Model save

.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 +1,77 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Llama-3.1-8B
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: llama_8b_lima_43
+  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. -->
+
+# llama_8b_lima_43
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9356
+
+## 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: 5.5e-06
+- train_batch_size: 3
+- eval_batch_size: 2
+- seed: 66
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 30
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: polynomial
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0422        | 0.0750 | 80   | 1.0044          |
+| 0.9127        | 0.1500 | 160  | 0.9607          |
+| 0.8605        | 0.2251 | 240  | 0.9440          |
+| 0.9068        | 0.3001 | 320  | 0.9343          |
+| 0.9147        | 0.3751 | 400  | 0.9293          |
+| 1.0192        | 0.4501 | 480  | 0.9250          |
+| 0.8303        | 0.5251 | 560  | 0.9192          |
+| 1.0284        | 0.6002 | 640  | 0.9292          |
+| 0.9183        | 0.6752 | 720  | 0.9389          |
+| 0.9897        | 0.7502 | 800  | 0.9337          |
+| 1.0209        | 0.8252 | 880  | 0.9390          |
+| 0.9118        | 0.9002 | 960  | 0.9374          |
+| 0.9077        | 0.9752 | 1040 | 0.9356          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beef02a6c0a88aa66391000da7678173291504d61dd89237b5f77230a5df0cfe
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1fa5aac09d32727bb723488cf9d733370207341117c4c25314ea6ff8ebb60a
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5b77fef2b88c418956356a5d57b6566c5b9e4d71491bb2d11340c90416177e
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25b36c2d1159fbb8f9a1e72a14e047c4d87dc54f7957b2c3a6e88e84759f709
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_log.jsonl

@@ -0,0 +1,227 @@
+{"current_steps": 5, "total_steps": 1066, "loss": 1.2775, "lr": 5.5e-07, "epoch": 0.0046886721680420105, "percentage": 0.47, "elapsed_time": "0:00:57", "remaining_time": "3:23:00"}
+{"current_steps": 10, "total_steps": 1066, "loss": 1.3472, "lr": 1.1e-06, "epoch": 0.009377344336084021, "percentage": 0.94, "elapsed_time": "0:01:58", "remaining_time": "3:29:09"}
+{"current_steps": 15, "total_steps": 1066, "loss": 1.1186, "lr": 1.6499999999999999e-06, "epoch": 0.014066016504126031, "percentage": 1.41, "elapsed_time": "0:02:52", "remaining_time": "3:21:35"}
+{"current_steps": 20, "total_steps": 1066, "loss": 1.1381, "lr": 2.2e-06, "epoch": 0.018754688672168042, "percentage": 1.88, "elapsed_time": "0:03:37", "remaining_time": "3:09:56"}
+{"current_steps": 25, "total_steps": 1066, "loss": 1.1455, "lr": 2.75e-06, "epoch": 0.023443360840210054, "percentage": 2.35, "elapsed_time": "0:04:22", "remaining_time": "3:02:10"}
+{"current_steps": 30, "total_steps": 1066, "loss": 1.049, "lr": 3.2999999999999997e-06, "epoch": 0.028132033008252063, "percentage": 2.81, "elapsed_time": "0:05:10", "remaining_time": "2:58:40"}
+{"current_steps": 35, "total_steps": 1066, "loss": 0.8965, "lr": 3.8499999999999996e-06, "epoch": 0.032820705176294075, "percentage": 3.28, "elapsed_time": "0:05:58", "remaining_time": "2:56:08"}
+{"current_steps": 40, "total_steps": 1066, "loss": 1.1271, "lr": 4.4e-06, "epoch": 0.037509377344336084, "percentage": 3.75, "elapsed_time": "0:06:50", "remaining_time": "2:55:27"}
+{"current_steps": 45, "total_steps": 1066, "loss": 1.0061, "lr": 4.95e-06, "epoch": 0.04219804951237809, "percentage": 4.22, "elapsed_time": "0:07:39", "remaining_time": "2:53:49"}
+{"current_steps": 50, "total_steps": 1066, "loss": 0.9871, "lr": 5.5e-06, "epoch": 0.04688672168042011, "percentage": 4.69, "elapsed_time": "0:08:22", "remaining_time": "2:50:02"}
+{"current_steps": 55, "total_steps": 1066, "loss": 1.0584, "lr": 5.414406436166232e-06, "epoch": 0.05157539384846212, "percentage": 5.16, "elapsed_time": "0:09:18", "remaining_time": "2:51:10"}
+{"current_steps": 60, "total_steps": 1066, "loss": 1.0672, "lr": 5.32986463435603e-06, "epoch": 0.056264066016504126, "percentage": 5.63, "elapsed_time": "0:10:06", "remaining_time": "2:49:31"}
+{"current_steps": 65, "total_steps": 1066, "loss": 0.9798, "lr": 5.246366801851234e-06, "epoch": 0.060952738184546135, "percentage": 6.1, "elapsed_time": "0:11:03", "remaining_time": "2:50:21"}
+{"current_steps": 70, "total_steps": 1066, "loss": 1.0684, "lr": 5.163905165275343e-06, "epoch": 0.06564141035258815, "percentage": 6.57, "elapsed_time": "0:11:54", "remaining_time": "2:49:21"}
+{"current_steps": 75, "total_steps": 1066, "loss": 1.1214, "lr": 5.082471970641763e-06, "epoch": 0.07033008252063015, "percentage": 7.04, "elapsed_time": "0:12:46", "remaining_time": "2:48:49"}
+{"current_steps": 80, "total_steps": 1066, "loss": 1.0422, "lr": 5.002059483402411e-06, "epoch": 0.07501875468867217, "percentage": 7.5, "elapsed_time": "0:13:35", "remaining_time": "2:47:35"}
+{"current_steps": 80, "total_steps": 1066, "eval_loss": 1.0044387578964233, "epoch": 0.07501875468867217, "percentage": 7.5, "elapsed_time": "0:13:57", "remaining_time": "2:52:04"}
+{"current_steps": 85, "total_steps": 1066, "loss": 1.004, "lr": 4.922659988496696e-06, "epoch": 0.07970742685671418, "percentage": 7.97, "elapsed_time": "0:14:41", "remaining_time": "2:49:34"}
+{"current_steps": 90, "total_steps": 1066, "loss": 1.1774, "lr": 4.844265790400869e-06, "epoch": 0.08439609902475619, "percentage": 8.44, "elapsed_time": "0:15:38", "remaining_time": "2:49:38"}
+{"current_steps": 95, "total_steps": 1066, "loss": 1.029, "lr": 4.766869213177739e-06, "epoch": 0.0890847711927982, "percentage": 8.91, "elapsed_time": "0:16:38", "remaining_time": "2:50:06"}
+{"current_steps": 100, "total_steps": 1066, "loss": 1.0735, "lr": 4.690462600526791e-06, "epoch": 0.09377344336084022, "percentage": 9.38, "elapsed_time": "0:17:30", "remaining_time": "2:49:08"}
+{"current_steps": 105, "total_steps": 1066, "loss": 1.0426, "lr": 4.615038315834675e-06, "epoch": 0.09846211552888222, "percentage": 9.85, "elapsed_time": "0:18:25", "remaining_time": "2:48:37"}
+{"current_steps": 110, "total_steps": 1066, "loss": 1.1257, "lr": 4.5405887422260886e-06, "epoch": 0.10315078769692423, "percentage": 10.32, "elapsed_time": "0:19:13", "remaining_time": "2:47:07"}
+{"current_steps": 115, "total_steps": 1066, "loss": 1.0203, "lr": 4.467106282615065e-06, "epoch": 0.10783945986496624, "percentage": 10.79, "elapsed_time": "0:20:00", "remaining_time": "2:45:28"}
+{"current_steps": 120, "total_steps": 1066, "loss": 1.1145, "lr": 4.394583359756651e-06, "epoch": 0.11252813203300825, "percentage": 11.26, "elapsed_time": "0:20:59", "remaining_time": "2:45:28"}
+{"current_steps": 125, "total_steps": 1066, "loss": 1.0943, "lr": 4.323012416298999e-06, "epoch": 0.11721680420105027, "percentage": 11.73, "elapsed_time": "0:21:51", "remaining_time": "2:44:31"}
+{"current_steps": 130, "total_steps": 1066, "loss": 1.087, "lr": 4.252385914835873e-06, "epoch": 0.12190547636909227, "percentage": 12.2, "elapsed_time": "0:22:45", "remaining_time": "2:43:49"}
+{"current_steps": 135, "total_steps": 1066, "loss": 1.0873, "lr": 4.182696337959566e-06, "epoch": 0.12659414853713427, "percentage": 12.66, "elapsed_time": "0:23:33", "remaining_time": "2:42:30"}
+{"current_steps": 140, "total_steps": 1066, "loss": 0.8704, "lr": 4.113936188314245e-06, "epoch": 0.1312828207051763, "percentage": 13.13, "elapsed_time": "0:24:12", "remaining_time": "2:40:04"}
+{"current_steps": 145, "total_steps": 1066, "loss": 1.1235, "lr": 4.046097988649726e-06, "epoch": 0.1359714928732183, "percentage": 13.6, "elapsed_time": "0:25:10", "remaining_time": "2:39:52"}
+{"current_steps": 150, "total_steps": 1066, "loss": 0.997, "lr": 3.979174281875685e-06, "epoch": 0.1406601650412603, "percentage": 14.07, "elapsed_time": "0:26:09", "remaining_time": "2:39:43"}
+{"current_steps": 155, "total_steps": 1066, "loss": 1.0179, "lr": 3.9131576311163e-06, "epoch": 0.14534883720930233, "percentage": 14.54, "elapsed_time": "0:27:08", "remaining_time": "2:39:31"}
+{"current_steps": 160, "total_steps": 1066, "loss": 0.9127, "lr": 3.848040619765356e-06, "epoch": 0.15003750937734434, "percentage": 15.01, "elapsed_time": "0:27:56", "remaining_time": "2:38:15"}
+{"current_steps": 160, "total_steps": 1066, "eval_loss": 0.9606707692146301, "epoch": 0.15003750937734434, "percentage": 15.01, "elapsed_time": "0:28:17", "remaining_time": "2:40:09"}
+{"current_steps": 165, "total_steps": 1066, "loss": 1.0887, "lr": 3.7838158515417857e-06, "epoch": 0.15472618154538634, "percentage": 15.48, "elapsed_time": "0:29:24", "remaining_time": "2:40:37"}
+{"current_steps": 170, "total_steps": 1066, "loss": 0.8966, "lr": 3.7204759505456866e-06, "epoch": 0.15941485371342837, "percentage": 15.95, "elapsed_time": "0:30:03", "remaining_time": "2:38:22"}
+{"current_steps": 175, "total_steps": 1066, "loss": 1.0543, "lr": 3.65801356131479e-06, "epoch": 0.16410352588147037, "percentage": 16.42, "elapsed_time": "0:30:59", "remaining_time": "2:37:47"}
+{"current_steps": 180, "total_steps": 1066, "loss": 0.9387, "lr": 3.596421348881407e-06, "epoch": 0.16879219804951237, "percentage": 16.89, "elapsed_time": "0:31:53", "remaining_time": "2:37:00"}
+{"current_steps": 185, "total_steps": 1066, "loss": 1.0746, "lr": 3.535691998829856e-06, "epoch": 0.1734808702175544, "percentage": 17.35, "elapsed_time": "0:32:42", "remaining_time": "2:35:45"}
+{"current_steps": 190, "total_steps": 1066, "loss": 0.8235, "lr": 3.4758182173543725e-06, "epoch": 0.1781695423855964, "percentage": 17.82, "elapsed_time": "0:33:33", "remaining_time": "2:34:43"}
+{"current_steps": 195, "total_steps": 1066, "loss": 0.9392, "lr": 3.4167927313175065e-06, "epoch": 0.1828582145536384, "percentage": 18.29, "elapsed_time": "0:34:23", "remaining_time": "2:33:38"}
+{"current_steps": 200, "total_steps": 1066, "loss": 0.9951, "lr": 3.358608288309036e-06, "epoch": 0.18754688672168043, "percentage": 18.76, "elapsed_time": "0:35:14", "remaining_time": "2:32:37"}
+{"current_steps": 205, "total_steps": 1066, "loss": 1.0835, "lr": 3.3012576567053635e-06, "epoch": 0.19223555888972244, "percentage": 19.23, "elapsed_time": "0:36:06", "remaining_time": "2:31:38"}
+{"current_steps": 210, "total_steps": 1066, "loss": 0.8606, "lr": 3.2447336257294427e-06, "epoch": 0.19692423105776444, "percentage": 19.7, "elapsed_time": "0:36:53", "remaining_time": "2:30:24"}
+{"current_steps": 215, "total_steps": 1066, "loss": 1.0039, "lr": 3.189029005511225e-06, "epoch": 0.20161290322580644, "percentage": 20.17, "elapsed_time": "0:37:48", "remaining_time": "2:29:37"}
+{"current_steps": 220, "total_steps": 1066, "loss": 0.9235, "lr": 3.134136627148626e-06, "epoch": 0.20630157539384847, "percentage": 20.64, "elapsed_time": "0:38:25", "remaining_time": "2:27:45"}
+{"current_steps": 225, "total_steps": 1066, "loss": 1.06, "lr": 3.080049342769041e-06, "epoch": 0.21099024756189047, "percentage": 21.11, "elapsed_time": "0:39:16", "remaining_time": "2:26:46"}
+{"current_steps": 230, "total_steps": 1066, "loss": 0.9432, "lr": 3.026760025591393e-06, "epoch": 0.21567891972993247, "percentage": 21.58, "elapsed_time": "0:40:02", "remaining_time": "2:25:32"}
+{"current_steps": 235, "total_steps": 1066, "loss": 1.0341, "lr": 2.97426156998874e-06, "epoch": 0.2203675918979745, "percentage": 22.05, "elapsed_time": "0:40:44", "remaining_time": "2:24:04"}
+{"current_steps": 240, "total_steps": 1066, "loss": 0.8605, "lr": 2.9225468915514425e-06, "epoch": 0.2250562640660165, "percentage": 22.51, "elapsed_time": "0:41:27", "remaining_time": "2:22:42"}
+{"current_steps": 240, "total_steps": 1066, "eval_loss": 0.944010317325592, "epoch": 0.2250562640660165, "percentage": 22.51, "elapsed_time": "0:41:48", "remaining_time": "2:23:52"}
+{"current_steps": 245, "total_steps": 1066, "loss": 0.986, "lr": 2.8716089271509e-06, "epoch": 0.2297449362340585, "percentage": 22.98, "elapsed_time": "0:42:34", "remaining_time": "2:22:38"}
+{"current_steps": 250, "total_steps": 1066, "loss": 0.8936, "lr": 2.8214406350038632e-06, "epoch": 0.23443360840210054, "percentage": 23.45, "elapsed_time": "0:43:12", "remaining_time": "2:21:02"}
+{"current_steps": 255, "total_steps": 1066, "loss": 1.0787, "lr": 2.772034994737337e-06, "epoch": 0.23912228057014254, "percentage": 23.92, "elapsed_time": "0:44:05", "remaining_time": "2:20:14"}
+{"current_steps": 260, "total_steps": 1066, "loss": 0.8681, "lr": 2.7233850074540736e-06, "epoch": 0.24381095273818454, "percentage": 24.39, "elapsed_time": "0:44:49", "remaining_time": "2:18:57"}
+{"current_steps": 265, "total_steps": 1066, "loss": 1.063, "lr": 2.6754836957986757e-06, "epoch": 0.24849962490622657, "percentage": 24.86, "elapsed_time": "0:45:46", "remaining_time": "2:18:21"}
+{"current_steps": 270, "total_steps": 1066, "loss": 0.9345, "lr": 2.6283241040243133e-06, "epoch": 0.25318829707426854, "percentage": 25.33, "elapsed_time": "0:46:54", "remaining_time": "2:18:17"}
+{"current_steps": 275, "total_steps": 1066, "loss": 0.9366, "lr": 2.5818992980600576e-06, "epoch": 0.25787696924231057, "percentage": 25.8, "elapsed_time": "0:47:37", "remaining_time": "2:16:59"}
+{"current_steps": 280, "total_steps": 1066, "loss": 0.9222, "lr": 2.5362023655788563e-06, "epoch": 0.2625656414103526, "percentage": 26.27, "elapsed_time": "0:48:23", "remaining_time": "2:15:49"}
+{"current_steps": 285, "total_steps": 1066, "loss": 0.9816, "lr": 2.491226416066151e-06, "epoch": 0.2672543135783946, "percentage": 26.74, "elapsed_time": "0:49:12", "remaining_time": "2:14:50"}
+{"current_steps": 290, "total_steps": 1066, "loss": 1.0592, "lr": 2.4469645808891426e-06, "epoch": 0.2719429857464366, "percentage": 27.2, "elapsed_time": "0:50:03", "remaining_time": "2:13:57"}
+{"current_steps": 295, "total_steps": 1066, "loss": 0.9458, "lr": 2.40341001336673e-06, "epoch": 0.27663165791447863, "percentage": 27.67, "elapsed_time": "0:50:57", "remaining_time": "2:13:10"}
+{"current_steps": 300, "total_steps": 1066, "loss": 0.8555, "lr": 2.3605558888401135e-06, "epoch": 0.2813203300825206, "percentage": 28.14, "elapsed_time": "0:51:46", "remaining_time": "2:12:12"}
+{"current_steps": 305, "total_steps": 1066, "loss": 1.1516, "lr": 2.318395404744094e-06, "epoch": 0.28600900225056264, "percentage": 28.61, "elapsed_time": "0:52:57", "remaining_time": "2:12:08"}
+{"current_steps": 310, "total_steps": 1066, "loss": 0.8737, "lr": 2.276921780679061e-06, "epoch": 0.29069767441860467, "percentage": 29.08, "elapsed_time": "0:53:55", "remaining_time": "2:11:31"}
+{"current_steps": 315, "total_steps": 1066, "loss": 1.0032, "lr": 2.2361282584836925e-06, "epoch": 0.29538634658664664, "percentage": 29.55, "elapsed_time": "0:54:48", "remaining_time": "2:10:41"}
+{"current_steps": 320, "total_steps": 1066, "loss": 0.9068, "lr": 2.1960081023083778e-06, "epoch": 0.30007501875468867, "percentage": 30.02, "elapsed_time": "0:55:39", "remaining_time": "2:09:44"}
+{"current_steps": 320, "total_steps": 1066, "eval_loss": 0.9342896938323975, "epoch": 0.30007501875468867, "percentage": 30.02, "elapsed_time": "0:55:59", "remaining_time": "2:10:31"}
+{"current_steps": 325, "total_steps": 1066, "loss": 1.0191, "lr": 2.156554598689365e-06, "epoch": 0.3047636909227307, "percentage": 30.49, "elapsed_time": "0:57:04", "remaining_time": "2:10:08"}
+{"current_steps": 330, "total_steps": 1066, "loss": 0.9328, "lr": 2.117761056623659e-06, "epoch": 0.3094523630907727, "percentage": 30.96, "elapsed_time": "0:58:08", "remaining_time": "2:09:41"}
+{"current_steps": 335, "total_steps": 1066, "loss": 1.0101, "lr": 2.0796208076446752e-06, "epoch": 0.3141410352588147, "percentage": 31.43, "elapsed_time": "0:58:55", "remaining_time": "2:08:34"}
+{"current_steps": 340, "total_steps": 1066, "loss": 0.9154, "lr": 2.0421272058986607e-06, "epoch": 0.31882970742685673, "percentage": 31.89, "elapsed_time": "0:59:58", "remaining_time": "2:08:04"}
+{"current_steps": 345, "total_steps": 1066, "loss": 1.044, "lr": 2.0052736282219008e-06, "epoch": 0.3235183795948987, "percentage": 32.36, "elapsed_time": "1:00:59", "remaining_time": "2:07:28"}
+{"current_steps": 350, "total_steps": 1066, "loss": 1.0251, "lr": 1.9690534742187182e-06, "epoch": 0.32820705176294074, "percentage": 32.83, "elapsed_time": "1:01:45", "remaining_time": "2:06:20"}
+{"current_steps": 355, "total_steps": 1066, "loss": 0.9126, "lr": 1.9334601663402865e-06, "epoch": 0.33289572393098277, "percentage": 33.3, "elapsed_time": "1:03:05", "remaining_time": "2:06:21"}
+{"current_steps": 360, "total_steps": 1066, "loss": 0.9877, "lr": 1.898487149964267e-06, "epoch": 0.33758439609902474, "percentage": 33.77, "elapsed_time": "1:04:07", "remaining_time": "2:05:46"}
+{"current_steps": 365, "total_steps": 1066, "loss": 0.9057, "lr": 1.8641278934752799e-06, "epoch": 0.34227306826706677, "percentage": 34.24, "elapsed_time": "1:05:03", "remaining_time": "2:04:56"}
+{"current_steps": 370, "total_steps": 1066, "loss": 1.0681, "lr": 1.8303758883462328e-06, "epoch": 0.3469617404351088, "percentage": 34.71, "elapsed_time": "1:06:09", "remaining_time": "2:04:27"}
+{"current_steps": 375, "total_steps": 1066, "loss": 0.9568, "lr": 1.7972246492205194e-06, "epoch": 0.3516504126031508, "percentage": 35.18, "elapsed_time": "1:07:12", "remaining_time": "2:03:50"}
+{"current_steps": 380, "total_steps": 1066, "loss": 1.032, "lr": 1.7646677139950976e-06, "epoch": 0.3563390847711928, "percentage": 35.65, "elapsed_time": "1:08:22", "remaining_time": "2:03:25"}
+{"current_steps": 385, "total_steps": 1066, "loss": 0.9867, "lr": 1.7326986439044696e-06, "epoch": 0.36102775693923483, "percentage": 36.12, "elapsed_time": "1:09:14", "remaining_time": "2:02:29"}
+{"current_steps": 390, "total_steps": 1066, "loss": 0.8747, "lr": 1.701311023605583e-06, "epoch": 0.3657164291072768, "percentage": 36.59, "elapsed_time": "1:10:13", "remaining_time": "2:01:43"}
+{"current_steps": 395, "total_steps": 1066, "loss": 0.9224, "lr": 1.6704984612636572e-06, "epoch": 0.37040510127531884, "percentage": 37.05, "elapsed_time": "1:11:13", "remaining_time": "2:00:58"}
+{"current_steps": 400, "total_steps": 1066, "loss": 0.9147, "lr": 1.6402545886389659e-06, "epoch": 0.37509377344336087, "percentage": 37.52, "elapsed_time": "1:12:11", "remaining_time": "2:00:11"}
+{"current_steps": 400, "total_steps": 1066, "eval_loss": 0.9293374419212341, "epoch": 0.37509377344336087, "percentage": 37.52, "elapsed_time": "1:12:31", "remaining_time": "2:00:45"}
+{"current_steps": 405, "total_steps": 1066, "loss": 0.9285, "lr": 1.610573061174586e-06, "epoch": 0.37978244561140284, "percentage": 37.99, "elapsed_time": "1:13:27", "remaining_time": "1:59:53"}
+{"current_steps": 410, "total_steps": 1066, "loss": 0.9994, "lr": 1.5814475580851346e-06, "epoch": 0.38447111777944487, "percentage": 38.46, "elapsed_time": "1:14:14", "remaining_time": "1:58:46"}
+{"current_steps": 415, "total_steps": 1066, "loss": 0.8864, "lr": 1.5528717824465089e-06, "epoch": 0.38915978994748684, "percentage": 38.93, "elapsed_time": "1:15:13", "remaining_time": "1:57:59"}
+{"current_steps": 420, "total_steps": 1066, "loss": 1.1302, "lr": 1.5248394612866496e-06, "epoch": 0.3938484621155289, "percentage": 39.4, "elapsed_time": "1:16:20", "remaining_time": "1:57:24"}
+{"current_steps": 425, "total_steps": 1066, "loss": 0.9394, "lr": 1.4973443456773522e-06, "epoch": 0.3985371342835709, "percentage": 39.87, "elapsed_time": "1:17:27", "remaining_time": "1:56:49"}
+{"current_steps": 430, "total_steps": 1066, "loss": 0.7922, "lr": 1.4703802108271373e-06, "epoch": 0.4032258064516129, "percentage": 40.34, "elapsed_time": "1:18:25", "remaining_time": "1:56:00"}
+{"current_steps": 435, "total_steps": 1066, "loss": 0.9312, "lr": 1.4439408561752077e-06, "epoch": 0.4079144786196549, "percentage": 40.81, "elapsed_time": "1:19:14", "remaining_time": "1:54:56"}
+{"current_steps": 440, "total_steps": 1066, "loss": 0.9859, "lr": 1.4180201054865116e-06, "epoch": 0.41260315078769694, "percentage": 41.28, "elapsed_time": "1:20:13", "remaining_time": "1:54:08"}
+{"current_steps": 445, "total_steps": 1066, "loss": 1.0307, "lr": 1.392611806947934e-06, "epoch": 0.4172918229557389, "percentage": 41.74, "elapsed_time": "1:21:14", "remaining_time": "1:53:22"}
+{"current_steps": 450, "total_steps": 1066, "loss": 0.92, "lr": 1.3677098332656357e-06, "epoch": 0.42198049512378094, "percentage": 42.21, "elapsed_time": "1:22:05", "remaining_time": "1:52:23"}
+{"current_steps": 455, "total_steps": 1066, "loss": 1.0955, "lr": 1.3433080817635696e-06, "epoch": 0.42666916729182297, "percentage": 42.68, "elapsed_time": "1:23:20", "remaining_time": "1:51:55"}
+{"current_steps": 460, "total_steps": 1066, "loss": 0.903, "lr": 1.3194004744831898e-06, "epoch": 0.43135783945986494, "percentage": 43.15, "elapsed_time": "1:24:10", "remaining_time": "1:50:53"}
+{"current_steps": 465, "total_steps": 1066, "loss": 0.8284, "lr": 1.2959809582843855e-06, "epoch": 0.436046511627907, "percentage": 43.62, "elapsed_time": "1:25:26", "remaining_time": "1:50:26"}
+{"current_steps": 470, "total_steps": 1066, "loss": 1.0462, "lr": 1.273043504947661e-06, "epoch": 0.440735183795949, "percentage": 44.09, "elapsed_time": "1:26:33", "remaining_time": "1:49:46"}
+{"current_steps": 475, "total_steps": 1066, "loss": 0.979, "lr": 1.2505821112775862e-06, "epoch": 0.445423855963991, "percentage": 44.56, "elapsed_time": "1:27:33", "remaining_time": "1:48:56"}
+{"current_steps": 480, "total_steps": 1066, "loss": 1.0192, "lr": 1.2285907992075474e-06, "epoch": 0.450112528132033, "percentage": 45.03, "elapsed_time": "1:28:26", "remaining_time": "1:47:58"}
+{"current_steps": 480, "total_steps": 1066, "eval_loss": 0.9250276684761047, "epoch": 0.450112528132033, "percentage": 45.03, "elapsed_time": "1:28:47", "remaining_time": "1:48:23"}
+{"current_steps": 485, "total_steps": 1066, "loss": 0.9037, "lr": 1.207063615905829e-06, "epoch": 0.45480120030007504, "percentage": 45.5, "elapsed_time": "1:29:42", "remaining_time": "1:47:27"}
+{"current_steps": 490, "total_steps": 1066, "loss": 1.0312, "lr": 1.1859946338830404e-06, "epoch": 0.459489872468117, "percentage": 45.97, "elapsed_time": "1:30:38", "remaining_time": "1:46:33"}
+{"current_steps": 495, "total_steps": 1066, "loss": 0.9113, "lr": 1.1653779511009372e-06, "epoch": 0.46417854463615904, "percentage": 46.44, "elapsed_time": "1:31:42", "remaining_time": "1:45:47"}
+{"current_steps": 500, "total_steps": 1066, "loss": 0.8337, "lr": 1.145207691082648e-06, "epoch": 0.46886721680420107, "percentage": 46.9, "elapsed_time": "1:32:39", "remaining_time": "1:44:53"}
+{"current_steps": 505, "total_steps": 1066, "loss": 0.9602, "lr": 1.1254780030243539e-06, "epoch": 0.47355588897224304, "percentage": 47.37, "elapsed_time": "1:33:35", "remaining_time": "1:43:58"}
+{"current_steps": 510, "total_steps": 1066, "loss": 0.9804, "lr": 1.1061830619084358e-06, "epoch": 0.4782445611402851, "percentage": 47.84, "elapsed_time": "1:34:58", "remaining_time": "1:43:32"}
+{"current_steps": 515, "total_steps": 1066, "loss": 0.977, "lr": 1.087317068618139e-06, "epoch": 0.4829332333083271, "percentage": 48.31, "elapsed_time": "1:36:06", "remaining_time": "1:42:49"}
+{"current_steps": 520, "total_steps": 1066, "loss": 0.9425, "lr": 1.0688742500537784e-06, "epoch": 0.4876219054763691, "percentage": 48.78, "elapsed_time": "1:37:30", "remaining_time": "1:42:23"}
+{"current_steps": 525, "total_steps": 1066, "loss": 0.9995, "lr": 1.0508488592505175e-06, "epoch": 0.4923105776444111, "percentage": 49.25, "elapsed_time": "1:38:30", "remaining_time": "1:41:30"}
+{"current_steps": 530, "total_steps": 1066, "loss": 0.9329, "lr": 1.0332351754977698e-06, "epoch": 0.49699924981245314, "percentage": 49.72, "elapsed_time": "1:39:38", "remaining_time": "1:40:46"}
+{"current_steps": 535, "total_steps": 1066, "loss": 0.9203, "lr": 1.016027504460246e-06, "epoch": 0.5016879219804952, "percentage": 50.19, "elapsed_time": "1:40:50", "remaining_time": "1:40:05"}
+{"current_steps": 540, "total_steps": 1066, "loss": 1.0291, "lr": 9.992201783006927e-07, "epoch": 0.5063765941485371, "percentage": 50.66, "elapsed_time": "1:41:51", "remaining_time": "1:39:13"}
+{"current_steps": 545, "total_steps": 1066, "loss": 0.9292, "lr": 9.828075558043617e-07, "epoch": 0.5110652663165791, "percentage": 51.13, "elapsed_time": "1:42:51", "remaining_time": "1:38:19"}
+{"current_steps": 550, "total_steps": 1066, "loss": 1.0165, "lr": 9.667840225052484e-07, "epoch": 0.5157539384846211, "percentage": 51.59, "elapsed_time": "1:43:53", "remaining_time": "1:37:28"}
+{"current_steps": 555, "total_steps": 1066, "loss": 1.012, "lr": 9.511439908141446e-07, "epoch": 0.5204426106526632, "percentage": 52.06, "elapsed_time": "1:44:53", "remaining_time": "1:36:34"}
+{"current_steps": 560, "total_steps": 1066, "loss": 0.8303, "lr": 9.358819001485473e-07, "epoch": 0.5251312828207052, "percentage": 52.53, "elapsed_time": "1:45:47", "remaining_time": "1:35:35"}
+{"current_steps": 560, "total_steps": 1066, "eval_loss": 0.9191934466362, "epoch": 0.5251312828207052, "percentage": 52.53, "elapsed_time": "1:46:07", "remaining_time": "1:35:53"}
+{"current_steps": 565, "total_steps": 1066, "loss": 1.022, "lr": 9.209922170644708e-07, "epoch": 0.5298199549887472, "percentage": 53.0, "elapsed_time": "1:47:06", "remaining_time": "1:34:58"}
+{"current_steps": 570, "total_steps": 1066, "loss": 0.9437, "lr": 9.06469435390206e-07, "epoch": 0.5345086271567892, "percentage": 53.47, "elapsed_time": "1:48:10", "remaining_time": "1:34:07"}
+{"current_steps": 575, "total_steps": 1066, "loss": 0.9776, "lr": 8.923080763620794e-07, "epoch": 0.5391972993248312, "percentage": 53.94, "elapsed_time": "1:49:18", "remaining_time": "1:33:20"}
+{"current_steps": 580, "total_steps": 1066, "loss": 0.8858, "lr": 8.785026887622588e-07, "epoch": 0.5438859714928732, "percentage": 54.41, "elapsed_time": "1:50:12", "remaining_time": "1:32:20"}
+{"current_steps": 585, "total_steps": 1066, "loss": 0.9392, "lr": 8.650478490586582e-07, "epoch": 0.5485746436609152, "percentage": 54.88, "elapsed_time": "1:51:16", "remaining_time": "1:31:29"}
+{"current_steps": 590, "total_steps": 1066, "loss": 1.0067, "lr": 8.519381615469985e-07, "epoch": 0.5532633158289573, "percentage": 55.35, "elapsed_time": "1:52:33", "remaining_time": "1:30:48"}
+{"current_steps": 595, "total_steps": 1066, "loss": 0.8645, "lr": 8.391682584950767e-07, "epoch": 0.5579519879969993, "percentage": 55.82, "elapsed_time": "1:53:35", "remaining_time": "1:29:55"}
+{"current_steps": 600, "total_steps": 1066, "loss": 0.8116, "lr": 8.267328002892997e-07, "epoch": 0.5626406601650412, "percentage": 56.29, "elapsed_time": "1:54:42", "remaining_time": "1:29:05"}
+{"current_steps": 605, "total_steps": 1066, "loss": 1.0685, "lr": 8.146264755835511e-07, "epoch": 0.5673293323330832, "percentage": 56.75, "elapsed_time": "1:55:42", "remaining_time": "1:28:10"}
+{"current_steps": 610, "total_steps": 1066, "loss": 1.0312, "lr": 8.028440014504431e-07, "epoch": 0.5720180045011253, "percentage": 57.22, "elapsed_time": "1:56:50", "remaining_time": "1:27:20"}
+{"current_steps": 615, "total_steps": 1066, "loss": 0.9753, "lr": 7.913801235350256e-07, "epoch": 0.5767066766691673, "percentage": 57.69, "elapsed_time": "1:58:00", "remaining_time": "1:26:32"}
+{"current_steps": 620, "total_steps": 1066, "loss": 1.0626, "lr": 7.80229616211014e-07, "epoch": 0.5813953488372093, "percentage": 58.16, "elapsed_time": "1:59:08", "remaining_time": "1:25:42"}
+{"current_steps": 625, "total_steps": 1066, "loss": 0.8915, "lr": 7.693872827396111e-07, "epoch": 0.5860840210052514, "percentage": 58.63, "elapsed_time": "2:00:05", "remaining_time": "1:24:44"}
+{"current_steps": 630, "total_steps": 1066, "loss": 0.9256, "lr": 7.58847955430991e-07, "epoch": 0.5907726931732933, "percentage": 59.1, "elapsed_time": "2:01:10", "remaining_time": "1:23:51"}
+{"current_steps": 635, "total_steps": 1066, "loss": 0.8844, "lr": 7.486064958085216e-07, "epoch": 0.5954613653413353, "percentage": 59.57, "elapsed_time": "2:02:08", "remaining_time": "1:22:54"}
+{"current_steps": 640, "total_steps": 1066, "loss": 1.0284, "lr": 7.386577947758049e-07, "epoch": 0.6001500375093773, "percentage": 60.04, "elapsed_time": "2:03:13", "remaining_time": "1:22:01"}
+{"current_steps": 640, "total_steps": 1066, "eval_loss": 0.9292100667953491, "epoch": 0.6001500375093773, "percentage": 60.04, "elapsed_time": "2:03:33", "remaining_time": "1:22:14"}
+{"current_steps": 645, "total_steps": 1066, "loss": 0.8607, "lr": 7.289967727866171e-07, "epoch": 0.6048387096774194, "percentage": 60.51, "elapsed_time": "2:04:18", "remaining_time": "1:21:08"}
+{"current_steps": 650, "total_steps": 1066, "loss": 1.0461, "lr": 7.196183800178289e-07, "epoch": 0.6095273818454614, "percentage": 60.98, "elapsed_time": "2:05:17", "remaining_time": "1:20:11"}
+{"current_steps": 655, "total_steps": 1066, "loss": 0.8923, "lr": 7.105175965454019e-07, "epoch": 0.6142160540135033, "percentage": 61.44, "elapsed_time": "2:06:12", "remaining_time": "1:19:11"}
+{"current_steps": 660, "total_steps": 1066, "loss": 0.908, "lr": 7.016894325235454e-07, "epoch": 0.6189047261815454, "percentage": 61.91, "elapsed_time": "2:07:17", "remaining_time": "1:18:17"}
+{"current_steps": 665, "total_steps": 1066, "loss": 0.8488, "lr": 6.931289283671353e-07, "epoch": 0.6235933983495874, "percentage": 62.38, "elapsed_time": "2:08:06", "remaining_time": "1:17:15"}
+{"current_steps": 670, "total_steps": 1066, "loss": 0.815, "lr": 6.84831154937491e-07, "epoch": 0.6282820705176294, "percentage": 62.85, "elapsed_time": "2:08:57", "remaining_time": "1:16:13"}
+{"current_steps": 675, "total_steps": 1066, "loss": 1.0641, "lr": 6.767912137316187e-07, "epoch": 0.6329707426856714, "percentage": 63.32, "elapsed_time": "2:10:04", "remaining_time": "1:15:21"}
+{"current_steps": 680, "total_steps": 1066, "loss": 0.9388, "lr": 6.690042370750264e-07, "epoch": 0.6376594148537135, "percentage": 63.79, "elapsed_time": "2:11:06", "remaining_time": "1:14:25"}
+{"current_steps": 685, "total_steps": 1066, "loss": 0.83, "lr": 6.614653883182271e-07, "epoch": 0.6423480870217554, "percentage": 64.26, "elapsed_time": "2:11:53", "remaining_time": "1:13:21"}
+{"current_steps": 690, "total_steps": 1066, "loss": 0.9852, "lr": 6.541698620370481e-07, "epoch": 0.6470367591897974, "percentage": 64.73, "elapsed_time": "2:12:52", "remaining_time": "1:12:24"}
+{"current_steps": 695, "total_steps": 1066, "loss": 0.8914, "lr": 6.471128842368711e-07, "epoch": 0.6517254313578394, "percentage": 65.2, "elapsed_time": "2:13:47", "remaining_time": "1:11:25"}
+{"current_steps": 700, "total_steps": 1066, "loss": 0.9833, "lr": 6.402897125609332e-07, "epoch": 0.6564141035258815, "percentage": 65.67, "elapsed_time": "2:14:35", "remaining_time": "1:10:22"}
+{"current_steps": 705, "total_steps": 1066, "loss": 1.0902, "lr": 6.336956365028259e-07, "epoch": 0.6611027756939235, "percentage": 66.14, "elapsed_time": "2:15:37", "remaining_time": "1:09:26"}
+{"current_steps": 710, "total_steps": 1066, "loss": 0.8316, "lr": 6.273259776233337e-07, "epoch": 0.6657914478619655, "percentage": 66.6, "elapsed_time": "2:16:33", "remaining_time": "1:08:28"}
+{"current_steps": 715, "total_steps": 1066, "loss": 1.0283, "lr": 6.211760897717641e-07, "epoch": 0.6704801200300075, "percentage": 67.07, "elapsed_time": "2:17:46", "remaining_time": "1:07:38"}
+{"current_steps": 720, "total_steps": 1066, "loss": 0.9183, "lr": 6.152413593119235e-07, "epoch": 0.6751687921980495, "percentage": 67.54, "elapsed_time": "2:18:40", "remaining_time": "1:06:38"}
+{"current_steps": 720, "total_steps": 1066, "eval_loss": 0.9389083385467529, "epoch": 0.6751687921980495, "percentage": 67.54, "elapsed_time": "2:19:01", "remaining_time": "1:06:48"}
+{"current_steps": 725, "total_steps": 1066, "loss": 1.034, "lr": 6.095172053529076e-07, "epoch": 0.6798574643660915, "percentage": 68.01, "elapsed_time": "2:20:10", "remaining_time": "1:05:56"}
+{"current_steps": 730, "total_steps": 1066, "loss": 0.898, "lr": 6.039990799848741e-07, "epoch": 0.6845461365341335, "percentage": 68.48, "elapsed_time": "2:21:19", "remaining_time": "1:05:02"}
+{"current_steps": 735, "total_steps": 1066, "loss": 0.7855, "lr": 5.986824685199863e-07, "epoch": 0.6892348087021756, "percentage": 68.95, "elapsed_time": "2:22:18", "remaining_time": "1:04:05"}
+{"current_steps": 740, "total_steps": 1066, "loss": 1.0417, "lr": 5.935628897387149e-07, "epoch": 0.6939234808702176, "percentage": 69.42, "elapsed_time": "2:23:29", "remaining_time": "1:03:12"}
+{"current_steps": 745, "total_steps": 1066, "loss": 0.9567, "lr": 5.886358961416999e-07, "epoch": 0.6986121530382595, "percentage": 69.89, "elapsed_time": "2:24:42", "remaining_time": "1:02:21"}
+{"current_steps": 750, "total_steps": 1066, "loss": 0.7935, "lr": 5.838970742073876e-07, "epoch": 0.7033008252063015, "percentage": 70.36, "elapsed_time": "2:25:44", "remaining_time": "1:01:24"}
+{"current_steps": 755, "total_steps": 1066, "loss": 0.9967, "lr": 5.793420446556638e-07, "epoch": 0.7079894973743436, "percentage": 70.83, "elapsed_time": "2:26:48", "remaining_time": "1:00:28"}
+{"current_steps": 760, "total_steps": 1066, "loss": 1.0786, "lr": 5.74966462717722e-07, "epoch": 0.7126781695423856, "percentage": 71.29, "elapsed_time": "2:27:55", "remaining_time": "0:59:33"}
+{"current_steps": 765, "total_steps": 1066, "loss": 1.115, "lr": 5.707660184124143e-07, "epoch": 0.7173668417104276, "percentage": 71.76, "elapsed_time": "2:29:17", "remaining_time": "0:58:44"}
+{"current_steps": 770, "total_steps": 1066, "loss": 0.9502, "lr": 5.667364368293497e-07, "epoch": 0.7220555138784697, "percentage": 72.23, "elapsed_time": "2:30:15", "remaining_time": "0:57:45"}
+{"current_steps": 775, "total_steps": 1066, "loss": 0.9964, "lr": 5.6287347841902e-07, "epoch": 0.7267441860465116, "percentage": 72.7, "elapsed_time": "2:31:21", "remaining_time": "0:56:49"}
+{"current_steps": 780, "total_steps": 1066, "loss": 1.0077, "lr": 5.591729392902467e-07, "epoch": 0.7314328582145536, "percentage": 73.17, "elapsed_time": "2:32:24", "remaining_time": "0:55:52"}
+{"current_steps": 785, "total_steps": 1066, "loss": 0.7058, "lr": 5.556306515152638e-07, "epoch": 0.7361215303825956, "percentage": 73.64, "elapsed_time": "2:33:26", "remaining_time": "0:54:55"}
+{"current_steps": 790, "total_steps": 1066, "loss": 0.856, "lr": 5.522424834427688e-07, "epoch": 0.7408102025506377, "percentage": 74.11, "elapsed_time": "2:34:16", "remaining_time": "0:53:53"}
+{"current_steps": 795, "total_steps": 1066, "loss": 0.9852, "lr": 5.490043400192936e-07, "epoch": 0.7454988747186797, "percentage": 74.58, "elapsed_time": "2:35:32", "remaining_time": "0:53:01"}
+{"current_steps": 800, "total_steps": 1066, "loss": 0.9897, "lr": 5.459121631192727e-07, "epoch": 0.7501875468867217, "percentage": 75.05, "elapsed_time": "2:36:35", "remaining_time": "0:52:03"}
+{"current_steps": 800, "total_steps": 1066, "eval_loss": 0.9337027072906494, "epoch": 0.7501875468867217, "percentage": 75.05, "elapsed_time": "2:36:55", "remaining_time": "0:52:10"}
+{"current_steps": 805, "total_steps": 1066, "loss": 0.9693, "lr": 5.429619318842062e-07, "epoch": 0.7548762190547637, "percentage": 75.52, "elapsed_time": "2:38:00", "remaining_time": "0:51:13"}
+{"current_steps": 810, "total_steps": 1066, "loss": 0.9363, "lr": 5.401496630713439e-07, "epoch": 0.7595648912228057, "percentage": 75.98, "elapsed_time": "2:39:09", "remaining_time": "0:50:18"}
+{"current_steps": 815, "total_steps": 1066, "loss": 0.9007, "lr": 5.374714114123462e-07, "epoch": 0.7642535633908477, "percentage": 76.45, "elapsed_time": "2:40:15", "remaining_time": "0:49:21"}
+{"current_steps": 820, "total_steps": 1066, "loss": 0.8538, "lr": 5.34923269982403e-07, "epoch": 0.7689422355588897, "percentage": 76.92, "elapsed_time": "2:41:09", "remaining_time": "0:48:20"}
+{"current_steps": 825, "total_steps": 1066, "loss": 0.9429, "lr": 5.325013705803326e-07, "epoch": 0.7736309077269318, "percentage": 77.39, "elapsed_time": "2:42:31", "remaining_time": "0:47:28"}
+{"current_steps": 830, "total_steps": 1066, "loss": 0.862, "lr": 5.302018841202155e-07, "epoch": 0.7783195798949737, "percentage": 77.86, "elapsed_time": "2:43:34", "remaining_time": "0:46:30"}
+{"current_steps": 835, "total_steps": 1066, "loss": 0.8743, "lr": 5.28021021035156e-07, "epoch": 0.7830082520630157, "percentage": 78.33, "elapsed_time": "2:44:35", "remaining_time": "0:45:31"}
+{"current_steps": 840, "total_steps": 1066, "loss": 0.8728, "lr": 5.25955031693814e-07, "epoch": 0.7876969242310577, "percentage": 78.8, "elapsed_time": "2:45:32", "remaining_time": "0:44:32"}
+{"current_steps": 845, "total_steps": 1066, "loss": 0.9804, "lr": 5.240002068303935e-07, "epoch": 0.7923855963990998, "percentage": 79.27, "elapsed_time": "2:46:47", "remaining_time": "0:43:37"}
+{"current_steps": 850, "total_steps": 1066, "loss": 0.9592, "lr": 5.22152877988829e-07, "epoch": 0.7970742685671418, "percentage": 79.74, "elapsed_time": "2:47:56", "remaining_time": "0:42:40"}
+{"current_steps": 855, "total_steps": 1066, "loss": 1.1113, "lr": 5.204094179819663e-07, "epoch": 0.8017629407351838, "percentage": 80.21, "elapsed_time": "2:49:10", "remaining_time": "0:41:45"}
+{"current_steps": 860, "total_steps": 1066, "loss": 0.896, "lr": 5.187662413666055e-07, "epoch": 0.8064516129032258, "percentage": 80.68, "elapsed_time": "2:50:26", "remaining_time": "0:40:49"}
+{"current_steps": 865, "total_steps": 1066, "loss": 0.9484, "lr": 5.137741469209312e-07, "epoch": 0.8111402850712678, "percentage": 81.14, "elapsed_time": "2:51:50", "remaining_time": "0:39:55"}
+{"current_steps": 870, "total_steps": 1066, "loss": 0.9107, "lr": 5.034812576940423e-07, "epoch": 0.8158289572393098, "percentage": 81.61, "elapsed_time": "2:53:02", "remaining_time": "0:38:59"}
+{"current_steps": 875, "total_steps": 1066, "loss": 1.0274, "lr": 4.931883684671535e-07, "epoch": 0.8205176294073518, "percentage": 82.08, "elapsed_time": "2:54:19", "remaining_time": "0:38:03"}
+{"current_steps": 880, "total_steps": 1066, "loss": 1.0209, "lr": 4.828954792402647e-07, "epoch": 0.8252063015753939, "percentage": 82.55, "elapsed_time": "2:55:39", "remaining_time": "0:37:07"}
+{"current_steps": 880, "total_steps": 1066, "eval_loss": 0.93896484375, "epoch": 0.8252063015753939, "percentage": 82.55, "elapsed_time": "2:56:00", "remaining_time": "0:37:12"}
+{"current_steps": 885, "total_steps": 1066, "loss": 0.9472, "lr": 4.7260259001337577e-07, "epoch": 0.8298949737434359, "percentage": 83.02, "elapsed_time": "2:57:17", "remaining_time": "0:36:15"}
+{"current_steps": 890, "total_steps": 1066, "loss": 0.9458, "lr": 4.6230970078648696e-07, "epoch": 0.8345836459114778, "percentage": 83.49, "elapsed_time": "2:58:53", "remaining_time": "0:35:22"}
+{"current_steps": 895, "total_steps": 1066, "loss": 0.7928, "lr": 4.5201681155959816e-07, "epoch": 0.8392723180795199, "percentage": 83.96, "elapsed_time": "3:00:07", "remaining_time": "0:34:24"}
+{"current_steps": 900, "total_steps": 1066, "loss": 0.8992, "lr": 4.417239223327093e-07, "epoch": 0.8439609902475619, "percentage": 84.43, "elapsed_time": "3:01:24", "remaining_time": "0:33:27"}
+{"current_steps": 905, "total_steps": 1066, "loss": 1.0681, "lr": 4.314310331058205e-07, "epoch": 0.8486496624156039, "percentage": 84.9, "elapsed_time": "3:03:00", "remaining_time": "0:32:33"}
+{"current_steps": 910, "total_steps": 1066, "loss": 1.057, "lr": 4.2113814387893164e-07, "epoch": 0.8533383345836459, "percentage": 85.37, "elapsed_time": "3:04:20", "remaining_time": "0:31:36"}
+{"current_steps": 915, "total_steps": 1066, "loss": 0.9609, "lr": 4.108452546520428e-07, "epoch": 0.858027006751688, "percentage": 85.83, "elapsed_time": "3:05:33", "remaining_time": "0:30:37"}
+{"current_steps": 920, "total_steps": 1066, "loss": 0.9775, "lr": 4.00552365425154e-07, "epoch": 0.8627156789197299, "percentage": 86.3, "elapsed_time": "3:07:11", "remaining_time": "0:29:42"}
+{"current_steps": 925, "total_steps": 1066, "loss": 0.7712, "lr": 3.9025947619826517e-07, "epoch": 0.8674043510877719, "percentage": 86.77, "elapsed_time": "3:08:08", "remaining_time": "0:28:40"}
+{"current_steps": 930, "total_steps": 1066, "loss": 0.9408, "lr": 3.7996658697137626e-07, "epoch": 0.872093023255814, "percentage": 87.24, "elapsed_time": "3:09:36", "remaining_time": "0:27:43"}
+{"current_steps": 935, "total_steps": 1066, "loss": 0.8363, "lr": 3.6967369774448745e-07, "epoch": 0.876781695423856, "percentage": 87.71, "elapsed_time": "3:10:38", "remaining_time": "0:26:42"}
+{"current_steps": 940, "total_steps": 1066, "loss": 0.9977, "lr": 3.5938080851759865e-07, "epoch": 0.881470367591898, "percentage": 88.18, "elapsed_time": "3:12:00", "remaining_time": "0:25:44"}
+{"current_steps": 945, "total_steps": 1066, "loss": 0.9326, "lr": 3.490879192907099e-07, "epoch": 0.88615903975994, "percentage": 88.65, "elapsed_time": "3:13:18", "remaining_time": "0:24:45"}
+{"current_steps": 950, "total_steps": 1066, "loss": 0.9909, "lr": 3.38795030063821e-07, "epoch": 0.890847711927982, "percentage": 89.12, "elapsed_time": "3:14:31", "remaining_time": "0:23:45"}
+{"current_steps": 955, "total_steps": 1066, "loss": 0.8207, "lr": 3.285021408369321e-07, "epoch": 0.895536384096024, "percentage": 89.59, "elapsed_time": "3:15:30", "remaining_time": "0:22:43"}
+{"current_steps": 960, "total_steps": 1066, "loss": 0.9118, "lr": 3.1820925161004326e-07, "epoch": 0.900225056264066, "percentage": 90.06, "elapsed_time": "3:16:45", "remaining_time": "0:21:43"}
+{"current_steps": 960, "total_steps": 1066, "eval_loss": 0.9374144077301025, "epoch": 0.900225056264066, "percentage": 90.06, "elapsed_time": "3:17:06", "remaining_time": "0:21:45"}
+{"current_steps": 965, "total_steps": 1066, "loss": 0.8345, "lr": 3.0791636238315446e-07, "epoch": 0.904913728432108, "percentage": 90.53, "elapsed_time": "3:18:16", "remaining_time": "0:20:45"}
+{"current_steps": 970, "total_steps": 1066, "loss": 0.7999, "lr": 2.9762347315626565e-07, "epoch": 0.9096024006001501, "percentage": 90.99, "elapsed_time": "3:19:23", "remaining_time": "0:19:43"}
+{"current_steps": 975, "total_steps": 1066, "loss": 0.8812, "lr": 2.873305839293768e-07, "epoch": 0.9142910727681921, "percentage": 91.46, "elapsed_time": "3:20:22", "remaining_time": "0:18:42"}
+{"current_steps": 980, "total_steps": 1066, "loss": 0.9124, "lr": 2.7703769470248794e-07, "epoch": 0.918979744936234, "percentage": 91.93, "elapsed_time": "3:21:23", "remaining_time": "0:17:40"}
+{"current_steps": 985, "total_steps": 1066, "loss": 0.8418, "lr": 2.6674480547559913e-07, "epoch": 0.923668417104276, "percentage": 92.4, "elapsed_time": "3:22:23", "remaining_time": "0:16:38"}
+{"current_steps": 990, "total_steps": 1066, "loss": 0.9194, "lr": 2.5645191624871027e-07, "epoch": 0.9283570892723181, "percentage": 92.87, "elapsed_time": "3:23:50", "remaining_time": "0:15:38"}
+{"current_steps": 995, "total_steps": 1066, "loss": 0.9541, "lr": 2.4615902702182147e-07, "epoch": 0.9330457614403601, "percentage": 93.34, "elapsed_time": "3:25:00", "remaining_time": "0:14:37"}
+{"current_steps": 1000, "total_steps": 1066, "loss": 0.8087, "lr": 2.3586613779493258e-07, "epoch": 0.9377344336084021, "percentage": 93.81, "elapsed_time": "3:26:08", "remaining_time": "0:13:36"}
+{"current_steps": 1005, "total_steps": 1066, "loss": 0.9081, "lr": 2.255732485680438e-07, "epoch": 0.9424231057764441, "percentage": 94.28, "elapsed_time": "3:27:22", "remaining_time": "0:12:35"}
+{"current_steps": 1010, "total_steps": 1066, "loss": 0.859, "lr": 2.1528035934115495e-07, "epoch": 0.9471117779444861, "percentage": 94.75, "elapsed_time": "3:28:24", "remaining_time": "0:11:33"}
+{"current_steps": 1015, "total_steps": 1066, "loss": 0.8725, "lr": 2.0498747011426614e-07, "epoch": 0.9518004501125281, "percentage": 95.22, "elapsed_time": "3:29:41", "remaining_time": "0:10:32"}
+{"current_steps": 1020, "total_steps": 1066, "loss": 0.7904, "lr": 1.9469458088737728e-07, "epoch": 0.9564891222805701, "percentage": 95.68, "elapsed_time": "3:31:03", "remaining_time": "0:09:31"}
+{"current_steps": 1025, "total_steps": 1066, "loss": 1.0669, "lr": 1.8440169166048842e-07, "epoch": 0.9611777944486122, "percentage": 96.15, "elapsed_time": "3:32:29", "remaining_time": "0:08:29"}
+{"current_steps": 1030, "total_steps": 1066, "loss": 0.8434, "lr": 1.7410880243359964e-07, "epoch": 0.9658664666166542, "percentage": 96.62, "elapsed_time": "3:33:33", "remaining_time": "0:07:27"}
+{"current_steps": 1035, "total_steps": 1066, "loss": 1.0234, "lr": 1.6381591320671076e-07, "epoch": 0.9705551387846961, "percentage": 97.09, "elapsed_time": "3:34:51", "remaining_time": "0:06:26"}
+{"current_steps": 1040, "total_steps": 1066, "loss": 0.9077, "lr": 1.5352302397982195e-07, "epoch": 0.9752438109527382, "percentage": 97.56, "elapsed_time": "3:36:06", "remaining_time": "0:05:24"}
+{"current_steps": 1040, "total_steps": 1066, "eval_loss": 0.9355975389480591, "epoch": 0.9752438109527382, "percentage": 97.56, "elapsed_time": "3:36:26", "remaining_time": "0:05:24"}
+{"current_steps": 1045, "total_steps": 1066, "loss": 0.7646, "lr": 1.432301347529331e-07, "epoch": 0.9799324831207802, "percentage": 98.03, "elapsed_time": "3:37:57", "remaining_time": "0:04:22"}
+{"current_steps": 1050, "total_steps": 1066, "loss": 0.8593, "lr": 1.329372455260443e-07, "epoch": 0.9846211552888222, "percentage": 98.5, "elapsed_time": "3:39:00", "remaining_time": "0:03:20"}
+{"current_steps": 1055, "total_steps": 1066, "loss": 1.0972, "lr": 1.2264435629915543e-07, "epoch": 0.9893098274568642, "percentage": 98.97, "elapsed_time": "3:40:18", "remaining_time": "0:02:17"}
+{"current_steps": 1060, "total_steps": 1066, "loss": 0.7634, "lr": 1.1235146707226661e-07, "epoch": 0.9939984996249063, "percentage": 99.44, "elapsed_time": "3:41:37", "remaining_time": "0:01:15"}
+{"current_steps": 1065, "total_steps": 1066, "loss": 0.9783, "lr": 1.0205857784537777e-07, "epoch": 0.9986871717929482, "percentage": 99.91, "elapsed_time": "3:42:54", "remaining_time": "0:00:12"}
+{"current_steps": 1066, "total_steps": 1066, "epoch": 0.9996249062265566, "percentage": 100.0, "elapsed_time": "3:43:23", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2d496c3092fe8595a7c98cebc75d38952f1e39df0611f495b3b3abb82d311d
+size 7288