27"}
+{"current_steps": 4200, "total_steps": 4334, "loss": 0.2899, "lr": 2.9100363613879246e-08, "epoch": 1.9374855824682813, "percentage": 96.91, "elapsed_time": "1 day, 0:02:17", "remaining_time": "0:46:00"}
+{"current_steps": 4210, "total_steps": 4334, "loss": 0.2905, "lr": 2.492256796725212e-08, "epoch": 1.9420991926182238, "percentage": 97.14, "elapsed_time": "1 day, 0:05:27", "remaining_time": "0:42:34"}
+{"current_steps": 4220, "total_steps": 4334, "loss": 0.3042, "lr": 2.1067597965624963e-08, "epoch": 1.946712802768166, "percentage": 97.37, "elapsed_time": "1 day, 0:08:43", "remaining_time": "0:39:08"}
+{"current_steps": 4230, "total_steps": 4334, "loss": 0.2793, "lr": 1.753570375247815e-08, "epoch": 1.9513264129181085, "percentage": 97.6, "elapsed_time": "1 day, 0:12:08", "remaining_time": "0:35:42"}
+{"current_steps": 4240, "total_steps": 4334, "loss": 0.3012, "lr": 1.4327114507365347e-08, "epoch": 1.9559400230680506, "percentage": 97.83, "elapsed_time": "1 day, 0:15:39", "remaining_time": "0:32:16"}
+{"current_steps": 4250, "total_steps": 4334, "loss": 0.2987, "lr": 1.1442038431044856e-08, "epoch": 1.9605536332179931, "percentage": 98.06, "elapsed_time": "1 day, 0:18:56", "remaining_time": "0:28:50"}
+{"current_steps": 4260, "total_steps": 4334, "loss": 0.3028, "lr": 8.880662731968748e-09, "epoch": 1.9651672433679352, "percentage": 98.29, "elapsed_time": "1 day, 0:22:11", "remaining_time": "0:25:23"}
+{"current_steps": 4270, "total_steps": 4334, "loss": 0.327, "lr": 6.6431536141348115e-09, "epoch": 1.9697808535178778, "percentage": 98.52, "elapsed_time": "1 day, 0:25:25", "remaining_time": "0:21:57"}
+{"current_steps": 4280, "total_steps": 4334, "loss": 0.2861, "lr": 4.729656266304061e-09, "epoch": 1.9743944636678201, "percentage": 98.75, "elapsed_time": "1 day, 0:28:35", "remaining_time": "0:18:31"}
+{"current_steps": 4290, "total_steps": 4334, "loss": 0.3224, "lr": 3.1402948525766085e-09, "epoch": 1.9790080738177624, "percentage": 98.98, "elapsed_time": "1 day, 0:31:38", "remaining_time": "0:15:05"}
+{"current_steps": 4300, "total_steps": 4334, "loss": 0.2968, "lr": 1.8751725043375526e-09, "epoch": 1.9836216839677048, "percentage": 99.22, "elapsed_time": "1 day, 0:34:48", "remaining_time": "0:11:39"}
+{"current_steps": 4310, "total_steps": 4334, "loss": 0.3063, "lr": 9.343713135623323e-10, "epoch": 1.988235294117647, "percentage": 99.45, "elapsed_time": "1 day, 0:38:07", "remaining_time": "0:08:13"}
+{"current_steps": 4320, "total_steps": 4334, "loss": 0.2943, "lr": 3.1795232749320947e-10, "epoch": 1.9928489042675894, "percentage": 99.68, "elapsed_time": "1 day, 0:41:19", "remaining_time": "0:04:48"}
+{"current_steps": 4330, "total_steps": 4334, "loss": 0.2894, "lr": 2.5955544673550438e-11, "epoch": 1.9974625144175318, "percentage": 99.91, "elapsed_time": "1 day, 0:44:46", "remaining_time": "0:01:22"}
+{"current_steps": 4334, "total_steps": 4334, "epoch": 1.9993079584775086, "percentage": 100.0, "elapsed_time": "1 day, 0:48:13", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,3137 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9993079584775086,
+  "eval_steps": 500,
+  "global_step": 4334,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00461361014994233,
+      "grad_norm": 5.300843715667725,
+      "learning_rate": 2.3041474654377884e-07,
+      "loss": 0.806,
+      "step": 10
+    },
+    {
+      "epoch": 0.00922722029988466,
+      "grad_norm": 5.792849540710449,
+      "learning_rate": 4.608294930875577e-07,
+      "loss": 0.8251,
+      "step": 20
+    },
+    {
+      "epoch": 0.01384083044982699,
+      "grad_norm": 4.814388751983643,
+      "learning_rate": 6.912442396313365e-07,
+      "loss": 0.7555,
+      "step": 30
+    },
+    {
+      "epoch": 0.01845444059976932,
+      "grad_norm": 2.745297431945801,
+      "learning_rate": 9.216589861751154e-07,
+      "loss": 0.7218,
+      "step": 40
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "grad_norm": 1.7126681804656982,
+      "learning_rate": 1.1520737327188942e-06,
+      "loss": 0.6751,
+      "step": 50
+    },
+    {
+      "epoch": 0.02768166089965398,
+      "grad_norm": 1.703934669494629,
+      "learning_rate": 1.382488479262673e-06,
+      "loss": 0.6197,
+      "step": 60
+    },
+    {
+      "epoch": 0.03229527104959631,
+      "grad_norm": 1.7122575044631958,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.5083,
+      "step": 70
+    },
+    {
+      "epoch": 0.03690888119953864,
+      "grad_norm": 2.8078525066375732,
+      "learning_rate": 1.8433179723502307e-06,
+      "loss": 0.5326,
+      "step": 80
+    },
+    {
+      "epoch": 0.04152249134948097,
+      "grad_norm": 1.8321082592010498,
+      "learning_rate": 2.0737327188940094e-06,
+      "loss": 0.5463,
+      "step": 90
+    },
+    {
+      "epoch": 0.0461361014994233,
+      "grad_norm": 1.547890305519104,
+      "learning_rate": 2.3041474654377884e-06,
+      "loss": 0.5445,
+      "step": 100
+    },
+    {
+      "epoch": 0.05074971164936563,
+      "grad_norm": 1.5186538696289062,
+      "learning_rate": 2.5345622119815673e-06,
+      "loss": 0.4972,
+      "step": 110
+    },
+    {
+      "epoch": 0.05536332179930796,
+      "grad_norm": 1.6117104291915894,
+      "learning_rate": 2.764976958525346e-06,
+      "loss": 0.519,
+      "step": 120
+    },
+    {
+      "epoch": 0.05997693194925029,
+      "grad_norm": 1.8595815896987915,
+      "learning_rate": 2.9953917050691243e-06,
+      "loss": 0.453,
+      "step": 130
+    },
+    {
+      "epoch": 0.06459054209919261,
+      "grad_norm": 1.2419018745422363,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.4799,
+      "step": 140
+    },
+    {
+      "epoch": 0.06920415224913495,
+      "grad_norm": 1.5790776014328003,
+      "learning_rate": 3.4562211981566825e-06,
+      "loss": 0.4896,
+      "step": 150
+    },
+    {
+      "epoch": 0.07381776239907728,
+      "grad_norm": 1.4088906049728394,
+      "learning_rate": 3.6866359447004615e-06,
+      "loss": 0.5167,
+      "step": 160
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 1.2521541118621826,
+      "learning_rate": 3.91705069124424e-06,
+      "loss": 0.5127,
+      "step": 170
+    },
+    {
+      "epoch": 0.08304498269896193,
+      "grad_norm": 2.0803122520446777,
+      "learning_rate": 4.147465437788019e-06,
+      "loss": 0.4465,
+      "step": 180
+    },
+    {
+      "epoch": 0.08765859284890427,
+      "grad_norm": 1.523786187171936,
+      "learning_rate": 4.377880184331797e-06,
+      "loss": 0.4761,
+      "step": 190
+    },
+    {
+      "epoch": 0.0922722029988466,
+      "grad_norm": 1.418717622756958,
+      "learning_rate": 4.608294930875577e-06,
+      "loss": 0.5055,
+      "step": 200
+    },
+    {
+      "epoch": 0.09688581314878893,
+      "grad_norm": 1.483023762702942,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.4557,
+      "step": 210
+    },
+    {
+      "epoch": 0.10149942329873125,
+      "grad_norm": 1.5981467962265015,
+      "learning_rate": 5.0691244239631346e-06,
+      "loss": 0.4686,
+      "step": 220
+    },
+    {
+      "epoch": 0.1061130334486736,
+      "grad_norm": 1.130113959312439,
+      "learning_rate": 5.299539170506913e-06,
+      "loss": 0.4843,
+      "step": 230
+    },
+    {
+      "epoch": 0.11072664359861592,
+      "grad_norm": 1.8060191869735718,
+      "learning_rate": 5.529953917050692e-06,
+      "loss": 0.5015,
+      "step": 240
+    },
+    {
+      "epoch": 0.11534025374855825,
+      "grad_norm": 1.069687008857727,
+      "learning_rate": 5.76036866359447e-06,
+      "loss": 0.4622,
+      "step": 250
+    },
+    {
+      "epoch": 0.11995386389850057,
+      "grad_norm": 1.1288576126098633,
+      "learning_rate": 5.9907834101382485e-06,
+      "loss": 0.4642,
+      "step": 260
+    },
+    {
+      "epoch": 0.1245674740484429,
+      "grad_norm": 1.7959188222885132,
+      "learning_rate": 6.221198156682028e-06,
+      "loss": 0.4357,
+      "step": 270
+    },
+    {
+      "epoch": 0.12918108419838523,
+      "grad_norm": 1.1214991807937622,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.4547,
+      "step": 280
+    },
+    {
+      "epoch": 0.13379469434832755,
+      "grad_norm": 1.6405386924743652,
+      "learning_rate": 6.682027649769586e-06,
+      "loss": 0.4464,
+      "step": 290
+    },
+    {
+      "epoch": 0.1384083044982699,
+      "grad_norm": 1.422194004058838,
+      "learning_rate": 6.912442396313365e-06,
+      "loss": 0.4957,
+      "step": 300
+    },
+    {
+      "epoch": 0.14302191464821223,
+      "grad_norm": 1.5487645864486694,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.4473,
+      "step": 310
+    },
+    {
+      "epoch": 0.14763552479815456,
+      "grad_norm": 1.3289945125579834,
+      "learning_rate": 7.373271889400923e-06,
+      "loss": 0.4831,
+      "step": 320
+    },
+    {
+      "epoch": 0.1522491349480969,
+      "grad_norm": 1.6698657274246216,
+      "learning_rate": 7.603686635944701e-06,
+      "loss": 0.4996,
+      "step": 330
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 1.4635429382324219,
+      "learning_rate": 7.83410138248848e-06,
+      "loss": 0.4861,
+      "step": 340
+    },
+    {
+      "epoch": 0.16147635524798154,
+      "grad_norm": 1.1806988716125488,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.4774,
+      "step": 350
+    },
+    {
+      "epoch": 0.16608996539792387,
+      "grad_norm": 1.4619848728179932,
+      "learning_rate": 8.294930875576038e-06,
+      "loss": 0.505,
+      "step": 360
+    },
+    {
+      "epoch": 0.1707035755478662,
+      "grad_norm": 1.3232295513153076,
+      "learning_rate": 8.525345622119815e-06,
+      "loss": 0.5116,
+      "step": 370
+    },
+    {
+      "epoch": 0.17531718569780855,
+      "grad_norm": 1.5264451503753662,
+      "learning_rate": 8.755760368663595e-06,
+      "loss": 0.4307,
+      "step": 380
+    },
+    {
+      "epoch": 0.17993079584775087,
+      "grad_norm": 1.2139824628829956,
+      "learning_rate": 8.986175115207374e-06,
+      "loss": 0.4525,
+      "step": 390
+    },
+    {
+      "epoch": 0.1845444059976932,
+      "grad_norm": 1.5944982767105103,
+      "learning_rate": 9.216589861751153e-06,
+      "loss": 0.4557,
+      "step": 400
+    },
+    {
+      "epoch": 0.18915801614763553,
+      "grad_norm": 1.3352501392364502,
+      "learning_rate": 9.447004608294931e-06,
+      "loss": 0.4927,
+      "step": 410
+    },
+    {
+      "epoch": 0.19377162629757785,
+      "grad_norm": 1.0890029668807983,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.4926,
+      "step": 420
+    },
+    {
+      "epoch": 0.19838523644752018,
+      "grad_norm": 1.675134539604187,
+      "learning_rate": 9.90783410138249e-06,
+      "loss": 0.4373,
+      "step": 430
+    },
+    {
+      "epoch": 0.2029988465974625,
+      "grad_norm": 1.240625023841858,
+      "learning_rate": 9.999941600087643e-06,
+      "loss": 0.4877,
+      "step": 440
+    },
+    {
+      "epoch": 0.20761245674740483,
+      "grad_norm": 1.6467055082321167,
+      "learning_rate": 9.999584716674727e-06,
+      "loss": 0.4628,
+      "step": 450
+    },
+    {
+      "epoch": 0.2122260668973472,
+      "grad_norm": 1.0588369369506836,
+      "learning_rate": 9.998903417374228e-06,
+      "loss": 0.4757,
+      "step": 460
+    },
+    {
+      "epoch": 0.21683967704728951,
+      "grad_norm": 1.150065302848816,
+      "learning_rate": 9.997897746394684e-06,
+      "loss": 0.486,
+      "step": 470
+    },
+    {
+      "epoch": 0.22145328719723184,
+      "grad_norm": 1.382214903831482,
+      "learning_rate": 9.996567768992642e-06,
+      "loss": 0.4862,
+      "step": 480
+    },
+    {
+      "epoch": 0.22606689734717417,
+      "grad_norm": 1.066063642501831,
+      "learning_rate": 9.994913571468432e-06,
+      "loss": 0.486,
+      "step": 490
+    },
+    {
+      "epoch": 0.2306805074971165,
+      "grad_norm": 1.6976910829544067,
+      "learning_rate": 9.992935261160559e-06,
+      "loss": 0.4468,
+      "step": 500
+    },
+    {
+      "epoch": 0.2306805074971165,
+      "eval_loss": 0.39874735474586487,
+      "eval_runtime": 400.8977,
+      "eval_samples_per_second": 8.409,
+      "eval_steps_per_second": 1.202,
+      "step": 500
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.5809332132339478,
+      "learning_rate": 9.990632966438743e-06,
+      "loss": 0.4171,
+      "step": 510
+    },
+    {
+      "epoch": 0.23990772779700115,
+      "grad_norm": 1.19710111618042,
+      "learning_rate": 9.988006836695593e-06,
+      "loss": 0.4764,
+      "step": 520
+    },
+    {
+      "epoch": 0.24452133794694347,
+      "grad_norm": 1.0074009895324707,
+      "learning_rate": 9.985057042336898e-06,
+      "loss": 0.4678,
+      "step": 530
+    },
+    {
+      "epoch": 0.2491349480968858,
+      "grad_norm": 1.1784993410110474,
+      "learning_rate": 9.981783774770595e-06,
+      "loss": 0.4524,
+      "step": 540
+    },
+    {
+      "epoch": 0.2537485582468281,
+      "grad_norm": 1.5833553075790405,
+      "learning_rate": 9.97818724639432e-06,
+      "loss": 0.4399,
+      "step": 550
+    },
+    {
+      "epoch": 0.25836216839677045,
+      "grad_norm": 1.1442863941192627,
+      "learning_rate": 9.974267690581646e-06,
+      "loss": 0.4897,
+      "step": 560
+    },
+    {
+      "epoch": 0.2629757785467128,
+      "grad_norm": 1.2376320362091064,
+      "learning_rate": 9.970025361666934e-06,
+      "loss": 0.4497,
+      "step": 570
+    },
+    {
+      "epoch": 0.2675893886966551,
+      "grad_norm": 1.0321787595748901,
+      "learning_rate": 9.965460534928827e-06,
+      "loss": 0.4832,
+      "step": 580
+    },
+    {
+      "epoch": 0.2722029988465975,
+      "grad_norm": 1.4388171434402466,
+      "learning_rate": 9.960573506572391e-06,
+      "loss": 0.4788,
+      "step": 590
+    },
+    {
+      "epoch": 0.2768166089965398,
+      "grad_norm": 1.7396047115325928,
+      "learning_rate": 9.95536459370989e-06,
+      "loss": 0.4484,
+      "step": 600
+    },
+    {
+      "epoch": 0.28143021914648214,
+      "grad_norm": 1.2319186925888062,
+      "learning_rate": 9.949834134340219e-06,
+      "loss": 0.4799,
+      "step": 610
+    },
+    {
+      "epoch": 0.28604382929642447,
+      "grad_norm": 1.3797781467437744,
+      "learning_rate": 9.94398248732696e-06,
+      "loss": 0.4506,
+      "step": 620
+    },
+    {
+      "epoch": 0.2906574394463668,
+      "grad_norm": 1.5929468870162964,
+      "learning_rate": 9.9378100323751e-06,
+      "loss": 0.5108,
+      "step": 630
+    },
+    {
+      "epoch": 0.2952710495963091,
+      "grad_norm": 1.4704443216323853,
+      "learning_rate": 9.931317170006398e-06,
+      "loss": 0.4607,
+      "step": 640
+    },
+    {
+      "epoch": 0.29988465974625145,
+      "grad_norm": 1.980751872062683,
+      "learning_rate": 9.924504321533387e-06,
+      "loss": 0.4564,
+      "step": 650
+    },
+    {
+      "epoch": 0.3044982698961938,
+      "grad_norm": 1.143687129020691,
+      "learning_rate": 9.91737192903204e-06,
+      "loss": 0.447,
+      "step": 660
+    },
+    {
+      "epoch": 0.3091118800461361,
+      "grad_norm": 1.0242226123809814,
+      "learning_rate": 9.909920455313087e-06,
+      "loss": 0.4712,
+      "step": 670
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 1.3482781648635864,
+      "learning_rate": 9.902150383891979e-06,
+      "loss": 0.4831,
+      "step": 680
+    },
+    {
+      "epoch": 0.31833910034602075,
+      "grad_norm": 1.1587884426116943,
+      "learning_rate": 9.894062218957517e-06,
+      "loss": 0.499,
+      "step": 690
+    },
+    {
+      "epoch": 0.3229527104959631,
+      "grad_norm": 1.1495003700256348,
+      "learning_rate": 9.885656485339129e-06,
+      "loss": 0.4482,
+      "step": 700
+    },
+    {
+      "epoch": 0.3275663206459054,
+      "grad_norm": 1.0492511987686157,
+      "learning_rate": 9.876933728472826e-06,
+      "loss": 0.4763,
+      "step": 710
+    },
+    {
+      "epoch": 0.33217993079584773,
+      "grad_norm": 1.2462799549102783,
+      "learning_rate": 9.867894514365802e-06,
+      "loss": 0.4707,
+      "step": 720
+    },
+    {
+      "epoch": 0.33679354094579006,
+      "grad_norm": 0.9900134205818176,
+      "learning_rate": 9.858539429559705e-06,
+      "loss": 0.472,
+      "step": 730
+    },
+    {
+      "epoch": 0.3414071510957324,
+      "grad_norm": 1.1227929592132568,
+      "learning_rate": 9.848869081092581e-06,
+      "loss": 0.497,
+      "step": 740
+    },
+    {
+      "epoch": 0.3460207612456747,
+      "grad_norm": 1.3729174137115479,
+      "learning_rate": 9.838884096459486e-06,
+      "loss": 0.4271,
+      "step": 750
+    },
+    {
+      "epoch": 0.3506343713956171,
+      "grad_norm": 1.1883389949798584,
+      "learning_rate": 9.828585123571763e-06,
+      "loss": 0.4977,
+      "step": 760
+    },
+    {
+      "epoch": 0.3552479815455594,
+      "grad_norm": 1.181907296180725,
+      "learning_rate": 9.817972830715003e-06,
+      "loss": 0.4605,
+      "step": 770
+    },
+    {
+      "epoch": 0.35986159169550175,
+      "grad_norm": 0.9973541498184204,
+      "learning_rate": 9.807047906505683e-06,
+      "loss": 0.4414,
+      "step": 780
+    },
+    {
+      "epoch": 0.3644752018454441,
+      "grad_norm": 1.148622989654541,
+      "learning_rate": 9.795811059846476e-06,
+      "loss": 0.4372,
+      "step": 790
+    },
+    {
+      "epoch": 0.3690888119953864,
+      "grad_norm": 0.8280909061431885,
+      "learning_rate": 9.78426301988026e-06,
+      "loss": 0.486,
+      "step": 800
+    },
+    {
+      "epoch": 0.3737024221453287,
+      "grad_norm": 1.027239203453064,
+      "learning_rate": 9.772404535942802e-06,
+      "loss": 0.4645,
+      "step": 810
+    },
+    {
+      "epoch": 0.37831603229527105,
+      "grad_norm": 1.01218581199646,
+      "learning_rate": 9.760236377514128e-06,
+      "loss": 0.4503,
+      "step": 820
+    },
+    {
+      "epoch": 0.3829296424452134,
+      "grad_norm": 1.0366742610931396,
+      "learning_rate": 9.747759334168602e-06,
+      "loss": 0.4602,
+      "step": 830
+    },
+    {
+      "epoch": 0.3875432525951557,
+      "grad_norm": 1.3200701475143433,
+      "learning_rate": 9.734974215523684e-06,
+      "loss": 0.4535,
+      "step": 840
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 1.200269103050232,
+      "learning_rate": 9.721881851187406e-06,
+      "loss": 0.4569,
+      "step": 850
+    },
+    {
+      "epoch": 0.39677047289504036,
+      "grad_norm": 1.3125215768814087,
+      "learning_rate": 9.708483090704524e-06,
+      "loss": 0.4359,
+      "step": 860
+    },
+    {
+      "epoch": 0.4013840830449827,
+      "grad_norm": 0.9996836185455322,
+      "learning_rate": 9.694778803501404e-06,
+      "loss": 0.4573,
+      "step": 870
+    },
+    {
+      "epoch": 0.405997693194925,
+      "grad_norm": 1.1388590335845947,
+      "learning_rate": 9.680769878829606e-06,
+      "loss": 0.4737,
+      "step": 880
+    },
+    {
+      "epoch": 0.41061130334486734,
+      "grad_norm": 1.0428895950317383,
+      "learning_rate": 9.666457225708175e-06,
+      "loss": 0.4532,
+      "step": 890
+    },
+    {
+      "epoch": 0.41522491349480967,
+      "grad_norm": 1.0916321277618408,
+      "learning_rate": 9.65184177286466e-06,
+      "loss": 0.4475,
+      "step": 900
+    },
+    {
+      "epoch": 0.419838523644752,
+      "grad_norm": 1.0428664684295654,
+      "learning_rate": 9.636924468674856e-06,
+      "loss": 0.4866,
+      "step": 910
+    },
+    {
+      "epoch": 0.4244521337946944,
+      "grad_norm": 1.1310166120529175,
+      "learning_rate": 9.62170628110125e-06,
+      "loss": 0.4437,
+      "step": 920
+    },
+    {
+      "epoch": 0.4290657439446367,
+      "grad_norm": 1.1518645286560059,
+      "learning_rate": 9.606188197630224e-06,
+      "loss": 0.4349,
+      "step": 930
+    },
+    {
+      "epoch": 0.43367935409457903,
+      "grad_norm": 1.1595722436904907,
+      "learning_rate": 9.590371225207981e-06,
+      "loss": 0.4917,
+      "step": 940
+    },
+    {
+      "epoch": 0.43829296424452135,
+      "grad_norm": 1.127502202987671,
+      "learning_rate": 9.574256390175192e-06,
+      "loss": 0.4682,
+      "step": 950
+    },
+    {
+      "epoch": 0.4429065743944637,
+      "grad_norm": 0.9480658769607544,
+      "learning_rate": 9.557844738200408e-06,
+      "loss": 0.4912,
+      "step": 960
+    },
+    {
+      "epoch": 0.447520184544406,
+      "grad_norm": 1.121092677116394,
+      "learning_rate": 9.541137334212212e-06,
+      "loss": 0.461,
+      "step": 970
+    },
+    {
+      "epoch": 0.45213379469434833,
+      "grad_norm": 1.1865901947021484,
+      "learning_rate": 9.524135262330098e-06,
+      "loss": 0.4414,
+      "step": 980
+    },
+    {
+      "epoch": 0.45674740484429066,
+      "grad_norm": 1.2148582935333252,
+      "learning_rate": 9.506839625794152e-06,
+      "loss": 0.4457,
+      "step": 990
+    },
+    {
+      "epoch": 0.461361014994233,
+      "grad_norm": 1.0445005893707275,
+      "learning_rate": 9.489251546893441e-06,
+      "loss": 0.4457,
+      "step": 1000
+    },
+    {
+      "epoch": 0.461361014994233,
+      "eval_loss": 0.386065274477005,
+      "eval_runtime": 400.8996,
+      "eval_samples_per_second": 8.409,
+      "eval_steps_per_second": 1.202,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4659746251441753,
+      "grad_norm": 1.1309161186218262,
+      "learning_rate": 9.4713721668932e-06,
+      "loss": 0.4457,
+      "step": 1010
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.0543358325958252,
+      "learning_rate": 9.453202645960775e-06,
+      "loss": 0.4343,
+      "step": 1020
+    },
+    {
+      "epoch": 0.47520184544405997,
+      "grad_norm": 0.9181652665138245,
+      "learning_rate": 9.434744163090341e-06,
+      "loss": 0.402,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4798154555940023,
+      "grad_norm": 0.8402210474014282,
+      "learning_rate": 9.415997916026401e-06,
+      "loss": 0.4742,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4844290657439446,
+      "grad_norm": 0.9334933757781982,
+      "learning_rate": 9.396965121186058e-06,
+      "loss": 0.4487,
+      "step": 1050
+    },
+    {
+      "epoch": 0.48904267589388695,
+      "grad_norm": 1.047976016998291,
+      "learning_rate": 9.377647013580102e-06,
+      "loss": 0.449,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4936562860438293,
+      "grad_norm": 1.0943602323532104,
+      "learning_rate": 9.358044846732848e-06,
+      "loss": 0.4591,
+      "step": 1070
+    },
+    {
+      "epoch": 0.4982698961937716,
+      "grad_norm": 1.235120177268982,
+      "learning_rate": 9.338159892600809e-06,
+      "loss": 0.457,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5028835063437139,
+      "grad_norm": 1.1438275575637817,
+      "learning_rate": 9.317993441490163e-06,
+      "loss": 0.4863,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5074971164936563,
+      "grad_norm": 1.0768276453018188,
+      "learning_rate": 9.297546801973027e-06,
+      "loss": 0.4863,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5121107266435986,
+      "grad_norm": 0.9337517023086548,
+      "learning_rate": 9.276821300802535e-06,
+      "loss": 0.4445,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5167243367935409,
+      "grad_norm": 1.2967017889022827,
+      "learning_rate": 9.255818282826755e-06,
+      "loss": 0.4654,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5213379469434832,
+      "grad_norm": 1.256011962890625,
+      "learning_rate": 9.23453911090143e-06,
+      "loss": 0.4164,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5259515570934256,
+      "grad_norm": 0.8023069500923157,
+      "learning_rate": 9.21298516580153e-06,
+      "loss": 0.4471,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5305651672433679,
+      "grad_norm": 1.1097207069396973,
+      "learning_rate": 9.191157846131662e-06,
+      "loss": 0.438,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5351787773933102,
+      "grad_norm": 1.0085464715957642,
+      "learning_rate": 9.169058568235324e-06,
+      "loss": 0.4754,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5397923875432526,
+      "grad_norm": 1.2570720911026,
+      "learning_rate": 9.146688766102985e-06,
+      "loss": 0.4622,
+      "step": 1170
+    },
+    {
+      "epoch": 0.544405997693195,
+      "grad_norm": 0.8718953728675842,
+      "learning_rate": 9.124049891279052e-06,
+      "loss": 0.4778,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 1.1282092332839966,
+      "learning_rate": 9.101143412767665e-06,
+      "loss": 0.43,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5536332179930796,
+      "grad_norm": 1.1799993515014648,
+      "learning_rate": 9.077970816937394e-06,
+      "loss": 0.4398,
+      "step": 1200
+    },
+    {
+      "epoch": 0.558246828143022,
+      "grad_norm": 1.0852458477020264,
+      "learning_rate": 9.05453360742477e-06,
+      "loss": 0.4509,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5628604382929643,
+      "grad_norm": 0.9532956480979919,
+      "learning_rate": 9.030833305036732e-06,
+      "loss": 0.4322,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5674740484429066,
+      "grad_norm": 1.1594491004943848,
+      "learning_rate": 9.006871447651941e-06,
+      "loss": 0.4463,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5720876585928489,
+      "grad_norm": 1.0407638549804688,
+      "learning_rate": 8.982649590120982e-06,
+      "loss": 0.4744,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5767012687427913,
+      "grad_norm": 0.9278146028518677,
+      "learning_rate": 8.95816930416548e-06,
+      "loss": 0.4506,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5813148788927336,
+      "grad_norm": 1.0362186431884766,
+      "learning_rate": 8.933432178276108e-06,
+      "loss": 0.5047,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5859284890426759,
+      "grad_norm": 1.1875795125961304,
+      "learning_rate": 8.908439817609514e-06,
+      "loss": 0.4331,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5905420991926182,
+      "grad_norm": 1.0592981576919556,
+      "learning_rate": 8.883193843884169e-06,
+      "loss": 0.4869,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5951557093425606,
+      "grad_norm": 1.037862777709961,
+      "learning_rate": 8.857695895275127e-06,
+      "loss": 0.4568,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5997693194925029,
+      "grad_norm": 1.190478801727295,
+      "learning_rate": 8.831947626307735e-06,
+      "loss": 0.4291,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6043829296424452,
+      "grad_norm": 1.168628215789795,
+      "learning_rate": 8.805950707750268e-06,
+      "loss": 0.4864,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6089965397923875,
+      "grad_norm": 1.1069689989089966,
+      "learning_rate": 8.779706826505513e-06,
+      "loss": 0.4755,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6136101499423299,
+      "grad_norm": 1.0567044019699097,
+      "learning_rate": 8.753217685501317e-06,
+      "loss": 0.4429,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6182237600922722,
+      "grad_norm": 1.3095778226852417,
+      "learning_rate": 8.72648500358008e-06,
+      "loss": 0.4799,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6228373702422145,
+      "grad_norm": 1.2443181276321411,
+      "learning_rate": 8.699510515387222e-06,
+      "loss": 0.4238,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.9751482605934143,
+      "learning_rate": 8.672295971258624e-06,
+      "loss": 0.4621,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6320645905420992,
+      "grad_norm": 1.0337327718734741,
+      "learning_rate": 8.644843137107058e-06,
+      "loss": 0.482,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6366782006920415,
+      "grad_norm": 1.4924689531326294,
+      "learning_rate": 8.617153794307588e-06,
+      "loss": 0.4138,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6412918108419838,
+      "grad_norm": 1.1185983419418335,
+      "learning_rate": 8.58922973958199e-06,
+      "loss": 0.4808,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6459054209919262,
+      "grad_norm": 0.8987427949905396,
+      "learning_rate": 8.561072784882156e-06,
+      "loss": 0.4196,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6505190311418685,
+      "grad_norm": 0.9043972492218018,
+      "learning_rate": 8.532684757272527e-06,
+      "loss": 0.4675,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6551326412918108,
+      "grad_norm": 1.1553007364273071,
+      "learning_rate": 8.504067498811533e-06,
+      "loss": 0.4585,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6597462514417531,
+      "grad_norm": 1.2655616998672485,
+      "learning_rate": 8.475222866432065e-06,
+      "loss": 0.4557,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6643598615916955,
+      "grad_norm": 0.9298520684242249,
+      "learning_rate": 8.446152731820984e-06,
+      "loss": 0.4378,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6689734717416378,
+      "grad_norm": 1.0106518268585205,
+      "learning_rate": 8.416858981297663e-06,
+      "loss": 0.482,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6735870818915801,
+      "grad_norm": 0.7871996760368347,
+      "learning_rate": 8.387343515691594e-06,
+      "loss": 0.4153,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6782006920415224,
+      "grad_norm": 0.8685919046401978,
+      "learning_rate": 8.357608250219046e-06,
+      "loss": 0.4619,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6828143021914648,
+      "grad_norm": 1.3125975131988525,
+      "learning_rate": 8.327655114358782e-06,
+      "loss": 0.4327,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6874279123414071,
+      "grad_norm": 1.0396238565444946,
+      "learning_rate": 8.297486051726864e-06,
+      "loss": 0.4713,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6920415224913494,
+      "grad_norm": 0.7324469685554504,
+      "learning_rate": 8.267103019950529e-06,
+      "loss": 0.4197,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6920415224913494,
+      "eval_loss": 0.3744993507862091,
+      "eval_runtime": 409.5922,
+      "eval_samples_per_second": 8.23,
+      "eval_steps_per_second": 1.177,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6966551326412919,
+      "grad_norm": 1.0459123849868774,
+      "learning_rate": 8.23650799054117e-06,
+      "loss": 0.4525,
+      "step": 1510
+    },
+    {
+      "epoch": 0.7012687427912342,
+      "grad_norm": 0.972507655620575,
+      "learning_rate": 8.2057029487664e-06,
+      "loss": 0.4344,
+      "step": 1520
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.9018703103065491,
+      "learning_rate": 8.174689893521239e-06,
+      "loss": 0.4456,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7104959630911188,
+      "grad_norm": 1.1698877811431885,
+      "learning_rate": 8.143470837198394e-06,
+      "loss": 0.4342,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7151095732410612,
+      "grad_norm": 0.8043988943099976,
+      "learning_rate": 8.112047805557693e-06,
+      "loss": 0.4407,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7197231833910035,
+      "grad_norm": 1.0644773244857788,
+      "learning_rate": 8.080422837594627e-06,
+      "loss": 0.4188,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7243367935409458,
+      "grad_norm": 1.3345856666564941,
+      "learning_rate": 8.048597985408047e-06,
+      "loss": 0.4594,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7289504036908881,
+      "grad_norm": 0.9245930910110474,
+      "learning_rate": 8.016575314067005e-06,
+      "loss": 0.4549,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7335640138408305,
+      "grad_norm": 0.8729799389839172,
+      "learning_rate": 7.984356901476755e-06,
+      "loss": 0.4548,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7381776239907728,
+      "grad_norm": 1.0106137990951538,
+      "learning_rate": 7.951944838243916e-06,
+      "loss": 0.4452,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7427912341407151,
+      "grad_norm": 1.196505069732666,
+      "learning_rate": 7.919341227540828e-06,
+      "loss": 0.4491,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7474048442906575,
+      "grad_norm": 1.1595311164855957,
+      "learning_rate": 7.886548184969063e-06,
+      "loss": 0.4731,
+      "step": 1620
+    },
+    {
+      "epoch": 0.7520184544405998,
+      "grad_norm": 1.1693317890167236,
+      "learning_rate": 7.85356783842216e-06,
+      "loss": 0.432,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7566320645905421,
+      "grad_norm": 0.9775774478912354,
+      "learning_rate": 7.820402327947543e-06,
+      "loss": 0.461,
+      "step": 1640
+    },
+    {
+      "epoch": 0.7612456747404844,
+      "grad_norm": 1.2050389051437378,
+      "learning_rate": 7.78705380560766e-06,
+      "loss": 0.4118,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7658592848904268,
+      "grad_norm": 0.976572573184967,
+      "learning_rate": 7.753524435340334e-06,
+      "loss": 0.445,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7704728950403691,
+      "grad_norm": 0.9844825863838196,
+      "learning_rate": 7.719816392818354e-06,
+      "loss": 0.453,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7750865051903114,
+      "grad_norm": 0.966995894908905,
+      "learning_rate": 7.685931865308293e-06,
+      "loss": 0.4424,
+      "step": 1680
+    },
+    {
+      "epoch": 0.7797001153402537,
+      "grad_norm": 0.9509267807006836,
+      "learning_rate": 7.651873051528582e-06,
+      "loss": 0.4164,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.89404296875,
+      "learning_rate": 7.617642161506837e-06,
+      "loss": 0.4345,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7889273356401384,
+      "grad_norm": 1.4994254112243652,
+      "learning_rate": 7.583241416436462e-06,
+      "loss": 0.4373,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7935409457900807,
+      "grad_norm": 1.2022879123687744,
+      "learning_rate": 7.548673048532504e-06,
+      "loss": 0.4146,
+      "step": 1720
+    },
+    {
+      "epoch": 0.798154555940023,
+      "grad_norm": 1.1147469282150269,
+      "learning_rate": 7.513939300886816e-06,
+      "loss": 0.4008,
+      "step": 1730
+    },
+    {
+      "epoch": 0.8027681660899654,
+      "grad_norm": 0.9766092896461487,
+      "learning_rate": 7.479042427322509e-06,
+      "loss": 0.4401,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8073817762399077,
+      "grad_norm": 1.0522454977035522,
+      "learning_rate": 7.443984692247701e-06,
+      "loss": 0.4565,
+      "step": 1750
+    },
+    {
+      "epoch": 0.81199538638985,
+      "grad_norm": 0.9872923493385315,
+      "learning_rate": 7.408768370508577e-06,
+      "loss": 0.432,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8166089965397924,
+      "grad_norm": 0.729234516620636,
+      "learning_rate": 7.373395747241792e-06,
+      "loss": 0.3847,
+      "step": 1770
+    },
+    {
+      "epoch": 0.8212226066897347,
+      "grad_norm": 0.9378695487976074,
+      "learning_rate": 7.337869117726176e-06,
+      "loss": 0.412,
+      "step": 1780
+    },
+    {
+      "epoch": 0.825836216839677,
+      "grad_norm": 1.1060293912887573,
+      "learning_rate": 7.302190787233808e-06,
+      "loss": 0.4462,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8304498269896193,
+      "grad_norm": 1.1734408140182495,
+      "learning_rate": 7.266363070880424e-06,
+      "loss": 0.4321,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8350634371395617,
+      "grad_norm": 0.9876635670661926,
+      "learning_rate": 7.2303882934751965e-06,
+      "loss": 0.4477,
+      "step": 1810
+    },
+    {
+      "epoch": 0.839677047289504,
+      "grad_norm": 1.1338772773742676,
+      "learning_rate": 7.194268789369875e-06,
+      "loss": 0.4028,
+      "step": 1820
+    },
+    {
+      "epoch": 0.8442906574394463,
+      "grad_norm": 0.9537489414215088,
+      "learning_rate": 7.158006902307322e-06,
+      "loss": 0.457,
+      "step": 1830
+    },
+    {
+      "epoch": 0.8489042675893888,
+      "grad_norm": 1.215729832649231,
+      "learning_rate": 7.121604985269423e-06,
+      "loss": 0.4248,
+      "step": 1840
+    },
+    {
+      "epoch": 0.8535178777393311,
+      "grad_norm": 1.3123574256896973,
+      "learning_rate": 7.085065400324407e-06,
+      "loss": 0.4731,
+      "step": 1850
+    },
+    {
+      "epoch": 0.8581314878892734,
+      "grad_norm": 0.9171858429908752,
+      "learning_rate": 7.048390518473579e-06,
+      "loss": 0.3925,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 1.195125937461853,
+      "learning_rate": 7.011582719497466e-06,
+      "loss": 0.4481,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8673587081891581,
+      "grad_norm": 1.029279112815857,
+      "learning_rate": 6.974644391801395e-06,
+      "loss": 0.4487,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8719723183391004,
+      "grad_norm": 1.345962643623352,
+      "learning_rate": 6.9375779322605154e-06,
+      "loss": 0.4424,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8765859284890427,
+      "grad_norm": 0.9620792269706726,
+      "learning_rate": 6.900385746064268e-06,
+      "loss": 0.4628,
+      "step": 1900
+    },
+    {
+      "epoch": 0.881199538638985,
+      "grad_norm": 1.1548868417739868,
+      "learning_rate": 6.863070246560319e-06,
+      "loss": 0.4194,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8858131487889274,
+      "grad_norm": 0.8851338624954224,
+      "learning_rate": 6.825633855097954e-06,
+      "loss": 0.4404,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8904267589388697,
+      "grad_norm": 1.1914703845977783,
+      "learning_rate": 6.788079000870966e-06,
+      "loss": 0.4654,
+      "step": 1930
+    },
+    {
+      "epoch": 0.895040369088812,
+      "grad_norm": 0.8694286346435547,
+      "learning_rate": 6.7504081207600295e-06,
+      "loss": 0.4849,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8996539792387543,
+      "grad_norm": 0.9843218326568604,
+      "learning_rate": 6.712623659174569e-06,
+      "loss": 0.4286,
+      "step": 1950
+    },
+    {
+      "epoch": 0.9042675893886967,
+      "grad_norm": 1.0082261562347412,
+      "learning_rate": 6.674728067894149e-06,
+      "loss": 0.4271,
+      "step": 1960
+    },
+    {
+      "epoch": 0.908881199538639,
+      "grad_norm": 1.0179473161697388,
+      "learning_rate": 6.636723805909384e-06,
+      "loss": 0.4384,
+      "step": 1970
+    },
+    {
+      "epoch": 0.9134948096885813,
+      "grad_norm": 1.102802038192749,
+      "learning_rate": 6.598613339262369e-06,
+      "loss": 0.4058,
+      "step": 1980
+    },
+    {
+      "epoch": 0.9181084198385236,
+      "grad_norm": 1.0184437036514282,
+      "learning_rate": 6.560399140886673e-06,
+      "loss": 0.4047,
+      "step": 1990
+    },
+    {
+      "epoch": 0.922722029988466,
+      "grad_norm": 0.9515882134437561,
+      "learning_rate": 6.522083690446863e-06,
+      "loss": 0.4264,
+      "step": 2000
+    },
+    {
+      "epoch": 0.922722029988466,
+      "eval_loss": 0.3640458583831787,
+      "eval_runtime": 405.1587,
+      "eval_samples_per_second": 8.32,
+      "eval_steps_per_second": 1.19,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9273356401384083,
+      "grad_norm": 0.9829747080802917,
+      "learning_rate": 6.483669474177609e-06,
+      "loss": 0.4309,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9319492502883506,
+      "grad_norm": 1.134294033050537,
+      "learning_rate": 6.445158984722358e-06,
+      "loss": 0.4321,
+      "step": 2020
+    },
+    {
+      "epoch": 0.936562860438293,
+      "grad_norm": 0.8324179649353027,
+      "learning_rate": 6.406554720971583e-06,
+      "loss": 0.4118,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.9672048091888428,
+      "learning_rate": 6.367859187900635e-06,
+      "loss": 0.4508,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9457900807381776,
+      "grad_norm": 0.7900782823562622,
+      "learning_rate": 6.329074896407202e-06,
+      "loss": 0.4088,
+      "step": 2050
+    },
+    {
+      "epoch": 0.9504036908881199,
+      "grad_norm": 1.2132816314697266,
+      "learning_rate": 6.29020436314838e-06,
+      "loss": 0.4,
+      "step": 2060
+    },
+    {
+      "epoch": 0.9550173010380623,
+      "grad_norm": 1.028160810470581,
+      "learning_rate": 6.251250110377368e-06,
+      "loss": 0.4122,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9596309111880046,
+      "grad_norm": 0.979695200920105,
+      "learning_rate": 6.212214665779805e-06,
+      "loss": 0.4449,
+      "step": 2080
+    },
+    {
+      "epoch": 0.9642445213379469,
+      "grad_norm": 0.845983624458313,
+      "learning_rate": 6.173100562309751e-06,
+      "loss": 0.4229,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9688581314878892,
+      "grad_norm": 1.1386796236038208,
+      "learning_rate": 6.133910338025329e-06,
+      "loss": 0.4389,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9734717416378316,
+      "grad_norm": 1.0641363859176636,
+      "learning_rate": 6.094646535924026e-06,
+      "loss": 0.4459,
+      "step": 2110
+    },
+    {
+      "epoch": 0.9780853517877739,
+      "grad_norm": 1.2342710494995117,
+      "learning_rate": 6.055311703777699e-06,
+      "loss": 0.4556,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9826989619377162,
+      "grad_norm": 0.9290037751197815,
+      "learning_rate": 6.0159083939672326e-06,
+      "loss": 0.4837,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9873125720876585,
+      "grad_norm": 1.0555449724197388,
+      "learning_rate": 5.976439163316936e-06,
+      "loss": 0.4119,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9919261822376009,
+      "grad_norm": 1.001559853553772,
+      "learning_rate": 5.936906572928625e-06,
+      "loss": 0.4391,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9965397923875432,
+      "grad_norm": 1.120397686958313,
+      "learning_rate": 5.897313188015433e-06,
+      "loss": 0.4175,
+      "step": 2160
+    },
+    {
+      "epoch": 1.0009227220299886,
+      "grad_norm": 1.0661535263061523,
+      "learning_rate": 5.8576615777353725e-06,
+      "loss": 0.4176,
+      "step": 2170
+    },
+    {
+      "epoch": 1.0055363321799309,
+      "grad_norm": 0.8464300036430359,
+      "learning_rate": 5.81795431502461e-06,
+      "loss": 0.3182,
+      "step": 2180
+    },
+    {
+      "epoch": 1.0101499423298732,
+      "grad_norm": 1.150085687637329,
+      "learning_rate": 5.778193976430518e-06,
+      "loss": 0.3412,
+      "step": 2190
+    },
+    {
+      "epoch": 1.0147635524798155,
+      "grad_norm": 1.1552358865737915,
+      "learning_rate": 5.738383141944493e-06,
+      "loss": 0.3254,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0193771626297579,
+      "grad_norm": 0.8325443863868713,
+      "learning_rate": 5.698524394834531e-06,
+      "loss": 0.3121,
+      "step": 2210
+    },
+    {
+      "epoch": 1.0239907727797002,
+      "grad_norm": 0.9441822171211243,
+      "learning_rate": 5.658620321477613e-06,
+      "loss": 0.309,
+      "step": 2220
+    },
+    {
+      "epoch": 1.0286043829296425,
+      "grad_norm": 0.683917224407196,
+      "learning_rate": 5.6186735111918735e-06,
+      "loss": 0.2945,
+      "step": 2230
+    },
+    {
+      "epoch": 1.0332179930795848,
+      "grad_norm": 1.1293641328811646,
+      "learning_rate": 5.5786865560685855e-06,
+      "loss": 0.3277,
+      "step": 2240
+    },
+    {
+      "epoch": 1.0378316032295272,
+      "grad_norm": 1.0378141403198242,
+      "learning_rate": 5.538662050803965e-06,
+      "loss": 0.3337,
+      "step": 2250
+    },
+    {
+      "epoch": 1.0424452133794695,
+      "grad_norm": 0.8613712787628174,
+      "learning_rate": 5.498602592530799e-06,
+      "loss": 0.3145,
+      "step": 2260
+    },
+    {
+      "epoch": 1.0470588235294118,
+      "grad_norm": 0.8895742297172546,
+      "learning_rate": 5.458510780649932e-06,
+      "loss": 0.3016,
+      "step": 2270
+    },
+    {
+      "epoch": 1.0516724336793541,
+      "grad_norm": 0.8962990045547485,
+      "learning_rate": 5.41838921666158e-06,
+      "loss": 0.3107,
+      "step": 2280
+    },
+    {
+      "epoch": 1.0562860438292965,
+      "grad_norm": 1.1359519958496094,
+      "learning_rate": 5.378240503996531e-06,
+      "loss": 0.313,
+      "step": 2290
+    },
+    {
+      "epoch": 1.0608996539792388,
+      "grad_norm": 0.9063310027122498,
+      "learning_rate": 5.338067247847219e-06,
+      "loss": 0.3186,
+      "step": 2300
+    },
+    {
+      "epoch": 1.0655132641291811,
+      "grad_norm": 0.927183985710144,
+      "learning_rate": 5.297872054998663e-06,
+      "loss": 0.3198,
+      "step": 2310
+    },
+    {
+      "epoch": 1.0701268742791235,
+      "grad_norm": 1.573792815208435,
+      "learning_rate": 5.257657533659326e-06,
+      "loss": 0.3181,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0747404844290658,
+      "grad_norm": 1.2177760601043701,
+      "learning_rate": 5.217426293291869e-06,
+      "loss": 0.3369,
+      "step": 2330
+    },
+    {
+      "epoch": 1.079354094579008,
+      "grad_norm": 1.1653475761413574,
+      "learning_rate": 5.177180944443821e-06,
+      "loss": 0.311,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0839677047289504,
+      "grad_norm": 0.874153196811676,
+      "learning_rate": 5.136924098578201e-06,
+      "loss": 0.3109,
+      "step": 2350
+    },
+    {
+      "epoch": 1.0885813148788928,
+      "grad_norm": 1.03621244430542,
+      "learning_rate": 5.096658367904043e-06,
+      "loss": 0.2808,
+      "step": 2360
+    },
+    {
+      "epoch": 1.093194925028835,
+      "grad_norm": 1.4676544666290283,
+      "learning_rate": 5.056386365206908e-06,
+      "loss": 0.3435,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0978085351787774,
+      "grad_norm": 1.0248422622680664,
+      "learning_rate": 5.016110703679341e-06,
+      "loss": 0.3141,
+      "step": 2380
+    },
+    {
+      "epoch": 1.1024221453287197,
+      "grad_norm": 1.0083783864974976,
+      "learning_rate": 4.9758339967512995e-06,
+      "loss": 0.3074,
+      "step": 2390
+    },
+    {
+      "epoch": 1.107035755478662,
+      "grad_norm": 0.9300906658172607,
+      "learning_rate": 4.935558857920576e-06,
+      "loss": 0.3255,
+      "step": 2400
+    },
+    {
+      "epoch": 1.1116493656286044,
+      "grad_norm": 1.1581122875213623,
+      "learning_rate": 4.895287900583216e-06,
+      "loss": 0.3007,
+      "step": 2410
+    },
+    {
+      "epoch": 1.1162629757785467,
+      "grad_norm": 1.3533753156661987,
+      "learning_rate": 4.855023737863927e-06,
+      "loss": 0.3383,
+      "step": 2420
+    },
+    {
+      "epoch": 1.120876585928489,
+      "grad_norm": 1.157009482383728,
+      "learning_rate": 4.814768982446532e-06,
+      "loss": 0.3207,
+      "step": 2430
+    },
+    {
+      "epoch": 1.1254901960784314,
+      "grad_norm": 1.2679253816604614,
+      "learning_rate": 4.774526246404417e-06,
+      "loss": 0.3069,
+      "step": 2440
+    },
+    {
+      "epoch": 1.1301038062283737,
+      "grad_norm": 1.1905463933944702,
+      "learning_rate": 4.734298141031057e-06,
+      "loss": 0.2949,
+      "step": 2450
+    },
+    {
+      "epoch": 1.134717416378316,
+      "grad_norm": 0.9034658670425415,
+      "learning_rate": 4.69408727667056e-06,
+      "loss": 0.3602,
+      "step": 2460
+    },
+    {
+      "epoch": 1.1393310265282584,
+      "grad_norm": 0.964447021484375,
+      "learning_rate": 4.653896262548291e-06,
+      "loss": 0.2999,
+      "step": 2470
+    },
+    {
+      "epoch": 1.1439446366782007,
+      "grad_norm": 0.8305296897888184,
+      "learning_rate": 4.613727706601558e-06,
+      "loss": 0.3186,
+      "step": 2480
+    },
+    {
+      "epoch": 1.148558246828143,
+      "grad_norm": 1.3243507146835327,
+      "learning_rate": 4.573584215310394e-06,
+      "loss": 0.2857,
+      "step": 2490
+    },
+    {
+      "epoch": 1.1531718569780853,
+      "grad_norm": 1.1306155920028687,
+      "learning_rate": 4.533468393528421e-06,
+      "loss": 0.3188,
+      "step": 2500
+    },
+    {
+      "epoch": 1.1531718569780853,
+      "eval_loss": 0.36377301812171936,
+      "eval_runtime": 432.1909,
+      "eval_samples_per_second": 7.8,
+      "eval_steps_per_second": 1.115,
+      "step": 2500
+    },
+    {
+      "epoch": 1.1577854671280277,
+      "grad_norm": 1.311614751815796,
+      "learning_rate": 4.493382844313826e-06,
+      "loss": 0.3255,
+      "step": 2510
+    },
+    {
+      "epoch": 1.16239907727797,
+      "grad_norm": 1.1632609367370605,
+      "learning_rate": 4.453330168760451e-06,
+      "loss": 0.3408,
+      "step": 2520
+    },
+    {
+      "epoch": 1.1670126874279123,
+      "grad_norm": 0.9437416195869446,
+      "learning_rate": 4.41331296582902e-06,
+      "loss": 0.3562,
+      "step": 2530
+    },
+    {
+      "epoch": 1.1716262975778546,
+      "grad_norm": 1.4374769926071167,
+      "learning_rate": 4.373333832178478e-06,
+      "loss": 0.3049,
+      "step": 2540
+    },
+    {
+      "epoch": 1.176239907727797,
+      "grad_norm": 0.9964131712913513,
+      "learning_rate": 4.333395361997521e-06,
+      "loss": 0.3223,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1808535178777393,
+      "grad_norm": 0.7799270749092102,
+      "learning_rate": 4.293500146836241e-06,
+      "loss": 0.2913,
+      "step": 2560
+    },
+    {
+      "epoch": 1.1854671280276816,
+      "grad_norm": 1.0871920585632324,
+      "learning_rate": 4.25365077543798e-06,
+      "loss": 0.2823,
+      "step": 2570
+    },
+    {
+      "epoch": 1.190080738177624,
+      "grad_norm": 1.0069403648376465,
+      "learning_rate": 4.213849833571341e-06,
+      "loss": 0.3583,
+      "step": 2580
+    },
+    {
+      "epoch": 1.1946943483275663,
+      "grad_norm": 0.9551932215690613,
+      "learning_rate": 4.174099903862403e-06,
+      "loss": 0.3101,
+      "step": 2590
+    },
+    {
+      "epoch": 1.1993079584775086,
+      "grad_norm": 0.7922395467758179,
+      "learning_rate": 4.134403565627144e-06,
+      "loss": 0.3311,
+      "step": 2600
+    },
+    {
+      "epoch": 1.203921568627451,
+      "grad_norm": 1.0218504667282104,
+      "learning_rate": 4.0947633947040616e-06,
+      "loss": 0.3437,
+      "step": 2610
+    },
+    {
+      "epoch": 1.2085351787773932,
+      "grad_norm": 1.01131272315979,
+      "learning_rate": 4.055181963287044e-06,
+      "loss": 0.2788,
+      "step": 2620
+    },
+    {
+      "epoch": 1.2131487889273356,
+      "grad_norm": 0.9900946021080017,
+      "learning_rate": 4.01566183975845e-06,
+      "loss": 0.3188,
+      "step": 2630
+    },
+    {
+      "epoch": 1.217762399077278,
+      "grad_norm": 1.219028353691101,
+      "learning_rate": 3.9762055885224614e-06,
+      "loss": 0.2936,
+      "step": 2640
+    },
+    {
+      "epoch": 1.2223760092272202,
+      "grad_norm": 1.4025200605392456,
+      "learning_rate": 3.936815769838682e-06,
+      "loss": 0.266,
+      "step": 2650
+    },
+    {
+      "epoch": 1.2269896193771626,
+      "grad_norm": 1.1445423364639282,
+      "learning_rate": 3.897494939655996e-06,
+      "loss": 0.315,
+      "step": 2660
+    },
+    {
+      "epoch": 1.2316032295271049,
+      "grad_norm": 1.1953898668289185,
+      "learning_rate": 3.8582456494467214e-06,
+      "loss": 0.3161,
+      "step": 2670
+    },
+    {
+      "epoch": 1.2362168396770472,
+      "grad_norm": 1.501749873161316,
+      "learning_rate": 3.819070446041059e-06,
+      "loss": 0.3216,
+      "step": 2680
+    },
+    {
+      "epoch": 1.2408304498269895,
+      "grad_norm": 0.9947803616523743,
+      "learning_rate": 3.779971871461813e-06,
+      "loss": 0.3184,
+      "step": 2690
+    },
+    {
+      "epoch": 1.2454440599769319,
+      "grad_norm": 0.9146224856376648,
+      "learning_rate": 3.7409524627594607e-06,
+      "loss": 0.3097,
+      "step": 2700
+    },
+    {
+      "epoch": 1.2500576701268744,
+      "grad_norm": 1.1721278429031372,
+      "learning_rate": 3.702014751847514e-06,
+      "loss": 0.2805,
+      "step": 2710
+    },
+    {
+      "epoch": 1.2546712802768165,
+      "grad_norm": 0.8447152972221375,
+      "learning_rate": 3.6631612653382354e-06,
+      "loss": 0.3199,
+      "step": 2720
+    },
+    {
+      "epoch": 1.259284890426759,
+      "grad_norm": 1.5338748693466187,
+      "learning_rate": 3.624394524378684e-06,
+      "loss": 0.3204,
+      "step": 2730
+    },
+    {
+      "epoch": 1.2638985005767012,
+      "grad_norm": 0.9287798404693604,
+      "learning_rate": 3.585717044487126e-06,
+      "loss": 0.3378,
+      "step": 2740
+    },
+    {
+      "epoch": 1.2685121107266437,
+      "grad_norm": 1.4134514331817627,
+      "learning_rate": 3.5471313353898056e-06,
+      "loss": 0.3073,
+      "step": 2750
+    },
+    {
+      "epoch": 1.2731257208765858,
+      "grad_norm": 1.08121919631958,
+      "learning_rate": 3.5086399008580885e-06,
+      "loss": 0.3255,
+      "step": 2760
+    },
+    {
+      "epoch": 1.2777393310265284,
+      "grad_norm": 1.100626826286316,
+      "learning_rate": 3.470245238546002e-06,
+      "loss": 0.3108,
+      "step": 2770
+    },
+    {
+      "epoch": 1.2823529411764705,
+      "grad_norm": 0.8085044622421265,
+      "learning_rate": 3.4319498398281638e-06,
+      "loss": 0.2944,
+      "step": 2780
+    },
+    {
+      "epoch": 1.286966551326413,
+      "grad_norm": 1.2880297899246216,
+      "learning_rate": 3.393756189638115e-06,
+      "loss": 0.3167,
+      "step": 2790
+    },
+    {
+      "epoch": 1.2915801614763551,
+      "grad_norm": 1.2243609428405762,
+      "learning_rate": 3.355666766307084e-06,
+      "loss": 0.3009,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2961937716262977,
+      "grad_norm": 0.699437141418457,
+      "learning_rate": 3.3176840414031653e-06,
+      "loss": 0.2878,
+      "step": 2810
+    },
+    {
+      "epoch": 1.3008073817762398,
+      "grad_norm": 1.0296318531036377,
+      "learning_rate": 3.2798104795709484e-06,
+      "loss": 0.2743,
+      "step": 2820
+    },
+    {
+      "epoch": 1.3054209919261823,
+      "grad_norm": 1.024989366531372,
+      "learning_rate": 3.242048538371585e-06,
+      "loss": 0.3117,
+      "step": 2830
+    },
+    {
+      "epoch": 1.3100346020761244,
+      "grad_norm": 1.111118197441101,
+      "learning_rate": 3.2044006681233226e-06,
+      "loss": 0.3065,
+      "step": 2840
+    },
+    {
+      "epoch": 1.314648212226067,
+      "grad_norm": 1.0204840898513794,
+      "learning_rate": 3.1668693117425128e-06,
+      "loss": 0.3182,
+      "step": 2850
+    },
+    {
+      "epoch": 1.3192618223760093,
+      "grad_norm": 0.909860372543335,
+      "learning_rate": 3.1294569045850844e-06,
+      "loss": 0.3362,
+      "step": 2860
+    },
+    {
+      "epoch": 1.3238754325259516,
+      "grad_norm": 1.1789814233779907,
+      "learning_rate": 3.092165874288525e-06,
+      "loss": 0.3202,
+      "step": 2870
+    },
+    {
+      "epoch": 1.328489042675894,
+      "grad_norm": 0.8858640193939209,
+      "learning_rate": 3.05499864061435e-06,
+      "loss": 0.3061,
+      "step": 2880
+    },
+    {
+      "epoch": 1.3331026528258363,
+      "grad_norm": 0.8976421356201172,
+      "learning_rate": 3.017957615291088e-06,
+      "loss": 0.2937,
+      "step": 2890
+    },
+    {
+      "epoch": 1.3377162629757786,
+      "grad_norm": 1.0524935722351074,
+      "learning_rate": 2.981045201857796e-06,
+      "loss": 0.3056,
+      "step": 2900
+    },
+    {
+      "epoch": 1.342329873125721,
+      "grad_norm": 1.0822246074676514,
+      "learning_rate": 2.9442637955080787e-06,
+      "loss": 0.2964,
+      "step": 2910
+    },
+    {
+      "epoch": 1.3469434832756633,
+      "grad_norm": 1.043286681175232,
+      "learning_rate": 2.9076157829346883e-06,
+      "loss": 0.322,
+      "step": 2920
+    },
+    {
+      "epoch": 1.3515570934256056,
+      "grad_norm": 1.2808856964111328,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.3186,
+      "step": 2930
+    },
+    {
+      "epoch": 1.356170703575548,
+      "grad_norm": 0.9058982729911804,
+      "learning_rate": 2.8347294424549075e-06,
+      "loss": 0.2989,
+      "step": 2940
+    },
+    {
+      "epoch": 1.3607843137254902,
+      "grad_norm": 0.8408973217010498,
+      "learning_rate": 2.7984958440387045e-06,
+      "loss": 0.3095,
+      "step": 2950
+    },
+    {
+      "epoch": 1.3653979238754326,
+      "grad_norm": 0.7515527606010437,
+      "learning_rate": 2.7624050980723032e-06,
+      "loss": 0.3209,
+      "step": 2960
+    },
+    {
+      "epoch": 1.370011534025375,
+      "grad_norm": 0.9075823426246643,
+      "learning_rate": 2.726459546432488e-06,
+      "loss": 0.3238,
+      "step": 2970
+    },
+    {
+      "epoch": 1.3746251441753172,
+      "grad_norm": 0.7237765192985535,
+      "learning_rate": 2.690661521574596e-06,
+      "loss": 0.2856,
+      "step": 2980
+    },
+    {
+      "epoch": 1.3792387543252596,
+      "grad_norm": 1.110317349433899,
+      "learning_rate": 2.655013346381158e-06,
+      "loss": 0.3145,
+      "step": 2990
+    },
+    {
+      "epoch": 1.3838523644752019,
+      "grad_norm": 0.925359845161438,
+      "learning_rate": 2.6195173340111767e-06,
+      "loss": 0.2938,
+      "step": 3000
+    },
+    {
+      "epoch": 1.3838523644752019,
+      "eval_loss": 0.3571609854698181,
+      "eval_runtime": 407.4112,
+      "eval_samples_per_second": 8.274,
+      "eval_steps_per_second": 1.183,
+      "step": 3000
+    },
+    {
+      "epoch": 1.3884659746251442,
+      "grad_norm": 0.768183171749115,
+      "learning_rate": 2.5841757877500245e-06,
+      "loss": 0.2978,
+      "step": 3010
+    },
+    {
+      "epoch": 1.3930795847750865,
+      "grad_norm": 0.9414054751396179,
+      "learning_rate": 2.548991000859997e-06,
+      "loss": 0.2824,
+      "step": 3020
+    },
+    {
+      "epoch": 1.3976931949250289,
+      "grad_norm": 1.148766040802002,
+      "learning_rate": 2.513965256431488e-06,
+      "loss": 0.3256,
+      "step": 3030
+    },
+    {
+      "epoch": 1.4023068050749712,
+      "grad_norm": 1.0877196788787842,
+      "learning_rate": 2.4791008272348656e-06,
+      "loss": 0.3297,
+      "step": 3040
+    },
+    {
+      "epoch": 1.4069204152249135,
+      "grad_norm": 1.0412601232528687,
+      "learning_rate": 2.444399975572974e-06,
+      "loss": 0.3279,
+      "step": 3050
+    },
+    {
+      "epoch": 1.4115340253748558,
+      "grad_norm": 1.1179814338684082,
+      "learning_rate": 2.40986495313435e-06,
+      "loss": 0.3103,
+      "step": 3060
+    },
+    {
+      "epoch": 1.4161476355247982,
+      "grad_norm": 0.7637813091278076,
+      "learning_rate": 2.3754980008471074e-06,
+      "loss": 0.3231,
+      "step": 3070
+    },
+    {
+      "epoch": 1.4207612456747405,
+      "grad_norm": 1.0383415222167969,
+      "learning_rate": 2.3413013487335332e-06,
+      "loss": 0.3138,
+      "step": 3080
+    },
+    {
+      "epoch": 1.4253748558246828,
+      "grad_norm": 0.8388441801071167,
+      "learning_rate": 2.307277215765377e-06,
+      "loss": 0.2695,
+      "step": 3090
+    },
+    {
+      "epoch": 1.4299884659746251,
+      "grad_norm": 0.9990552663803101,
+      "learning_rate": 2.273427809719867e-06,
+      "loss": 0.2983,
+      "step": 3100
+    },
+    {
+      "epoch": 1.4346020761245675,
+      "grad_norm": 0.8428414463996887,
+      "learning_rate": 2.2397553270364546e-06,
+      "loss": 0.3141,
+      "step": 3110
+    },
+    {
+      "epoch": 1.4392156862745098,
+      "grad_norm": 0.9415843486785889,
+      "learning_rate": 2.206261952674284e-06,
+      "loss": 0.2959,
+      "step": 3120
+    },
+    {
+      "epoch": 1.4438292964244521,
+      "grad_norm": 1.3723379373550415,
+      "learning_rate": 2.172949859970422e-06,
+      "loss": 0.3348,
+      "step": 3130
+    },
+    {
+      "epoch": 1.4484429065743945,
+      "grad_norm": 0.8914421796798706,
+      "learning_rate": 2.1398212104988273e-06,
+      "loss": 0.3098,
+      "step": 3140
+    },
+    {
+      "epoch": 1.4530565167243368,
+      "grad_norm": 0.8774773478507996,
+      "learning_rate": 2.1068781539300874e-06,
+      "loss": 0.2701,
+      "step": 3150
+    },
+    {
+      "epoch": 1.457670126874279,
+      "grad_norm": 1.0844688415527344,
+      "learning_rate": 2.0741228278919347e-06,
+      "loss": 0.3135,
+      "step": 3160
+    },
+    {
+      "epoch": 1.4622837370242214,
+      "grad_norm": 1.0603561401367188,
+      "learning_rate": 2.0415573578305343e-06,
+      "loss": 0.3234,
+      "step": 3170
+    },
+    {
+      "epoch": 1.4668973471741638,
+      "grad_norm": 0.9056031703948975,
+      "learning_rate": 2.0091838568725685e-06,
+      "loss": 0.3034,
+      "step": 3180
+    },
+    {
+      "epoch": 1.471510957324106,
+      "grad_norm": 0.8055946230888367,
+      "learning_rate": 1.977004425688126e-06,
+      "loss": 0.3403,
+      "step": 3190
+    },
+    {
+      "epoch": 1.4761245674740484,
+      "grad_norm": 1.1034411191940308,
+      "learning_rate": 1.945021152354379e-06,
+      "loss": 0.3235,
+      "step": 3200
+    },
+    {
+      "epoch": 1.4807381776239907,
+      "grad_norm": 1.3559411764144897,
+      "learning_rate": 1.913236112220101e-06,
+      "loss": 0.2852,
+      "step": 3210
+    },
+    {
+      "epoch": 1.485351787773933,
+      "grad_norm": 1.1443620920181274,
+      "learning_rate": 1.8816513677709935e-06,
+      "loss": 0.3362,
+      "step": 3220
+    },
+    {
+      "epoch": 1.4899653979238754,
+      "grad_norm": 0.9599668979644775,
+      "learning_rate": 1.8502689684958664e-06,
+      "loss": 0.2814,
+      "step": 3230
+    },
+    {
+      "epoch": 1.4945790080738177,
+      "grad_norm": 1.053106665611267,
+      "learning_rate": 1.8190909507536326e-06,
+      "loss": 0.3092,
+      "step": 3240
+    },
+    {
+      "epoch": 1.49919261822376,
+      "grad_norm": 0.979612410068512,
+      "learning_rate": 1.7881193376411822e-06,
+      "loss": 0.2931,
+      "step": 3250
+    },
+    {
+      "epoch": 1.5038062283737024,
+      "grad_norm": 1.0935841798782349,
+      "learning_rate": 1.7573561388621102e-06,
+      "loss": 0.2852,
+      "step": 3260
+    },
+    {
+      "epoch": 1.5084198385236447,
+      "grad_norm": 1.003023386001587,
+      "learning_rate": 1.7268033505962972e-06,
+      "loss": 0.3252,
+      "step": 3270
+    },
+    {
+      "epoch": 1.5130334486735872,
+      "grad_norm": 0.8895878195762634,
+      "learning_rate": 1.6964629553703893e-06,
+      "loss": 0.2965,
+      "step": 3280
+    },
+    {
+      "epoch": 1.5176470588235293,
+      "grad_norm": 1.2238770723342896,
+      "learning_rate": 1.6663369219291558e-06,
+      "loss": 0.3256,
+      "step": 3290
+    },
+    {
+      "epoch": 1.522260668973472,
+      "grad_norm": 0.9977489709854126,
+      "learning_rate": 1.6364272051077335e-06,
+      "loss": 0.3087,
+      "step": 3300
+    },
+    {
+      "epoch": 1.526874279123414,
+      "grad_norm": 0.8793919682502747,
+      "learning_rate": 1.606735745704784e-06,
+      "loss": 0.3082,
+      "step": 3310
+    },
+    {
+      "epoch": 1.5314878892733566,
+      "grad_norm": 1.015448808670044,
+      "learning_rate": 1.5772644703565564e-06,
+      "loss": 0.3089,
+      "step": 3320
+    },
+    {
+      "epoch": 1.5361014994232987,
+      "grad_norm": 0.9907401204109192,
+      "learning_rate": 1.5480152914118784e-06,
+      "loss": 0.312,
+      "step": 3330
+    },
+    {
+      "epoch": 1.5407151095732412,
+      "grad_norm": 1.1181472539901733,
+      "learning_rate": 1.5189901068080536e-06,
+      "loss": 0.2756,
+      "step": 3340
+    },
+    {
+      "epoch": 1.5453287197231833,
+      "grad_norm": 0.7450747489929199,
+      "learning_rate": 1.4901907999477167e-06,
+      "loss": 0.2931,
+      "step": 3350
+    },
+    {
+      "epoch": 1.5499423298731259,
+      "grad_norm": 0.7395336031913757,
+      "learning_rate": 1.4616192395766189e-06,
+      "loss": 0.3312,
+      "step": 3360
+    },
+    {
+      "epoch": 1.554555940023068,
+      "grad_norm": 1.0844025611877441,
+      "learning_rate": 1.4332772796623655e-06,
+      "loss": 0.2877,
+      "step": 3370
+    },
+    {
+      "epoch": 1.5591695501730105,
+      "grad_norm": 1.0162688493728638,
+      "learning_rate": 1.405166759274123e-06,
+      "loss": 0.2865,
+      "step": 3380
+    },
+    {
+      "epoch": 1.5637831603229526,
+      "grad_norm": 1.459636926651001,
+      "learning_rate": 1.3772895024632753e-06,
+      "loss": 0.2772,
+      "step": 3390
+    },
+    {
+      "epoch": 1.5683967704728952,
+      "grad_norm": 1.1167926788330078,
+      "learning_rate": 1.349647318145067e-06,
+      "loss": 0.2826,
+      "step": 3400
+    },
+    {
+      "epoch": 1.5730103806228373,
+      "grad_norm": 1.4571030139923096,
+      "learning_rate": 1.3222419999812248e-06,
+      "loss": 0.2582,
+      "step": 3410
+    },
+    {
+      "epoch": 1.5776239907727798,
+      "grad_norm": 1.154638648033142,
+      "learning_rate": 1.2950753262635712e-06,
+      "loss": 0.3361,
+      "step": 3420
+    },
+    {
+      "epoch": 1.582237600922722,
+      "grad_norm": 0.5414898991584778,
+      "learning_rate": 1.2681490597986313e-06,
+      "loss": 0.305,
+      "step": 3430
+    },
+    {
+      "epoch": 1.5868512110726645,
+      "grad_norm": 0.8521725535392761,
+      "learning_rate": 1.2414649477932511e-06,
+      "loss": 0.2935,
+      "step": 3440
+    },
+    {
+      "epoch": 1.5914648212226066,
+      "grad_norm": 1.0056465864181519,
+      "learning_rate": 1.2150247217412186e-06,
+      "loss": 0.3227,
+      "step": 3450
+    },
+    {
+      "epoch": 1.5960784313725491,
+      "grad_norm": 1.3629816770553589,
+      "learning_rate": 1.1888300973109112e-06,
+      "loss": 0.3037,
+      "step": 3460
+    },
+    {
+      "epoch": 1.6006920415224912,
+      "grad_norm": 1.0090680122375488,
+      "learning_rate": 1.1628827742339688e-06,
+      "loss": 0.3172,
+      "step": 3470
+    },
+    {
+      "epoch": 1.6053056516724338,
+      "grad_norm": 1.347844123840332,
+      "learning_rate": 1.1371844361950045e-06,
+      "loss": 0.3046,
+      "step": 3480
+    },
+    {
+      "epoch": 1.6099192618223759,
+      "grad_norm": 0.7335895299911499,
+      "learning_rate": 1.1117367507223452e-06,
+      "loss": 0.3107,
+      "step": 3490
+    },
+    {
+      "epoch": 1.6145328719723184,
+      "grad_norm": 0.8737802505493164,
+      "learning_rate": 1.0865413690798321e-06,
+      "loss": 0.2891,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6145328719723184,
+      "eval_loss": 0.3522779047489166,
+      "eval_runtime": 405.2938,
+      "eval_samples_per_second": 8.317,
+      "eval_steps_per_second": 1.189,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6191464821222605,
+      "grad_norm": 0.9549174904823303,
+      "learning_rate": 1.061599926159676e-06,
+      "loss": 0.3177,
+      "step": 3510
+    },
+    {
+      "epoch": 1.623760092272203,
+      "grad_norm": 1.2092400789260864,
+      "learning_rate": 1.036914040376364e-06,
+      "loss": 0.2951,
+      "step": 3520
+    },
+    {
+      "epoch": 1.6283737024221452,
+      "grad_norm": 0.9136941432952881,
+      "learning_rate": 1.0124853135616475e-06,
+      "loss": 0.273,
+      "step": 3530
+    },
+    {
+      "epoch": 1.6329873125720877,
+      "grad_norm": 0.8041252493858337,
+      "learning_rate": 9.883153308606035e-07,
+      "loss": 0.307,
+      "step": 3540
+    },
+    {
+      "epoch": 1.6376009227220298,
+      "grad_norm": 2.2038888931274414,
+      "learning_rate": 9.644056606287727e-07,
+      "loss": 0.3031,
+      "step": 3550
+    },
+    {
+      "epoch": 1.6422145328719724,
+      "grad_norm": 0.995631754398346,
+      "learning_rate": 9.407578543303913e-07,
+      "loss": 0.3121,
+      "step": 3560
+    },
+    {
+      "epoch": 1.6468281430219145,
+      "grad_norm": 1.1409215927124023,
+      "learning_rate": 9.173734464377204e-07,
+      "loss": 0.2709,
+      "step": 3570
+    },
+    {
+      "epoch": 1.651441753171857,
+      "grad_norm": 1.1905242204666138,
+      "learning_rate": 8.942539543314799e-07,
+      "loss": 0.2877,
+      "step": 3580
+    },
+    {
+      "epoch": 1.6560553633217991,
+      "grad_norm": 1.2991387844085693,
+      "learning_rate": 8.714008782023797e-07,
+      "loss": 0.306,
+      "step": 3590
+    },
+    {
+      "epoch": 1.6606689734717417,
+      "grad_norm": 1.122862696647644,
+      "learning_rate": 8.488157009537796e-07,
+      "loss": 0.3156,
+      "step": 3600
+    },
+    {
+      "epoch": 1.665282583621684,
+      "grad_norm": 1.0552375316619873,
+      "learning_rate": 8.264998881054659e-07,
+      "loss": 0.3164,
+      "step": 3610
+    },
+    {
+      "epoch": 1.6698961937716263,
+      "grad_norm": 1.0529013872146606,
+      "learning_rate": 8.044548876985531e-07,
+      "loss": 0.2823,
+      "step": 3620
+    },
+    {
+      "epoch": 1.6745098039215687,
+      "grad_norm": 1.0816291570663452,
+      "learning_rate": 7.826821302015275e-07,
+      "loss": 0.3184,
+      "step": 3630
+    },
+    {
+      "epoch": 1.679123414071511,
+      "grad_norm": 0.7152329683303833,
+      "learning_rate": 7.61183028417422e-07,
+      "loss": 0.2956,
+      "step": 3640
+    },
+    {
+      "epoch": 1.6837370242214533,
+      "grad_norm": 0.9819076061248779,
+      "learning_rate": 7.399589773921412e-07,
+      "loss": 0.3187,
+      "step": 3650
+    },
+    {
+      "epoch": 1.6883506343713957,
+      "grad_norm": 0.6662834286689758,
+      "learning_rate": 7.190113543239408e-07,
+      "loss": 0.3194,
+      "step": 3660
+    },
+    {
+      "epoch": 1.692964244521338,
+      "grad_norm": 1.200137734413147,
+      "learning_rate": 6.983415184740616e-07,
+      "loss": 0.2958,
+      "step": 3670
+    },
+    {
+      "epoch": 1.6975778546712803,
+      "grad_norm": 0.8711331486701965,
+      "learning_rate": 6.779508110785332e-07,
+      "loss": 0.2761,
+      "step": 3680
+    },
+    {
+      "epoch": 1.7021914648212226,
+      "grad_norm": 1.2060991525650024,
+      "learning_rate": 6.578405552611361e-07,
+      "loss": 0.2758,
+      "step": 3690
+    },
+    {
+      "epoch": 1.706805074971165,
+      "grad_norm": 0.7914460897445679,
+      "learning_rate": 6.380120559475505e-07,
+      "loss": 0.3272,
+      "step": 3700
+    },
+    {
+      "epoch": 1.7114186851211073,
+      "grad_norm": 1.0925244092941284,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.2947,
+      "step": 3710
+    },
+    {
+      "epoch": 1.7160322952710496,
+      "grad_norm": 0.9509474635124207,
+      "learning_rate": 5.992054550371723e-07,
+      "loss": 0.3304,
+      "step": 3720
+    },
+    {
+      "epoch": 1.720645905420992,
+      "grad_norm": 1.3933912515640259,
+      "learning_rate": 5.802298715451016e-07,
+      "loss": 0.3214,
+      "step": 3730
+    },
+    {
+      "epoch": 1.7252595155709343,
+      "grad_norm": 1.1641534566879272,
+      "learning_rate": 5.615410806028875e-07,
+      "loss": 0.2974,
+      "step": 3740
+    },
+    {
+      "epoch": 1.7298731257208766,
+      "grad_norm": 0.8583273887634277,
+      "learning_rate": 5.431402948993947e-07,
+      "loss": 0.2869,
+      "step": 3750
+    },
+    {
+      "epoch": 1.734486735870819,
+      "grad_norm": 1.1167171001434326,
+      "learning_rate": 5.250287084352373e-07,
+      "loss": 0.329,
+      "step": 3760
+    },
+    {
+      "epoch": 1.7391003460207612,
+      "grad_norm": 1.1780617237091064,
+      "learning_rate": 5.072074964453055e-07,
+      "loss": 0.3262,
+      "step": 3770
+    },
+    {
+      "epoch": 1.7437139561707036,
+      "grad_norm": 1.1685618162155151,
+      "learning_rate": 4.896778153225062e-07,
+      "loss": 0.2963,
+      "step": 3780
+    },
+    {
+      "epoch": 1.748327566320646,
+      "grad_norm": 1.0674740076065063,
+      "learning_rate": 4.7244080254272795e-07,
+      "loss": 0.3124,
+      "step": 3790
+    },
+    {
+      "epoch": 1.7529411764705882,
+      "grad_norm": 1.2227847576141357,
+      "learning_rate": 4.55497576591028e-07,
+      "loss": 0.293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.7575547866205306,
+      "grad_norm": 1.0834511518478394,
+      "learning_rate": 4.3884923688905676e-07,
+      "loss": 0.3092,
+      "step": 3810
+    },
+    {
+      "epoch": 1.7621683967704729,
+      "grad_norm": 0.7183946371078491,
+      "learning_rate": 4.224968637237198e-07,
+      "loss": 0.2644,
+      "step": 3820
+    },
+    {
+      "epoch": 1.7667820069204152,
+      "grad_norm": 1.1382250785827637,
+      "learning_rate": 4.064415181770787e-07,
+      "loss": 0.2823,
+      "step": 3830
+    },
+    {
+      "epoch": 1.7713956170703575,
+      "grad_norm": 1.1042758226394653,
+      "learning_rate": 3.90684242057498e-07,
+      "loss": 0.3121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.7760092272202999,
+      "grad_norm": 0.8227053284645081,
+      "learning_rate": 3.752260578320427e-07,
+      "loss": 0.3145,
+      "step": 3850
+    },
+    {
+      "epoch": 1.7806228373702422,
+      "grad_norm": 1.0205223560333252,
+      "learning_rate": 3.600679685601349e-07,
+      "loss": 0.3086,
+      "step": 3860
+    },
+    {
+      "epoch": 1.7852364475201845,
+      "grad_norm": 0.8816052675247192,
+      "learning_rate": 3.4521095782846623e-07,
+      "loss": 0.2978,
+      "step": 3870
+    },
+    {
+      "epoch": 1.7898500576701268,
+      "grad_norm": 1.44774329662323,
+      "learning_rate": 3.306559896871714e-07,
+      "loss": 0.3016,
+      "step": 3880
+    },
+    {
+      "epoch": 1.7944636678200692,
+      "grad_norm": 0.9304317235946655,
+      "learning_rate": 3.164040085872755e-07,
+      "loss": 0.3066,
+      "step": 3890
+    },
+    {
+      "epoch": 1.7990772779700115,
+      "grad_norm": 1.0888575315475464,
+      "learning_rate": 3.0245593931940766e-07,
+      "loss": 0.2851,
+      "step": 3900
+    },
+    {
+      "epoch": 1.8036908881199538,
+      "grad_norm": 0.8086104989051819,
+      "learning_rate": 2.8881268695379436e-07,
+      "loss": 0.2901,
+      "step": 3910
+    },
+    {
+      "epoch": 1.8083044982698961,
+      "grad_norm": 0.7356364727020264,
+      "learning_rate": 2.7547513678153005e-07,
+      "loss": 0.2997,
+      "step": 3920
+    },
+    {
+      "epoch": 1.8129181084198385,
+      "grad_norm": 1.017858624458313,
+      "learning_rate": 2.624441542571327e-07,
+      "loss": 0.3282,
+      "step": 3930
+    },
+    {
+      "epoch": 1.8175317185697808,
+      "grad_norm": 0.9155429601669312,
+      "learning_rate": 2.497205849423834e-07,
+      "loss": 0.2596,
+      "step": 3940
+    },
+    {
+      "epoch": 1.8221453287197233,
+      "grad_norm": 0.9723671078681946,
+      "learning_rate": 2.3730525445146146e-07,
+      "loss": 0.3077,
+      "step": 3950
+    },
+    {
+      "epoch": 1.8267589388696654,
+      "grad_norm": 1.2884184122085571,
+      "learning_rate": 2.25198968397371e-07,
+      "loss": 0.3411,
+      "step": 3960
+    },
+    {
+      "epoch": 1.831372549019608,
+      "grad_norm": 0.9986656308174133,
+      "learning_rate": 2.134025123396638e-07,
+      "loss": 0.2816,
+      "step": 3970
+    },
+    {
+      "epoch": 1.83598615916955,
+      "grad_norm": 0.7283441424369812,
+      "learning_rate": 2.019166517334703e-07,
+      "loss": 0.3093,
+      "step": 3980
+    },
+    {
+      "epoch": 1.8405997693194927,
+      "grad_norm": 1.1408605575561523,
+      "learning_rate": 1.9074213187982416e-07,
+      "loss": 0.2848,
+      "step": 3990
+    },
+    {
+      "epoch": 1.8452133794694348,
+      "grad_norm": 1.2907861471176147,
+      "learning_rate": 1.7987967787730541e-07,
+      "loss": 0.3013,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8452133794694348,
+      "eval_loss": 0.3492071032524109,
+      "eval_runtime": 413.2138,
+      "eval_samples_per_second": 8.158,
+      "eval_steps_per_second": 1.166,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8498269896193773,
+      "grad_norm": 0.9750341176986694,
+      "learning_rate": 1.6932999457498823e-07,
+      "loss": 0.2951,
+      "step": 4010
+    },
+    {
+      "epoch": 1.8544405997693194,
+      "grad_norm": 1.0746599435806274,
+      "learning_rate": 1.5909376652670283e-07,
+      "loss": 0.2518,
+      "step": 4020
+    },
+    {
+      "epoch": 1.859054209919262,
+      "grad_norm": 1.2660961151123047,
+      "learning_rate": 1.4917165794661849e-07,
+      "loss": 0.3032,
+      "step": 4030
+    },
+    {
+      "epoch": 1.863667820069204,
+      "grad_norm": 0.8381269574165344,
+      "learning_rate": 1.395643126661428e-07,
+      "loss": 0.2954,
+      "step": 4040
+    },
+    {
+      "epoch": 1.8682814302191466,
+      "grad_norm": 0.9705010056495667,
+      "learning_rate": 1.302723540921419e-07,
+      "loss": 0.2756,
+      "step": 4050
+    },
+    {
+      "epoch": 1.8728950403690887,
+      "grad_norm": 1.080946445465088,
+      "learning_rate": 1.212963851664928e-07,
+      "loss": 0.2792,
+      "step": 4060
+    },
+    {
+      "epoch": 1.8775086505190313,
+      "grad_norm": 1.0065879821777344,
+      "learning_rate": 1.1263698832695513e-07,
+      "loss": 0.3286,
+      "step": 4070
+    },
+    {
+      "epoch": 1.8821222606689734,
+      "grad_norm": 0.9605699181556702,
+      "learning_rate": 1.0429472546938158e-07,
+      "loss": 0.2919,
+      "step": 4080
+    },
+    {
+      "epoch": 1.886735870818916,
+      "grad_norm": 1.2412244081497192,
+      "learning_rate": 9.627013791125294e-08,
+      "loss": 0.3285,
+      "step": 4090
+    },
+    {
+      "epoch": 1.891349480968858,
+      "grad_norm": 1.0108641386032104,
+      "learning_rate": 8.856374635655696e-08,
+      "loss": 0.3172,
+      "step": 4100
+    },
+    {
+      "epoch": 1.8959630911188006,
+      "grad_norm": 1.0112003087997437,
+      "learning_rate": 8.117605086199686e-08,
+      "loss": 0.2838,
+      "step": 4110
+    },
+    {
+      "epoch": 1.9005767012687427,
+      "grad_norm": 0.8483492136001587,
+      "learning_rate": 7.410753080454746e-08,
+      "loss": 0.3001,
+      "step": 4120
+    },
+    {
+      "epoch": 1.9051903114186852,
+      "grad_norm": 0.8492743372917175,
+      "learning_rate": 6.735864485034493e-08,
+      "loss": 0.2853,
+      "step": 4130
+    },
+    {
+      "epoch": 1.9098039215686273,
+      "grad_norm": 1.6273894309997559,
+      "learning_rate": 6.092983092492844e-08,
+      "loss": 0.3221,
+      "step": 4140
+    },
+    {
+      "epoch": 1.9144175317185699,
+      "grad_norm": 1.2614809274673462,
+      "learning_rate": 5.482150618481952e-08,
+      "loss": 0.2815,
+      "step": 4150
+    },
+    {
+      "epoch": 1.919031141868512,
+      "grad_norm": 1.0911434888839722,
+      "learning_rate": 4.9034066990457094e-08,
+      "loss": 0.3051,
+      "step": 4160
+    },
+    {
+      "epoch": 1.9236447520184545,
+      "grad_norm": 1.4605953693389893,
+      "learning_rate": 4.356788888047747e-08,
+      "loss": 0.301,
+      "step": 4170
+    },
+    {
+      "epoch": 1.9282583621683966,
+      "grad_norm": 0.8996632099151611,
+      "learning_rate": 3.8423326547344376e-08,
+      "loss": 0.297,
+      "step": 4180
+    },
+    {
+      "epoch": 1.9328719723183392,
+      "grad_norm": 0.7587381601333618,
+      "learning_rate": 3.360071381433516e-08,
+      "loss": 0.309,
+      "step": 4190
+    },
+    {
+      "epoch": 1.9374855824682813,
+      "grad_norm": 0.9873301386833191,
+      "learning_rate": 2.9100363613879246e-08,
+      "loss": 0.2899,
+      "step": 4200
+    },
+    {
+      "epoch": 1.9420991926182238,
+      "grad_norm": 1.2133296728134155,
+      "learning_rate": 2.492256796725212e-08,
+      "loss": 0.2905,
+      "step": 4210
+    },
+    {
+      "epoch": 1.946712802768166,
+      "grad_norm": 1.017208456993103,
+      "learning_rate": 2.1067597965624963e-08,
+      "loss": 0.3042,
+      "step": 4220
+    },
+    {
+      "epoch": 1.9513264129181085,
+      "grad_norm": 1.4077831506729126,
+      "learning_rate": 1.753570375247815e-08,
+      "loss": 0.2793,
+      "step": 4230
+    },
+    {
+      "epoch": 1.9559400230680506,
+      "grad_norm": 1.1960562467575073,
+      "learning_rate": 1.4327114507365347e-08,
+      "loss": 0.3012,
+      "step": 4240
+    },
+    {
+      "epoch": 1.9605536332179931,
+      "grad_norm": 1.1810780763626099,
+      "learning_rate": 1.1442038431044856e-08,
+      "loss": 0.2987,
+      "step": 4250
+    },
+    {
+      "epoch": 1.9651672433679352,
+      "grad_norm": 1.0378133058547974,
+      "learning_rate": 8.880662731968748e-09,
+      "loss": 0.3028,
+      "step": 4260
+    },
+    {
+      "epoch": 1.9697808535178778,
+      "grad_norm": 0.9532252550125122,
+      "learning_rate": 6.6431536141348115e-09,
+      "loss": 0.327,
+      "step": 4270
+    },
+    {
+      "epoch": 1.9743944636678201,
+      "grad_norm": 0.8077103495597839,
+      "learning_rate": 4.729656266304061e-09,
+      "loss": 0.2861,
+      "step": 4280
+    },
+    {
+      "epoch": 1.9790080738177624,
+      "grad_norm": 1.0243134498596191,
+      "learning_rate": 3.1402948525766085e-09,
+      "loss": 0.3224,
+      "step": 4290
+    },
+    {
+      "epoch": 1.9836216839677048,
+      "grad_norm": 1.4665522575378418,
+      "learning_rate": 1.8751725043375526e-09,
+      "loss": 0.2968,
+      "step": 4300
+    },
+    {
+      "epoch": 1.988235294117647,
+      "grad_norm": 1.1807401180267334,
+      "learning_rate": 9.343713135623323e-10,
+      "loss": 0.3063,
+      "step": 4310
+    },
+    {
+      "epoch": 1.9928489042675894,
+      "grad_norm": 1.1453770399093628,
+      "learning_rate": 3.1795232749320947e-10,
+      "loss": 0.2943,
+      "step": 4320
+    },
+    {
+      "epoch": 1.9974625144175318,
+      "grad_norm": 1.3085640668869019,
+      "learning_rate": 2.5955544673550438e-11,
+      "loss": 0.2894,
+      "step": 4330
+    },
+    {
+      "epoch": 1.9993079584775086,
+      "step": 4334,
+      "total_flos": 545751381377024.0,
+      "train_loss": 0.3850643413100971,
+      "train_runtime": 89295.2192,
+      "train_samples_per_second": 0.68,
+      "train_steps_per_second": 0.049
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4334,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 545751381377024.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a35127ad4b0c9c29592d5922a4090bcd7436ded6fb9a3c22a375247290b1621
+size 7672