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 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-14B-Base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen3_14b_distill_32b_5e5
+  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. -->
+
+# qwen3_14b_distill_32b_5e5
+
+This model is a fine-tuned version of [Qwen/Qwen3-14B-Base](https://huggingface.co/Qwen/Qwen3-14B-Base) on the distill_qwen3_8b dataset.
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 512
+- optimizer: Use OptimizerNames.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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.5.1
+- Datasets 3.1.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4042009736118272.0,
+    "train_loss": 0.38500409647059525,
+    "train_runtime": 77088.3871,
+    "train_samples_per_second": 5.837,
+    "train_steps_per_second": 0.011
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b83b0377a8a095e2bcad6a3a76b1ca032c6f4ea0b482654ab8c78bb1ce5569
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b758627296b2f11fd853f2f43a05ec5e2a29633b8e954af5fd062e0f2ad6a3
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7176b02326baa83dd34950faff0ab55c4297d64497e345323c41c3267e8a4b2
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d648b2372e8163235d06896a321907b366ba83ef7baf710ee156afa0e44c4d7d
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c44f0d26ad5af34c717dd22e93935b211e7f1a0bca50b3be0336a1688ab97bb
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6615991bb788ea3119f48fbd467a5e9610424ba3811479a8a785472b67a3c94
+size 4733130504

model.safetensors.index.json

@@ -0,0 +1,450 @@
+{
+  "metadata": {
+    "total_size": 29536614400
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-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-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-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_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-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_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-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-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-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_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-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_norm.weight": "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_norm.weight": "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.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "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_norm.weight": "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.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_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4042009736118272.0,
+    "train_loss": 0.38500409647059525,
+    "train_runtime": 77088.3871,
+    "train_samples_per_second": 5.837,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,88 @@
+{"current_steps": 10, "total_steps": 879, "loss": 0.6914, "lr": 5.113636363636364e-06, "epoch": 0.034129692832764506, "percentage": 1.14, "elapsed_time": "0:15:23", "remaining_time": "22:18:06"}
+{"current_steps": 20, "total_steps": 879, "loss": 0.5785, "lr": 1.0795454545454547e-05, "epoch": 0.06825938566552901, "percentage": 2.28, "elapsed_time": "0:29:06", "remaining_time": "20:50:19"}
+{"current_steps": 30, "total_steps": 879, "loss": 0.5215, "lr": 1.6477272727272726e-05, "epoch": 0.10238907849829351, "percentage": 3.41, "elapsed_time": "0:42:37", "remaining_time": "20:06:25"}
+{"current_steps": 40, "total_steps": 879, "loss": 0.4933, "lr": 2.215909090909091e-05, "epoch": 0.13651877133105803, "percentage": 4.55, "elapsed_time": "0:57:28", "remaining_time": "20:05:33"}
+{"current_steps": 50, "total_steps": 879, "loss": 0.4751, "lr": 2.784090909090909e-05, "epoch": 0.17064846416382254, "percentage": 5.69, "elapsed_time": "1:11:44", "remaining_time": "19:49:33"}
+{"current_steps": 60, "total_steps": 879, "loss": 0.4648, "lr": 3.352272727272727e-05, "epoch": 0.20477815699658702, "percentage": 6.83, "elapsed_time": "1:27:51", "remaining_time": "19:59:19"}
+{"current_steps": 70, "total_steps": 879, "loss": 0.4589, "lr": 3.9204545454545456e-05, "epoch": 0.23890784982935154, "percentage": 7.96, "elapsed_time": "1:42:15", "remaining_time": "19:41:45"}
+{"current_steps": 80, "total_steps": 879, "loss": 0.4492, "lr": 4.488636363636364e-05, "epoch": 0.27303754266211605, "percentage": 9.1, "elapsed_time": "1:56:00", "remaining_time": "19:18:40"}
+{"current_steps": 90, "total_steps": 879, "loss": 0.4529, "lr": 4.99998028230155e-05, "epoch": 0.30716723549488056, "percentage": 10.24, "elapsed_time": "2:10:38", "remaining_time": "19:05:16"}
+{"current_steps": 100, "total_steps": 879, "loss": 0.4483, "lr": 4.997614534810769e-05, "epoch": 0.3412969283276451, "percentage": 11.38, "elapsed_time": "2:24:36", "remaining_time": "18:46:26"}
+{"current_steps": 110, "total_steps": 879, "loss": 0.4408, "lr": 4.991309523184661e-05, "epoch": 0.37542662116040953, "percentage": 12.51, "elapsed_time": "2:39:52", "remaining_time": "18:37:43"}
+{"current_steps": 120, "total_steps": 879, "loss": 0.4361, "lr": 4.9810751917544375e-05, "epoch": 0.40955631399317405, "percentage": 13.65, "elapsed_time": "2:54:02", "remaining_time": "18:20:50"}
+{"current_steps": 130, "total_steps": 879, "loss": 0.4375, "lr": 4.96692768221618e-05, "epoch": 0.44368600682593856, "percentage": 14.79, "elapsed_time": "3:08:22", "remaining_time": "18:05:17"}
+{"current_steps": 140, "total_steps": 879, "loss": 0.4343, "lr": 4.948889308171989e-05, "epoch": 0.4778156996587031, "percentage": 15.93, "elapsed_time": "3:23:31", "remaining_time": "17:54:16"}
+{"current_steps": 150, "total_steps": 879, "loss": 0.4322, "lr": 4.926988519936732e-05, "epoch": 0.5119453924914675, "percentage": 17.06, "elapsed_time": "3:37:48", "remaining_time": "17:38:34"}
+{"current_steps": 160, "total_steps": 879, "loss": 0.4287, "lr": 4.9012598596659034e-05, "epoch": 0.5460750853242321, "percentage": 18.2, "elapsed_time": "3:53:36", "remaining_time": "17:29:48"}
+{"current_steps": 170, "total_steps": 879, "loss": 0.4282, "lr": 4.8717439068753755e-05, "epoch": 0.5802047781569966, "percentage": 19.34, "elapsed_time": "4:07:52", "remaining_time": "17:13:45"}
+{"current_steps": 180, "total_steps": 879, "loss": 0.4227, "lr": 4.838487214438951e-05, "epoch": 0.6143344709897611, "percentage": 20.48, "elapsed_time": "4:22:53", "remaining_time": "17:00:55"}
+{"current_steps": 190, "total_steps": 879, "loss": 0.4286, "lr": 4.801542235164678e-05, "epoch": 0.6484641638225256, "percentage": 21.62, "elapsed_time": "4:37:21", "remaining_time": "16:45:47"}
+{"current_steps": 200, "total_steps": 879, "loss": 0.4287, "lr": 4.7609672390657276e-05, "epoch": 0.6825938566552902, "percentage": 22.75, "elapsed_time": "4:51:32", "remaining_time": "16:29:45"}
+{"current_steps": 210, "total_steps": 879, "loss": 0.4215, "lr": 4.716826221456305e-05, "epoch": 0.7167235494880546, "percentage": 23.89, "elapsed_time": "5:07:35", "remaining_time": "16:19:52"}
+{"current_steps": 220, "total_steps": 879, "loss": 0.4197, "lr": 4.669188802017569e-05, "epoch": 0.7508532423208191, "percentage": 25.03, "elapsed_time": "5:22:42", "remaining_time": "16:06:40"}
+{"current_steps": 230, "total_steps": 879, "loss": 0.425, "lr": 4.6181301149927245e-05, "epoch": 0.7849829351535836, "percentage": 26.17, "elapsed_time": "5:36:44", "remaining_time": "15:50:10"}
+{"current_steps": 240, "total_steps": 879, "loss": 0.4232, "lr": 4.563730690684502e-05, "epoch": 0.8191126279863481, "percentage": 27.3, "elapsed_time": "5:50:47", "remaining_time": "15:33:58"}
+{"current_steps": 250, "total_steps": 879, "loss": 0.4252, "lr": 4.5060763284419114e-05, "epoch": 0.8532423208191127, "percentage": 28.44, "elapsed_time": "6:05:16", "remaining_time": "15:19:01"}
+{"current_steps": 260, "total_steps": 879, "loss": 0.4173, "lr": 4.445257961336594e-05, "epoch": 0.8873720136518771, "percentage": 29.58, "elapsed_time": "6:21:19", "remaining_time": "15:07:50"}
+{"current_steps": 270, "total_steps": 879, "loss": 0.4205, "lr": 4.3813715127422186e-05, "epoch": 0.9215017064846417, "percentage": 30.72, "elapsed_time": "6:35:54", "remaining_time": "14:52:59"}
+{"current_steps": 280, "total_steps": 879, "loss": 0.4185, "lr": 4.3145177450431235e-05, "epoch": 0.9556313993174061, "percentage": 31.85, "elapsed_time": "6:50:17", "remaining_time": "14:37:44"}
+{"current_steps": 290, "total_steps": 879, "loss": 0.417, "lr": 4.244802100710809e-05, "epoch": 0.9897610921501706, "percentage": 32.99, "elapsed_time": "7:04:07", "remaining_time": "14:21:23"}
+{"current_steps": 300, "total_steps": 879, "loss": 0.3911, "lr": 4.172334535998958e-05, "epoch": 1.023890784982935, "percentage": 34.13, "elapsed_time": "7:18:27", "remaining_time": "14:06:13"}
+{"current_steps": 310, "total_steps": 879, "loss": 0.3733, "lr": 4.0972293475192634e-05, "epoch": 1.0580204778156996, "percentage": 35.27, "elapsed_time": "7:34:13", "remaining_time": "13:53:43"}
+{"current_steps": 320, "total_steps": 879, "loss": 0.3778, "lr": 4.0196049919716004e-05, "epoch": 1.0921501706484642, "percentage": 36.41, "elapsed_time": "7:47:31", "remaining_time": "13:36:41"}
+{"current_steps": 330, "total_steps": 879, "loss": 0.3778, "lr": 3.9395838993128645e-05, "epoch": 1.1262798634812285, "percentage": 37.54, "elapsed_time": "8:01:04", "remaining_time": "13:20:19"}
+{"current_steps": 340, "total_steps": 879, "loss": 0.3751, "lr": 3.8572922796591415e-05, "epoch": 1.1604095563139931, "percentage": 38.68, "elapsed_time": "8:14:48", "remaining_time": "13:04:25"}
+{"current_steps": 350, "total_steps": 879, "loss": 0.3755, "lr": 3.7728599242257786e-05, "epoch": 1.1945392491467577, "percentage": 39.82, "elapsed_time": "8:28:49", "remaining_time": "12:49:03"}
+{"current_steps": 360, "total_steps": 879, "loss": 0.38, "lr": 3.686420000619301e-05, "epoch": 1.2286689419795223, "percentage": 40.96, "elapsed_time": "8:44:34", "remaining_time": "12:36:15"}
+{"current_steps": 370, "total_steps": 879, "loss": 0.3802, "lr": 3.5981088428040464e-05, "epoch": 1.2627986348122868, "percentage": 42.09, "elapsed_time": "8:58:54", "remaining_time": "12:21:22"}
+{"current_steps": 380, "total_steps": 879, "loss": 0.3739, "lr": 3.5080657360747985e-05, "epoch": 1.2969283276450512, "percentage": 43.23, "elapsed_time": "9:13:27", "remaining_time": "12:06:46"}
+{"current_steps": 390, "total_steps": 879, "loss": 0.3791, "lr": 3.416432697374533e-05, "epoch": 1.3310580204778157, "percentage": 44.37, "elapsed_time": "9:27:28", "remaining_time": "11:51:30"}
+{"current_steps": 400, "total_steps": 879, "loss": 0.3778, "lr": 3.323354251303797e-05, "epoch": 1.36518771331058, "percentage": 45.51, "elapsed_time": "9:41:38", "remaining_time": "11:36:30"}
+{"current_steps": 410, "total_steps": 879, "loss": 0.3773, "lr": 3.228977202174973e-05, "epoch": 1.3993174061433447, "percentage": 46.64, "elapsed_time": "9:57:43", "remaining_time": "11:23:43"}
+{"current_steps": 420, "total_steps": 879, "loss": 0.3774, "lr": 3.1334504024709605e-05, "epoch": 1.4334470989761092, "percentage": 47.78, "elapsed_time": "10:11:41", "remaining_time": "11:08:29"}
+{"current_steps": 430, "total_steps": 879, "loss": 0.3754, "lr": 3.0369245180734605e-05, "epoch": 1.4675767918088738, "percentage": 48.92, "elapsed_time": "10:25:50", "remaining_time": "10:53:29"}
+{"current_steps": 440, "total_steps": 879, "loss": 0.3769, "lr": 2.9395517906311494e-05, "epoch": 1.5017064846416384, "percentage": 50.06, "elapsed_time": "10:40:53", "remaining_time": "10:39:26"}
+{"current_steps": 450, "total_steps": 879, "loss": 0.3736, "lr": 2.841485797442535e-05, "epoch": 1.5358361774744027, "percentage": 51.19, "elapsed_time": "10:55:14", "remaining_time": "10:24:40"}
+{"current_steps": 460, "total_steps": 879, "loss": 0.3749, "lr": 2.742881209232215e-05, "epoch": 1.5699658703071673, "percentage": 52.33, "elapsed_time": "11:10:20", "remaining_time": "10:10:35"}
+{"current_steps": 470, "total_steps": 879, "loss": 0.3725, "lr": 2.6438935462025672e-05, "epoch": 1.6040955631399316, "percentage": 53.47, "elapsed_time": "11:25:01", "remaining_time": "9:56:07"}
+{"current_steps": 480, "total_steps": 879, "loss": 0.3736, "lr": 2.5446789327456373e-05, "epoch": 1.6382252559726962, "percentage": 54.61, "elapsed_time": "11:39:36", "remaining_time": "9:41:33"}
+{"current_steps": 490, "total_steps": 879, "loss": 0.3757, "lr": 2.4453938512020927e-05, "epoch": 1.6723549488054608, "percentage": 55.75, "elapsed_time": "11:54:15", "remaining_time": "9:27:02"}
+{"current_steps": 500, "total_steps": 879, "loss": 0.3718, "lr": 2.3461948950556133e-05, "epoch": 1.7064846416382253, "percentage": 56.88, "elapsed_time": "12:07:46", "remaining_time": "9:11:38"}
+{"current_steps": 510, "total_steps": 879, "loss": 0.3766, "lr": 2.247238521951992e-05, "epoch": 1.74061433447099, "percentage": 58.02, "elapsed_time": "12:23:07", "remaining_time": "8:57:40"}
+{"current_steps": 520, "total_steps": 879, "loss": 0.375, "lr": 2.1486808069324687e-05, "epoch": 1.7747440273037542, "percentage": 59.16, "elapsed_time": "12:37:33", "remaining_time": "8:43:00"}
+{"current_steps": 530, "total_steps": 879, "loss": 0.3733, "lr": 2.0506771962705304e-05, "epoch": 1.8088737201365188, "percentage": 60.3, "elapsed_time": "12:51:39", "remaining_time": "8:28:07"}
+{"current_steps": 540, "total_steps": 879, "loss": 0.3716, "lr": 1.953382262300389e-05, "epoch": 1.8430034129692832, "percentage": 61.43, "elapsed_time": "13:06:09", "remaining_time": "8:13:32"}
+{"current_steps": 550, "total_steps": 879, "loss": 0.3722, "lr": 1.8569494596238658e-05, "epoch": 1.8771331058020477, "percentage": 62.57, "elapsed_time": "13:20:42", "remaining_time": "7:58:58"}
+{"current_steps": 560, "total_steps": 879, "loss": 0.372, "lr": 1.7615308830801576e-05, "epoch": 1.9112627986348123, "percentage": 63.71, "elapsed_time": "13:37:11", "remaining_time": "7:45:30"}
+{"current_steps": 570, "total_steps": 879, "loss": 0.3728, "lr": 1.6672770278602508e-05, "epoch": 1.9453924914675769, "percentage": 64.85, "elapsed_time": "13:51:30", "remaining_time": "7:30:45"}
+{"current_steps": 580, "total_steps": 879, "loss": 0.3729, "lr": 1.5743365521443033e-05, "epoch": 1.9795221843003414, "percentage": 65.98, "elapsed_time": "14:06:24", "remaining_time": "7:16:20"}
+{"current_steps": 590, "total_steps": 879, "loss": 0.3545, "lr": 1.4828560426363918e-05, "epoch": 2.013651877133106, "percentage": 67.12, "elapsed_time": "14:21:21", "remaining_time": "7:01:55"}
+{"current_steps": 600, "total_steps": 879, "loss": 0.3297, "lr": 1.3929797833664013e-05, "epoch": 2.04778156996587, "percentage": 68.26, "elapsed_time": "14:35:11", "remaining_time": "6:46:58"}
+{"current_steps": 610, "total_steps": 879, "loss": 0.3297, "lr": 1.30484952812373e-05, "epoch": 2.0819112627986347, "percentage": 69.4, "elapsed_time": "14:51:25", "remaining_time": "6:33:06"}
+{"current_steps": 620, "total_steps": 879, "loss": 0.3304, "lr": 1.2186042768816988e-05, "epoch": 2.1160409556313993, "percentage": 70.53, "elapsed_time": "15:06:01", "remaining_time": "6:18:29"}
+{"current_steps": 630, "total_steps": 879, "loss": 0.3265, "lr": 1.1343800565653332e-05, "epoch": 2.150170648464164, "percentage": 71.67, "elapsed_time": "15:20:41", "remaining_time": "6:03:53"}
+{"current_steps": 640, "total_steps": 879, "loss": 0.329, "lr": 1.0523097065082413e-05, "epoch": 2.1843003412969284, "percentage": 72.81, "elapsed_time": "15:35:13", "remaining_time": "5:49:14"}
+{"current_steps": 650, "total_steps": 879, "loss": 0.3276, "lr": 9.725226689370154e-06, "epoch": 2.218430034129693, "percentage": 73.95, "elapsed_time": "15:50:08", "remaining_time": "5:34:44"}
+{"current_steps": 660, "total_steps": 879, "loss": 0.3287, "lr": 8.951447848135758e-06, "epoch": 2.252559726962457, "percentage": 75.09, "elapsed_time": "16:05:25", "remaining_time": "5:20:20"}
+{"current_steps": 670, "total_steps": 879, "loss": 0.3298, "lr": 8.202980953574735e-06, "epoch": 2.2866894197952217, "percentage": 76.22, "elapsed_time": "16:19:57", "remaining_time": "5:05:41"}
+{"current_steps": 680, "total_steps": 879, "loss": 0.3283, "lr": 7.481006495611817e-06, "epoch": 2.3208191126279862, "percentage": 77.36, "elapsed_time": "16:34:48", "remaining_time": "4:51:07"}
+{"current_steps": 690, "total_steps": 879, "loss": 0.3274, "lr": 6.786663180019751e-06, "epoch": 2.354948805460751, "percentage": 78.5, "elapsed_time": "16:48:35", "remaining_time": "4:36:16"}
+{"current_steps": 700, "total_steps": 879, "loss": 0.3255, "lr": 6.121046132440458e-06, "epoch": 2.3890784982935154, "percentage": 79.64, "elapsed_time": "17:03:46", "remaining_time": "4:21:47"}
+{"current_steps": 710, "total_steps": 879, "loss": 0.3262, "lr": 5.485205171141272e-06, "epoch": 2.42320819112628, "percentage": 80.77, "elapsed_time": "17:19:24", "remaining_time": "4:07:24"}
+{"current_steps": 720, "total_steps": 879, "loss": 0.325, "lr": 4.880143151230418e-06, "epoch": 2.4573378839590445, "percentage": 81.91, "elapsed_time": "17:33:46", "remaining_time": "3:52:42"}
+{"current_steps": 730, "total_steps": 879, "loss": 0.3255, "lr": 4.306814382943306e-06, "epoch": 2.491467576791809, "percentage": 83.05, "elapsed_time": "17:48:11", "remaining_time": "3:38:01"}
+{"current_steps": 740, "total_steps": 879, "loss": 0.3283, "lr": 3.7661231264943086e-06, "epoch": 2.5255972696245736, "percentage": 84.19, "elapsed_time": "18:02:58", "remaining_time": "3:23:25"}
+{"current_steps": 750, "total_steps": 879, "loss": 0.3238, "lr": 3.2589221658679586e-06, "epoch": 2.5597269624573378, "percentage": 85.32, "elapsed_time": "18:17:09", "remaining_time": "3:08:42"}
+{"current_steps": 760, "total_steps": 879, "loss": 0.3268, "lr": 2.7860114637989933e-06, "epoch": 2.5938566552901023, "percentage": 86.46, "elapsed_time": "18:32:25", "remaining_time": "2:54:11"}
+{"current_steps": 770, "total_steps": 879, "loss": 0.3322, "lr": 2.3481369000626585e-06, "epoch": 2.627986348122867, "percentage": 87.6, "elapsed_time": "18:46:54", "remaining_time": "2:39:31"}
+{"current_steps": 780, "total_steps": 879, "loss": 0.3229, "lr": 1.9459890950652093e-06, "epoch": 2.6621160409556315, "percentage": 88.74, "elapsed_time": "19:00:32", "remaining_time": "2:24:45"}
+{"current_steps": 790, "total_steps": 879, "loss": 0.3243, "lr": 1.5802023205900797e-06, "epoch": 2.696245733788396, "percentage": 89.87, "elapsed_time": "19:15:20", "remaining_time": "2:10:09"}
+{"current_steps": 800, "total_steps": 879, "loss": 0.3282, "lr": 1.251353499417704e-06, "epoch": 2.73037542662116, "percentage": 91.01, "elapsed_time": "19:30:38", "remaining_time": "1:55:36"}
+{"current_steps": 810, "total_steps": 879, "loss": 0.3237, "lr": 9.599612953967746e-07, "epoch": 2.7645051194539247, "percentage": 92.15, "elapsed_time": "19:45:29", "remaining_time": "1:40:59"}
+{"current_steps": 820, "total_steps": 879, "loss": 0.3309, "lr": 7.064852954021373e-07, "epoch": 2.7986348122866893, "percentage": 93.29, "elapsed_time": "19:59:18", "remaining_time": "1:26:17"}
+{"current_steps": 830, "total_steps": 879, "loss": 0.3249, "lr": 4.913252844694821e-07, "epoch": 2.832764505119454, "percentage": 94.43, "elapsed_time": "20:13:29", "remaining_time": "1:11:38"}
+{"current_steps": 840, "total_steps": 879, "loss": 0.3248, "lr": 3.1482061525015537e-07, "epoch": 2.8668941979522184, "percentage": 95.56, "elapsed_time": "20:27:01", "remaining_time": "0:56:58"}
+{"current_steps": 850, "total_steps": 879, "loss": 0.3216, "lr": 1.772496727805495e-07, "epoch": 2.901023890784983, "percentage": 96.7, "elapsed_time": "20:41:06", "remaining_time": "0:42:20"}
+{"current_steps": 860, "total_steps": 879, "loss": 0.3255, "lr": 7.882943541027976e-08, "epoch": 2.9351535836177476, "percentage": 97.84, "elapsed_time": "20:57:00", "remaining_time": "0:27:46"}
+{"current_steps": 870, "total_steps": 879, "loss": 0.3277, "lr": 1.9715132581624164e-08, "epoch": 2.969283276450512, "percentage": 98.98, "elapsed_time": "21:11:10", "remaining_time": "0:13:09"}
+{"current_steps": 879, "total_steps": 879, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "21:24:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,652 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 879,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034129692832764506,
+      "grad_norm": 1.3683982802260004,
+      "learning_rate": 5.113636363636364e-06,
+      "loss": 0.6914,
+      "step": 10
+    },
+    {
+      "epoch": 0.06825938566552901,
+      "grad_norm": 1.1329734773219333,
+      "learning_rate": 1.0795454545454547e-05,
+      "loss": 0.5785,
+      "step": 20
+    },
+    {
+      "epoch": 0.10238907849829351,
+      "grad_norm": 0.4818340266515117,
+      "learning_rate": 1.6477272727272726e-05,
+      "loss": 0.5215,
+      "step": 30
+    },
+    {
+      "epoch": 0.13651877133105803,
+      "grad_norm": 0.40192420678859747,
+      "learning_rate": 2.215909090909091e-05,
+      "loss": 0.4933,
+      "step": 40
+    },
+    {
+      "epoch": 0.17064846416382254,
+      "grad_norm": 0.30113184989165265,
+      "learning_rate": 2.784090909090909e-05,
+      "loss": 0.4751,
+      "step": 50
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.6030940025399546,
+      "learning_rate": 3.352272727272727e-05,
+      "loss": 0.4648,
+      "step": 60
+    },
+    {
+      "epoch": 0.23890784982935154,
+      "grad_norm": 0.40486139505957924,
+      "learning_rate": 3.9204545454545456e-05,
+      "loss": 0.4589,
+      "step": 70
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.4001169424739457,
+      "learning_rate": 4.488636363636364e-05,
+      "loss": 0.4492,
+      "step": 80
+    },
+    {
+      "epoch": 0.30716723549488056,
+      "grad_norm": 0.7056769426783731,
+      "learning_rate": 4.99998028230155e-05,
+      "loss": 0.4529,
+      "step": 90
+    },
+    {
+      "epoch": 0.3412969283276451,
+      "grad_norm": 0.4127457799735406,
+      "learning_rate": 4.997614534810769e-05,
+      "loss": 0.4483,
+      "step": 100
+    },
+    {
+      "epoch": 0.37542662116040953,
+      "grad_norm": 0.4253433644026189,
+      "learning_rate": 4.991309523184661e-05,
+      "loss": 0.4408,
+      "step": 110
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.2650767061773436,
+      "learning_rate": 4.9810751917544375e-05,
+      "loss": 0.4361,
+      "step": 120
+    },
+    {
+      "epoch": 0.44368600682593856,
+      "grad_norm": 0.3236300985877029,
+      "learning_rate": 4.96692768221618e-05,
+      "loss": 0.4375,
+      "step": 130
+    },
+    {
+      "epoch": 0.4778156996587031,
+      "grad_norm": 0.2677148257178138,
+      "learning_rate": 4.948889308171989e-05,
+      "loss": 0.4343,
+      "step": 140
+    },
+    {
+      "epoch": 0.5119453924914675,
+      "grad_norm": 0.31194545617250247,
+      "learning_rate": 4.926988519936732e-05,
+      "loss": 0.4322,
+      "step": 150
+    },
+    {
+      "epoch": 0.5460750853242321,
+      "grad_norm": 0.2742536503128216,
+      "learning_rate": 4.9012598596659034e-05,
+      "loss": 0.4287,
+      "step": 160
+    },
+    {
+      "epoch": 0.5802047781569966,
+      "grad_norm": 0.2332933827806788,
+      "learning_rate": 4.8717439068753755e-05,
+      "loss": 0.4282,
+      "step": 170
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.3218993549663778,
+      "learning_rate": 4.838487214438951e-05,
+      "loss": 0.4227,
+      "step": 180
+    },
+    {
+      "epoch": 0.6484641638225256,
+      "grad_norm": 0.25861357657721123,
+      "learning_rate": 4.801542235164678e-05,
+      "loss": 0.4286,
+      "step": 190
+    },
+    {
+      "epoch": 0.6825938566552902,
+      "grad_norm": 0.2918271012332895,
+      "learning_rate": 4.7609672390657276e-05,
+      "loss": 0.4287,
+      "step": 200
+    },
+    {
+      "epoch": 0.7167235494880546,
+      "grad_norm": 0.24406366100330784,
+      "learning_rate": 4.716826221456305e-05,
+      "loss": 0.4215,
+      "step": 210
+    },
+    {
+      "epoch": 0.7508532423208191,
+      "grad_norm": 0.22515461276733315,
+      "learning_rate": 4.669188802017569e-05,
+      "loss": 0.4197,
+      "step": 220
+    },
+    {
+      "epoch": 0.7849829351535836,
+      "grad_norm": 0.2186800997634458,
+      "learning_rate": 4.6181301149927245e-05,
+      "loss": 0.425,
+      "step": 230
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.23708113058085334,
+      "learning_rate": 4.563730690684502e-05,
+      "loss": 0.4232,
+      "step": 240
+    },
+    {
+      "epoch": 0.8532423208191127,
+      "grad_norm": 0.2585858683862343,
+      "learning_rate": 4.5060763284419114e-05,
+      "loss": 0.4252,
+      "step": 250
+    },
+    {
+      "epoch": 0.8873720136518771,
+      "grad_norm": 0.2695864266113866,
+      "learning_rate": 4.445257961336594e-05,
+      "loss": 0.4173,
+      "step": 260
+    },
+    {
+      "epoch": 0.9215017064846417,
+      "grad_norm": 0.23595963689596886,
+      "learning_rate": 4.3813715127422186e-05,
+      "loss": 0.4205,
+      "step": 270
+    },
+    {
+      "epoch": 0.9556313993174061,
+      "grad_norm": 0.24101367889924785,
+      "learning_rate": 4.3145177450431235e-05,
+      "loss": 0.4185,
+      "step": 280
+    },
+    {
+      "epoch": 0.9897610921501706,
+      "grad_norm": 0.1941853912616131,
+      "learning_rate": 4.244802100710809e-05,
+      "loss": 0.417,
+      "step": 290
+    },
+    {
+      "epoch": 1.023890784982935,
+      "grad_norm": 0.24088200863220327,
+      "learning_rate": 4.172334535998958e-05,
+      "loss": 0.3911,
+      "step": 300
+    },
+    {
+      "epoch": 1.0580204778156996,
+      "grad_norm": 0.2401594568811406,
+      "learning_rate": 4.0972293475192634e-05,
+      "loss": 0.3733,
+      "step": 310
+    },
+    {
+      "epoch": 1.0921501706484642,
+      "grad_norm": 0.22375295442616824,
+      "learning_rate": 4.0196049919716004e-05,
+      "loss": 0.3778,
+      "step": 320
+    },
+    {
+      "epoch": 1.1262798634812285,
+      "grad_norm": 0.21296450960759827,
+      "learning_rate": 3.9395838993128645e-05,
+      "loss": 0.3778,
+      "step": 330
+    },
+    {
+      "epoch": 1.1604095563139931,
+      "grad_norm": 0.2364577800890562,
+      "learning_rate": 3.8572922796591415e-05,
+      "loss": 0.3751,
+      "step": 340
+    },
+    {
+      "epoch": 1.1945392491467577,
+      "grad_norm": 0.20516445679828432,
+      "learning_rate": 3.7728599242257786e-05,
+      "loss": 0.3755,
+      "step": 350
+    },
+    {
+      "epoch": 1.2286689419795223,
+      "grad_norm": 0.2080061173225757,
+      "learning_rate": 3.686420000619301e-05,
+      "loss": 0.38,
+      "step": 360
+    },
+    {
+      "epoch": 1.2627986348122868,
+      "grad_norm": 0.20693994205238442,
+      "learning_rate": 3.5981088428040464e-05,
+      "loss": 0.3802,
+      "step": 370
+    },
+    {
+      "epoch": 1.2969283276450512,
+      "grad_norm": 0.16640578029703731,
+      "learning_rate": 3.5080657360747985e-05,
+      "loss": 0.3739,
+      "step": 380
+    },
+    {
+      "epoch": 1.3310580204778157,
+      "grad_norm": 0.1996673960644544,
+      "learning_rate": 3.416432697374533e-05,
+      "loss": 0.3791,
+      "step": 390
+    },
+    {
+      "epoch": 1.36518771331058,
+      "grad_norm": 0.23313473957202652,
+      "learning_rate": 3.323354251303797e-05,
+      "loss": 0.3778,
+      "step": 400
+    },
+    {
+      "epoch": 1.3993174061433447,
+      "grad_norm": 0.18739705777804985,
+      "learning_rate": 3.228977202174973e-05,
+      "loss": 0.3773,
+      "step": 410
+    },
+    {
+      "epoch": 1.4334470989761092,
+      "grad_norm": 0.19881497754130406,
+      "learning_rate": 3.1334504024709605e-05,
+      "loss": 0.3774,
+      "step": 420
+    },
+    {
+      "epoch": 1.4675767918088738,
+      "grad_norm": 0.18919226309345596,
+      "learning_rate": 3.0369245180734605e-05,
+      "loss": 0.3754,
+      "step": 430
+    },
+    {
+      "epoch": 1.5017064846416384,
+      "grad_norm": 0.16804781179686107,
+      "learning_rate": 2.9395517906311494e-05,
+      "loss": 0.3769,
+      "step": 440
+    },
+    {
+      "epoch": 1.5358361774744027,
+      "grad_norm": 0.19724123435397653,
+      "learning_rate": 2.841485797442535e-05,
+      "loss": 0.3736,
+      "step": 450
+    },
+    {
+      "epoch": 1.5699658703071673,
+      "grad_norm": 0.1492512432657133,
+      "learning_rate": 2.742881209232215e-05,
+      "loss": 0.3749,
+      "step": 460
+    },
+    {
+      "epoch": 1.6040955631399316,
+      "grad_norm": 0.15514563941327603,
+      "learning_rate": 2.6438935462025672e-05,
+      "loss": 0.3725,
+      "step": 470
+    },
+    {
+      "epoch": 1.6382252559726962,
+      "grad_norm": 0.15833970336928466,
+      "learning_rate": 2.5446789327456373e-05,
+      "loss": 0.3736,
+      "step": 480
+    },
+    {
+      "epoch": 1.6723549488054608,
+      "grad_norm": 0.1508024128691703,
+      "learning_rate": 2.4453938512020927e-05,
+      "loss": 0.3757,
+      "step": 490
+    },
+    {
+      "epoch": 1.7064846416382253,
+      "grad_norm": 0.1561566494075755,
+      "learning_rate": 2.3461948950556133e-05,
+      "loss": 0.3718,
+      "step": 500
+    },
+    {
+      "epoch": 1.74061433447099,
+      "grad_norm": 0.16769278782996944,
+      "learning_rate": 2.247238521951992e-05,
+      "loss": 0.3766,
+      "step": 510
+    },
+    {
+      "epoch": 1.7747440273037542,
+      "grad_norm": 0.14100411189778878,
+      "learning_rate": 2.1486808069324687e-05,
+      "loss": 0.375,
+      "step": 520
+    },
+    {
+      "epoch": 1.8088737201365188,
+      "grad_norm": 0.16483764215517682,
+      "learning_rate": 2.0506771962705304e-05,
+      "loss": 0.3733,
+      "step": 530
+    },
+    {
+      "epoch": 1.8430034129692832,
+      "grad_norm": 0.155764171343142,
+      "learning_rate": 1.953382262300389e-05,
+      "loss": 0.3716,
+      "step": 540
+    },
+    {
+      "epoch": 1.8771331058020477,
+      "grad_norm": 0.15072440831975784,
+      "learning_rate": 1.8569494596238658e-05,
+      "loss": 0.3722,
+      "step": 550
+    },
+    {
+      "epoch": 1.9112627986348123,
+      "grad_norm": 0.1452936635170902,
+      "learning_rate": 1.7615308830801576e-05,
+      "loss": 0.372,
+      "step": 560
+    },
+    {
+      "epoch": 1.9453924914675769,
+      "grad_norm": 0.1459972272942582,
+      "learning_rate": 1.6672770278602508e-05,
+      "loss": 0.3728,
+      "step": 570
+    },
+    {
+      "epoch": 1.9795221843003414,
+      "grad_norm": 0.15824724688437872,
+      "learning_rate": 1.5743365521443033e-05,
+      "loss": 0.3729,
+      "step": 580
+    },
+    {
+      "epoch": 2.013651877133106,
+      "grad_norm": 0.17864631402612208,
+      "learning_rate": 1.4828560426363918e-05,
+      "loss": 0.3545,
+      "step": 590
+    },
+    {
+      "epoch": 2.04778156996587,
+      "grad_norm": 0.1588637310837059,
+      "learning_rate": 1.3929797833664013e-05,
+      "loss": 0.3297,
+      "step": 600
+    },
+    {
+      "epoch": 2.0819112627986347,
+      "grad_norm": 0.1418501854463478,
+      "learning_rate": 1.30484952812373e-05,
+      "loss": 0.3297,
+      "step": 610
+    },
+    {
+      "epoch": 2.1160409556313993,
+      "grad_norm": 0.15348962450232634,
+      "learning_rate": 1.2186042768816988e-05,
+      "loss": 0.3304,
+      "step": 620
+    },
+    {
+      "epoch": 2.150170648464164,
+      "grad_norm": 0.1348514462379786,
+      "learning_rate": 1.1343800565653332e-05,
+      "loss": 0.3265,
+      "step": 630
+    },
+    {
+      "epoch": 2.1843003412969284,
+      "grad_norm": 0.1356947041461966,
+      "learning_rate": 1.0523097065082413e-05,
+      "loss": 0.329,
+      "step": 640
+    },
+    {
+      "epoch": 2.218430034129693,
+      "grad_norm": 0.1494755476959583,
+      "learning_rate": 9.725226689370154e-06,
+      "loss": 0.3276,
+      "step": 650
+    },
+    {
+      "epoch": 2.252559726962457,
+      "grad_norm": 0.13335640045718117,
+      "learning_rate": 8.951447848135758e-06,
+      "loss": 0.3287,
+      "step": 660
+    },
+    {
+      "epoch": 2.2866894197952217,
+      "grad_norm": 0.13979403886356553,
+      "learning_rate": 8.202980953574735e-06,
+      "loss": 0.3298,
+      "step": 670
+    },
+    {
+      "epoch": 2.3208191126279862,
+      "grad_norm": 0.11971919873813754,
+      "learning_rate": 7.481006495611817e-06,
+      "loss": 0.3283,
+      "step": 680
+    },
+    {
+      "epoch": 2.354948805460751,
+      "grad_norm": 0.13500834901363976,
+      "learning_rate": 6.786663180019751e-06,
+      "loss": 0.3274,
+      "step": 690
+    },
+    {
+      "epoch": 2.3890784982935154,
+      "grad_norm": 0.17890565254397334,
+      "learning_rate": 6.121046132440458e-06,
+      "loss": 0.3255,
+      "step": 700
+    },
+    {
+      "epoch": 2.42320819112628,
+      "grad_norm": 0.1302286181845878,
+      "learning_rate": 5.485205171141272e-06,
+      "loss": 0.3262,
+      "step": 710
+    },
+    {
+      "epoch": 2.4573378839590445,
+      "grad_norm": 0.12203910298248397,
+      "learning_rate": 4.880143151230418e-06,
+      "loss": 0.325,
+      "step": 720
+    },
+    {
+      "epoch": 2.491467576791809,
+      "grad_norm": 0.12474109586190246,
+      "learning_rate": 4.306814382943306e-06,
+      "loss": 0.3255,
+      "step": 730
+    },
+    {
+      "epoch": 2.5255972696245736,
+      "grad_norm": 0.12095736373178395,
+      "learning_rate": 3.7661231264943086e-06,
+      "loss": 0.3283,
+      "step": 740
+    },
+    {
+      "epoch": 2.5597269624573378,
+      "grad_norm": 0.11718436619787706,
+      "learning_rate": 3.2589221658679586e-06,
+      "loss": 0.3238,
+      "step": 750
+    },
+    {
+      "epoch": 2.5938566552901023,
+      "grad_norm": 0.11404515711854785,
+      "learning_rate": 2.7860114637989933e-06,
+      "loss": 0.3268,
+      "step": 760
+    },
+    {
+      "epoch": 2.627986348122867,
+      "grad_norm": 0.1211242651755094,
+      "learning_rate": 2.3481369000626585e-06,
+      "loss": 0.3322,
+      "step": 770
+    },
+    {
+      "epoch": 2.6621160409556315,
+      "grad_norm": 0.11417951185976549,
+      "learning_rate": 1.9459890950652093e-06,
+      "loss": 0.3229,
+      "step": 780
+    },
+    {
+      "epoch": 2.696245733788396,
+      "grad_norm": 0.11391563747812329,
+      "learning_rate": 1.5802023205900797e-06,
+      "loss": 0.3243,
+      "step": 790
+    },
+    {
+      "epoch": 2.73037542662116,
+      "grad_norm": 0.11074398617174237,
+      "learning_rate": 1.251353499417704e-06,
+      "loss": 0.3282,
+      "step": 800
+    },
+    {
+      "epoch": 2.7645051194539247,
+      "grad_norm": 0.11126589393346809,
+      "learning_rate": 9.599612953967746e-07,
+      "loss": 0.3237,
+      "step": 810
+    },
+    {
+      "epoch": 2.7986348122866893,
+      "grad_norm": 0.10702690737924332,
+      "learning_rate": 7.064852954021373e-07,
+      "loss": 0.3309,
+      "step": 820
+    },
+    {
+      "epoch": 2.832764505119454,
+      "grad_norm": 0.11277244407549764,
+      "learning_rate": 4.913252844694821e-07,
+      "loss": 0.3249,
+      "step": 830
+    },
+    {
+      "epoch": 2.8668941979522184,
+      "grad_norm": 0.1109451852100889,
+      "learning_rate": 3.1482061525015537e-07,
+      "loss": 0.3248,
+      "step": 840
+    },
+    {
+      "epoch": 2.901023890784983,
+      "grad_norm": 0.11192896622215733,
+      "learning_rate": 1.772496727805495e-07,
+      "loss": 0.3216,
+      "step": 850
+    },
+    {
+      "epoch": 2.9351535836177476,
+      "grad_norm": 0.11288193182916881,
+      "learning_rate": 7.882943541027976e-08,
+      "loss": 0.3255,
+      "step": 860
+    },
+    {
+      "epoch": 2.969283276450512,
+      "grad_norm": 0.11665972567296903,
+      "learning_rate": 1.9715132581624164e-08,
+      "loss": 0.3277,
+      "step": 870
+    },
+    {
+      "epoch": 3.0,
+      "step": 879,
+      "total_flos": 4042009736118272.0,
+      "train_loss": 0.38500409647059525,
+      "train_runtime": 77088.3871,
+      "train_samples_per_second": 5.837,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 879,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4042009736118272.0,
+  "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:e4f7fda2d7232df549ddda1afe0e2358dbb40b4388ab1ef5ab894846b4f385ee
+size 7736