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 +1,74 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Llama-3.1-8B-Instruct
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: llama_8b_lima_44
+  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_44
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9046
+
+## 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: 6
+- total_train_batch_size: 36
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0313        | 0.0974 | 80   | 0.9290          |
+| 0.985         | 0.1948 | 160  | 0.9194          |
+| 1.091         | 0.2923 | 240  | 0.9109          |
+| 0.9087        | 0.3897 | 320  | 0.9030          |
+| 1.0107        | 0.4871 | 400  | 0.8975          |
+| 0.9108        | 0.5845 | 480  | 0.8940          |
+| 1.1531        | 0.6820 | 560  | 0.9039          |
+| 1.2698        | 0.7794 | 640  | 0.9069          |
+| 1.1988        | 0.8768 | 720  | 0.9063          |
+| 1.1649        | 0.9742 | 800  | 0.9046          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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 sha256:3a4ee1b48363dc43ae8e333abccff9127d5a6b4e46654263b5218744a9ed3a9d
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc054eae02b9cfa9b7f6fb605def76f91e469f5d0f1ee6c9b290dc42dddeb3f
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caca07fa8bd978f221f360157a1b534ca8c5d1d1667a14d5454d51e442645954
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02acd1e769f549c3c6f8f683cfb5b56e97bd0409b6262962a52c934ef05c784c
+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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "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 +1,175 @@
+{"current_steps": 5, "total_steps": 821, "loss": 1.1009, "lr": 5.5e-07, "epoch": 0.006088897909478384, "percentage": 0.61, "elapsed_time": "0:00:34", "remaining_time": "1:34:58"}
+{"current_steps": 10, "total_steps": 821, "loss": 1.0381, "lr": 1.1e-06, "epoch": 0.012177795818956769, "percentage": 1.22, "elapsed_time": "0:01:11", "remaining_time": "1:36:48"}
+{"current_steps": 15, "total_steps": 821, "loss": 0.9465, "lr": 1.6499999999999999e-06, "epoch": 0.018266693728435153, "percentage": 1.83, "elapsed_time": "0:01:38", "remaining_time": "1:28:23"}
+{"current_steps": 20, "total_steps": 821, "loss": 1.2107, "lr": 2.2e-06, "epoch": 0.024355591637913537, "percentage": 2.44, "elapsed_time": "0:02:12", "remaining_time": "1:28:09"}
+{"current_steps": 25, "total_steps": 821, "loss": 1.1834, "lr": 2.75e-06, "epoch": 0.03044448954739192, "percentage": 3.05, "elapsed_time": "0:02:44", "remaining_time": "1:27:27"}
+{"current_steps": 30, "total_steps": 821, "loss": 1.0345, "lr": 3.2999999999999997e-06, "epoch": 0.036533387456870306, "percentage": 3.65, "elapsed_time": "0:03:16", "remaining_time": "1:26:17"}
+{"current_steps": 35, "total_steps": 821, "loss": 0.8937, "lr": 3.8499999999999996e-06, "epoch": 0.04262228536634869, "percentage": 4.26, "elapsed_time": "0:03:46", "remaining_time": "1:24:50"}
+{"current_steps": 40, "total_steps": 821, "loss": 1.0384, "lr": 4.4e-06, "epoch": 0.048711183275827075, "percentage": 4.87, "elapsed_time": "0:04:21", "remaining_time": "1:24:57"}
+{"current_steps": 45, "total_steps": 821, "loss": 0.8559, "lr": 4.95e-06, "epoch": 0.05480008118530546, "percentage": 5.48, "elapsed_time": "0:04:48", "remaining_time": "1:22:47"}
+{"current_steps": 50, "total_steps": 821, "loss": 1.0974, "lr": 5.5e-06, "epoch": 0.06088897909478384, "percentage": 6.09, "elapsed_time": "0:05:18", "remaining_time": "1:21:45"}
+{"current_steps": 55, "total_steps": 821, "loss": 1.0212, "lr": 5.416103509565232e-06, "epoch": 0.06697787700426223, "percentage": 6.7, "elapsed_time": "0:05:43", "remaining_time": "1:19:47"}
+{"current_steps": 60, "total_steps": 821, "loss": 0.9416, "lr": 5.333024453086441e-06, "epoch": 0.07306677491374061, "percentage": 7.31, "elapsed_time": "0:06:12", "remaining_time": "1:18:40"}
+{"current_steps": 65, "total_steps": 821, "loss": 1.2031, "lr": 5.250760158320862e-06, "epoch": 0.079155672823219, "percentage": 7.92, "elapsed_time": "0:06:45", "remaining_time": "1:18:37"}
+{"current_steps": 70, "total_steps": 821, "loss": 0.8486, "lr": 5.16930794423241e-06, "epoch": 0.08524457073269738, "percentage": 8.53, "elapsed_time": "0:07:12", "remaining_time": "1:17:20"}
+{"current_steps": 75, "total_steps": 821, "loss": 1.1537, "lr": 5.088665120904279e-06, "epoch": 0.09133346864217577, "percentage": 9.14, "elapsed_time": "0:07:49", "remaining_time": "1:17:54"}
+{"current_steps": 80, "total_steps": 821, "loss": 1.0313, "lr": 5.008828989450109e-06, "epoch": 0.09742236655165415, "percentage": 9.74, "elapsed_time": "0:08:14", "remaining_time": "1:16:16"}
+{"current_steps": 80, "total_steps": 821, "eval_loss": 0.9289844036102295, "epoch": 0.09742236655165415, "percentage": 9.74, "elapsed_time": "0:08:24", "remaining_time": "1:17:56"}
+{"current_steps": 85, "total_steps": 821, "loss": 0.9282, "lr": 4.92979684192366e-06, "epoch": 0.10351126446113254, "percentage": 10.35, "elapsed_time": "0:08:55", "remaining_time": "1:17:13"}
+{"current_steps": 90, "total_steps": 821, "loss": 0.8977, "lr": 4.851565961226947e-06, "epoch": 0.10960016237061092, "percentage": 10.96, "elapsed_time": "0:09:26", "remaining_time": "1:16:41"}
+{"current_steps": 95, "total_steps": 821, "loss": 0.9419, "lr": 4.774133621016826e-06, "epoch": 0.11568906028008931, "percentage": 11.57, "elapsed_time": "0:09:55", "remaining_time": "1:15:53"}
+{"current_steps": 100, "total_steps": 821, "loss": 0.9848, "lr": 4.69749708560997e-06, "epoch": 0.12177795818956769, "percentage": 12.18, "elapsed_time": "0:10:24", "remaining_time": "1:15:02"}
+{"current_steps": 105, "total_steps": 821, "loss": 1.215, "lr": 4.621653609886213e-06, "epoch": 0.12786685609904608, "percentage": 12.79, "elapsed_time": "0:10:53", "remaining_time": "1:14:14"}
+{"current_steps": 110, "total_steps": 821, "loss": 1.1061, "lr": 4.5466004391902066e-06, "epoch": 0.13395575400852447, "percentage": 13.4, "elapsed_time": "0:11:28", "remaining_time": "1:14:13"}
+{"current_steps": 115, "total_steps": 821, "loss": 0.9953, "lr": 4.472334809231365e-06, "epoch": 0.14004465191800283, "percentage": 14.01, "elapsed_time": "0:12:04", "remaining_time": "1:14:05"}
+{"current_steps": 120, "total_steps": 821, "loss": 0.6939, "lr": 4.398853945982053e-06, "epoch": 0.14613354982748122, "percentage": 14.62, "elapsed_time": "0:12:32", "remaining_time": "1:13:15"}
+{"current_steps": 125, "total_steps": 821, "loss": 0.9363, "lr": 4.326155065573944e-06, "epoch": 0.15222244773695962, "percentage": 15.23, "elapsed_time": "0:12:56", "remaining_time": "1:12:05"}
+{"current_steps": 130, "total_steps": 821, "loss": 1.195, "lr": 4.254235374192553e-06, "epoch": 0.158311345646438, "percentage": 15.83, "elapsed_time": "0:13:29", "remaining_time": "1:11:42"}
+{"current_steps": 135, "total_steps": 821, "loss": 0.9793, "lr": 4.183092067969859e-06, "epoch": 0.16440024355591637, "percentage": 16.44, "elapsed_time": "0:13:58", "remaining_time": "1:10:59"}
+{"current_steps": 140, "total_steps": 821, "loss": 0.9404, "lr": 4.112722332874986e-06, "epoch": 0.17048914146539476, "percentage": 17.05, "elapsed_time": "0:14:29", "remaining_time": "1:10:27"}
+{"current_steps": 145, "total_steps": 821, "loss": 0.7751, "lr": 4.043123344602879e-06, "epoch": 0.17657803937487315, "percentage": 17.66, "elapsed_time": "0:14:57", "remaining_time": "1:09:44"}
+{"current_steps": 150, "total_steps": 821, "loss": 0.874, "lr": 3.974292268460949e-06, "epoch": 0.18266693728435154, "percentage": 18.27, "elapsed_time": "0:15:27", "remaining_time": "1:09:07"}
+{"current_steps": 155, "total_steps": 821, "loss": 0.9028, "lr": 3.906226259253599e-06, "epoch": 0.1887558351938299, "percentage": 18.88, "elapsed_time": "0:15:53", "remaining_time": "1:08:15"}
+{"current_steps": 160, "total_steps": 821, "loss": 0.985, "lr": 3.838922461164612e-06, "epoch": 0.1948447331033083, "percentage": 19.49, "elapsed_time": "0:16:24", "remaining_time": "1:07:45"}
+{"current_steps": 160, "total_steps": 821, "eval_loss": 0.9194434881210327, "epoch": 0.1948447331033083, "percentage": 19.49, "elapsed_time": "0:16:34", "remaining_time": "1:08:26"}
+{"current_steps": 165, "total_steps": 821, "loss": 1.2669, "lr": 3.772378007637317e-06, "epoch": 0.2009336310127867, "percentage": 20.1, "elapsed_time": "0:17:07", "remaining_time": "1:08:06"}
+{"current_steps": 170, "total_steps": 821, "loss": 0.8301, "lr": 3.7065900212524865e-06, "epoch": 0.20702252892226508, "percentage": 20.71, "elapsed_time": "0:17:33", "remaining_time": "1:07:13"}
+{"current_steps": 175, "total_steps": 821, "loss": 0.9021, "lr": 3.6415556136039017e-06, "epoch": 0.21311142683174344, "percentage": 21.32, "elapsed_time": "0:18:03", "remaining_time": "1:06:40"}
+{"current_steps": 180, "total_steps": 821, "loss": 0.925, "lr": 3.57727188517153e-06, "epoch": 0.21920032474122184, "percentage": 21.92, "elapsed_time": "0:18:37", "remaining_time": "1:06:17"}
+{"current_steps": 185, "total_steps": 821, "loss": 0.861, "lr": 3.513735925192236e-06, "epoch": 0.22528922265070023, "percentage": 22.53, "elapsed_time": "0:19:01", "remaining_time": "1:05:23"}
+{"current_steps": 190, "total_steps": 821, "loss": 1.1969, "lr": 3.4509448115279674e-06, "epoch": 0.23137812056017862, "percentage": 23.14, "elapsed_time": "0:19:31", "remaining_time": "1:04:50"}
+{"current_steps": 195, "total_steps": 821, "loss": 0.8704, "lr": 3.388895610531349e-06, "epoch": 0.23746701846965698, "percentage": 23.75, "elapsed_time": "0:20:05", "remaining_time": "1:04:28"}
+{"current_steps": 200, "total_steps": 821, "loss": 0.9503, "lr": 3.3275853769086063e-06, "epoch": 0.24355591637913537, "percentage": 24.36, "elapsed_time": "0:20:36", "remaining_time": "1:03:59"}
+{"current_steps": 205, "total_steps": 821, "loss": 0.9347, "lr": 3.267011153579745e-06, "epoch": 0.24964481428861376, "percentage": 24.97, "elapsed_time": "0:21:04", "remaining_time": "1:03:20"}
+{"current_steps": 210, "total_steps": 821, "loss": 0.8733, "lr": 3.2071699715359122e-06, "epoch": 0.25573371219809216, "percentage": 25.58, "elapsed_time": "0:21:35", "remaining_time": "1:02:49"}
+{"current_steps": 215, "total_steps": 821, "loss": 1.065, "lr": 3.148058849693859e-06, "epoch": 0.2618226101075705, "percentage": 26.19, "elapsed_time": "0:22:05", "remaining_time": "1:02:15"}
+{"current_steps": 220, "total_steps": 821, "loss": 0.9307, "lr": 3.0896747947474105e-06, "epoch": 0.26791150801704894, "percentage": 26.8, "elapsed_time": "0:22:34", "remaining_time": "1:01:40"}
+{"current_steps": 225, "total_steps": 821, "loss": 1.0314, "lr": 3.0320148010158774e-06, "epoch": 0.2740004059265273, "percentage": 27.41, "elapsed_time": "0:23:07", "remaining_time": "1:01:16"}
+{"current_steps": 230, "total_steps": 821, "loss": 0.9115, "lr": 2.975075850289298e-06, "epoch": 0.28008930383600567, "percentage": 28.01, "elapsed_time": "0:23:37", "remaining_time": "1:00:41"}
+{"current_steps": 235, "total_steps": 821, "loss": 1.0111, "lr": 2.9188549116704386e-06, "epoch": 0.2861782017454841, "percentage": 28.62, "elapsed_time": "0:24:12", "remaining_time": "1:00:21"}
+{"current_steps": 240, "total_steps": 821, "loss": 1.091, "lr": 2.8633489414134293e-06, "epoch": 0.29226709965496245, "percentage": 29.23, "elapsed_time": "0:24:44", "remaining_time": "0:59:54"}
+{"current_steps": 240, "total_steps": 821, "eval_loss": 0.9108514189720154, "epoch": 0.29226709965496245, "percentage": 29.23, "elapsed_time": "0:24:54", "remaining_time": "1:00:18"}
+{"current_steps": 245, "total_steps": 821, "loss": 0.9449, "lr": 2.8085548827589632e-06, "epoch": 0.2983559975644408, "percentage": 29.84, "elapsed_time": "0:25:42", "remaining_time": "1:00:25"}
+{"current_steps": 250, "total_steps": 821, "loss": 1.0587, "lr": 2.7544696657659385e-06, "epoch": 0.30444489547391923, "percentage": 30.45, "elapsed_time": "0:26:15", "remaining_time": "0:59:59"}
+{"current_steps": 255, "total_steps": 821, "loss": 0.7525, "lr": 2.7010902071394348e-06, "epoch": 0.3105337933833976, "percentage": 31.06, "elapsed_time": "0:26:39", "remaining_time": "0:59:09"}
+{"current_steps": 260, "total_steps": 821, "loss": 0.8815, "lr": 2.6484134100549204e-06, "epoch": 0.316622691292876, "percentage": 31.67, "elapsed_time": "0:27:06", "remaining_time": "0:58:29"}
+{"current_steps": 265, "total_steps": 821, "loss": 1.1089, "lr": 2.5964361639785647e-06, "epoch": 0.3227115892023544, "percentage": 32.28, "elapsed_time": "0:27:38", "remaining_time": "0:58:00"}
+{"current_steps": 270, "total_steps": 821, "loss": 1.0962, "lr": 2.5451553444835415e-06, "epoch": 0.32880048711183274, "percentage": 32.89, "elapsed_time": "0:28:14", "remaining_time": "0:57:38"}
+{"current_steps": 275, "total_steps": 821, "loss": 0.981, "lr": 2.4945678130621847e-06, "epoch": 0.33488938502131116, "percentage": 33.5, "elapsed_time": "0:28:47", "remaining_time": "0:57:09"}
+{"current_steps": 280, "total_steps": 821, "loss": 0.8348, "lr": 2.4446704169338846e-06, "epoch": 0.3409782829307895, "percentage": 34.1, "elapsed_time": "0:29:14", "remaining_time": "0:56:29"}
+{"current_steps": 285, "total_steps": 821, "loss": 0.7611, "lr": 2.3954599888485643e-06, "epoch": 0.3470671808402679, "percentage": 34.71, "elapsed_time": "0:29:38", "remaining_time": "0:55:44"}
+{"current_steps": 290, "total_steps": 821, "loss": 1.1149, "lr": 2.3469333468856106e-06, "epoch": 0.3531560787497463, "percentage": 35.32, "elapsed_time": "0:30:15", "remaining_time": "0:55:23"}
+{"current_steps": 295, "total_steps": 821, "loss": 0.8705, "lr": 2.299087294248103e-06, "epoch": 0.35924497665922467, "percentage": 35.93, "elapsed_time": "0:30:46", "remaining_time": "0:54:51"}
+{"current_steps": 300, "total_steps": 821, "loss": 0.7842, "lr": 2.25191861905219e-06, "epoch": 0.3653338745687031, "percentage": 36.54, "elapsed_time": "0:31:15", "remaining_time": "0:54:16"}
+{"current_steps": 305, "total_steps": 821, "loss": 0.9357, "lr": 2.205424094111439e-06, "epoch": 0.37142277247818145, "percentage": 37.15, "elapsed_time": "0:31:44", "remaining_time": "0:53:41"}
+{"current_steps": 310, "total_steps": 821, "loss": 1.088, "lr": 2.1596004767160085e-06, "epoch": 0.3775116703876598, "percentage": 37.76, "elapsed_time": "0:32:20", "remaining_time": "0:53:18"}
+{"current_steps": 315, "total_steps": 821, "loss": 1.0323, "lr": 2.1144445084064565e-06, "epoch": 0.38360056829713823, "percentage": 38.37, "elapsed_time": "0:32:57", "remaining_time": "0:52:56"}
+{"current_steps": 320, "total_steps": 821, "loss": 0.9087, "lr": 2.069952914741992e-06, "epoch": 0.3896894662066166, "percentage": 38.98, "elapsed_time": "0:33:33", "remaining_time": "0:52:32"}
+{"current_steps": 320, "total_steps": 821, "eval_loss": 0.9030415415763855, "epoch": 0.3896894662066166, "percentage": 38.98, "elapsed_time": "0:33:43", "remaining_time": "0:52:47"}
+{"current_steps": 325, "total_steps": 821, "loss": 0.9356, "lr": 2.026122405062999e-06, "epoch": 0.39577836411609496, "percentage": 39.59, "elapsed_time": "0:34:18", "remaining_time": "0:52:21"}
+{"current_steps": 330, "total_steps": 821, "loss": 0.9179, "lr": 1.982949672247615e-06, "epoch": 0.4018672620255734, "percentage": 40.19, "elapsed_time": "0:34:48", "remaining_time": "0:51:47"}
+{"current_steps": 335, "total_steps": 821, "loss": 0.9632, "lr": 1.940431392462155e-06, "epoch": 0.40795615993505174, "percentage": 40.8, "elapsed_time": "0:35:23", "remaining_time": "0:51:20"}
+{"current_steps": 340, "total_steps": 821, "loss": 0.8374, "lr": 1.8985642249051713e-06, "epoch": 0.41404505784453016, "percentage": 41.41, "elapsed_time": "0:35:49", "remaining_time": "0:50:41"}
+{"current_steps": 345, "total_steps": 821, "loss": 0.8853, "lr": 1.8573448115449084e-06, "epoch": 0.4201339557540085, "percentage": 42.02, "elapsed_time": "0:36:25", "remaining_time": "0:50:15"}
+{"current_steps": 350, "total_steps": 821, "loss": 1.006, "lr": 1.8167697768499194e-06, "epoch": 0.4262228536634869, "percentage": 42.63, "elapsed_time": "0:36:59", "remaining_time": "0:49:46"}
+{"current_steps": 355, "total_steps": 821, "loss": 0.7937, "lr": 1.7768357275125856e-06, "epoch": 0.4323117515729653, "percentage": 43.24, "elapsed_time": "0:37:25", "remaining_time": "0:49:07"}
+{"current_steps": 360, "total_steps": 821, "loss": 0.937, "lr": 1.737539252165281e-06, "epoch": 0.43840064948244367, "percentage": 43.85, "elapsed_time": "0:37:57", "remaining_time": "0:48:35"}
+{"current_steps": 365, "total_steps": 821, "loss": 0.8412, "lr": 1.6988769210889033e-06, "epoch": 0.44448954739192204, "percentage": 44.46, "elapsed_time": "0:38:27", "remaining_time": "0:48:02"}
+{"current_steps": 370, "total_steps": 821, "loss": 1.0682, "lr": 1.6608452859134694e-06, "epoch": 0.45057844530140045, "percentage": 45.07, "elapsed_time": "0:39:00", "remaining_time": "0:47:32"}
+{"current_steps": 375, "total_steps": 821, "loss": 0.9272, "lr": 1.6234408793104964e-06, "epoch": 0.4566673432108788, "percentage": 45.68, "elapsed_time": "0:39:30", "remaining_time": "0:46:58"}
+{"current_steps": 380, "total_steps": 821, "loss": 0.8386, "lr": 1.5866602146768156e-06, "epoch": 0.46275624112035724, "percentage": 46.29, "elapsed_time": "0:39:58", "remaining_time": "0:46:23"}
+{"current_steps": 385, "total_steps": 821, "loss": 1.0616, "lr": 1.55049978580951e-06, "epoch": 0.4688451390298356, "percentage": 46.89, "elapsed_time": "0:40:40", "remaining_time": "0:46:03"}
+{"current_steps": 390, "total_steps": 821, "loss": 0.9667, "lr": 1.5149560665716053e-06, "epoch": 0.47493403693931396, "percentage": 47.5, "elapsed_time": "0:41:14", "remaining_time": "0:45:34"}
+{"current_steps": 395, "total_steps": 821, "loss": 0.876, "lr": 1.4800255105481483e-06, "epoch": 0.4810229348487924, "percentage": 48.11, "elapsed_time": "0:41:49", "remaining_time": "0:45:05"}
+{"current_steps": 400, "total_steps": 821, "loss": 1.0107, "lr": 1.445704550692281e-06, "epoch": 0.48711183275827075, "percentage": 48.72, "elapsed_time": "0:42:23", "remaining_time": "0:44:36"}
+{"current_steps": 400, "total_steps": 821, "eval_loss": 0.8974834680557251, "epoch": 0.48711183275827075, "percentage": 48.72, "elapsed_time": "0:42:33", "remaining_time": "0:44:47"}
+{"current_steps": 405, "total_steps": 821, "loss": 0.9153, "lr": 1.4119895989608974e-06, "epoch": 0.4932007306677491, "percentage": 49.33, "elapsed_time": "0:43:12", "remaining_time": "0:44:22"}
+{"current_steps": 410, "total_steps": 821, "loss": 0.8891, "lr": 1.3788770459394496e-06, "epoch": 0.49928962857722753, "percentage": 49.94, "elapsed_time": "0:43:45", "remaining_time": "0:43:51"}
+{"current_steps": 415, "total_steps": 821, "loss": 0.9571, "lr": 1.3463632604554425e-06, "epoch": 0.5053785264867059, "percentage": 50.55, "elapsed_time": "0:44:22", "remaining_time": "0:43:24"}
+{"current_steps": 420, "total_steps": 821, "loss": 0.963, "lr": 1.3144445891801363e-06, "epoch": 0.5114674243961843, "percentage": 51.16, "elapsed_time": "0:44:55", "remaining_time": "0:42:53"}
+{"current_steps": 425, "total_steps": 821, "loss": 1.1635, "lr": 1.28311735621795e-06, "epoch": 0.5175563223056627, "percentage": 51.77, "elapsed_time": "0:45:35", "remaining_time": "0:42:28"}
+{"current_steps": 430, "total_steps": 821, "loss": 1.0585, "lr": 1.252377862683016e-06, "epoch": 0.523645220215141, "percentage": 52.38, "elapsed_time": "0:46:11", "remaining_time": "0:42:00"}
+{"current_steps": 435, "total_steps": 821, "loss": 0.9143, "lr": 1.222222386262332e-06, "epoch": 0.5297341181246195, "percentage": 52.98, "elapsed_time": "0:46:41", "remaining_time": "0:41:25"}
+{"current_steps": 440, "total_steps": 821, "loss": 0.9188, "lr": 1.1926471807648967e-06, "epoch": 0.5358230160340979, "percentage": 53.59, "elapsed_time": "0:47:11", "remaining_time": "0:40:52"}
+{"current_steps": 445, "total_steps": 821, "loss": 0.8914, "lr": 1.1636484756561917e-06, "epoch": 0.5419119139435762, "percentage": 54.2, "elapsed_time": "0:47:43", "remaining_time": "0:40:19"}
+{"current_steps": 450, "total_steps": 821, "loss": 1.0831, "lr": 1.1352224755773445e-06, "epoch": 0.5480008118530546, "percentage": 54.81, "elapsed_time": "0:48:13", "remaining_time": "0:39:45"}
+{"current_steps": 455, "total_steps": 821, "loss": 1.0402, "lr": 1.107365359848245e-06, "epoch": 0.554089709762533, "percentage": 55.42, "elapsed_time": "0:48:49", "remaining_time": "0:39:16"}
+{"current_steps": 460, "total_steps": 821, "loss": 0.9395, "lr": 1.0800732819538616e-06, "epoch": 0.5601786076720113, "percentage": 56.03, "elapsed_time": "0:49:21", "remaining_time": "0:38:44"}
+{"current_steps": 465, "total_steps": 821, "loss": 0.8586, "lr": 1.0533423690129516e-06, "epoch": 0.5662675055814897, "percentage": 56.64, "elapsed_time": "0:50:01", "remaining_time": "0:38:17"}
+{"current_steps": 470, "total_steps": 821, "loss": 0.9337, "lr": 1.0271687212283061e-06, "epoch": 0.5723564034909682, "percentage": 57.25, "elapsed_time": "0:50:36", "remaining_time": "0:37:47"}
+{"current_steps": 475, "total_steps": 821, "loss": 0.8562, "lr": 1.0015484113176207e-06, "epoch": 0.5784453014004465, "percentage": 57.86, "elapsed_time": "0:51:08", "remaining_time": "0:37:15"}
+{"current_steps": 480, "total_steps": 821, "loss": 0.9108, "lr": 9.764774839240228e-07, "epoch": 0.5845341993099249, "percentage": 58.47, "elapsed_time": "0:51:43", "remaining_time": "0:36:44"}
+{"current_steps": 480, "total_steps": 821, "eval_loss": 0.8940006494522095, "epoch": 0.5845341993099249, "percentage": 58.47, "elapsed_time": "0:51:53", "remaining_time": "0:36:51"}
+{"current_steps": 485, "total_steps": 821, "loss": 0.9483, "lr": 9.519519550052165e-07, "epoch": 0.5906230972194033, "percentage": 59.07, "elapsed_time": "0:52:23", "remaining_time": "0:36:17"}
+{"current_steps": 490, "total_steps": 821, "loss": 0.9252, "lr": 9.27967811200154e-07, "epoch": 0.5967119951288816, "percentage": 59.68, "elapsed_time": "0:53:02", "remaining_time": "0:35:50"}
+{"current_steps": 495, "total_steps": 821, "loss": 1.045, "lr": 9.045210091720488e-07, "epoch": 0.60280089303836, "percentage": 60.29, "elapsed_time": "0:53:39", "remaining_time": "0:35:20"}
+{"current_steps": 500, "total_steps": 821, "loss": 0.8324, "lr": 8.816074749264782e-07, "epoch": 0.6088897909478385, "percentage": 60.9, "elapsed_time": "0:54:10", "remaining_time": "0:34:46"}
+{"current_steps": 505, "total_steps": 821, "loss": 0.9797, "lr": 8.592231031032369e-07, "epoch": 0.6149786888573169, "percentage": 61.51, "elapsed_time": "0:54:41", "remaining_time": "0:34:13"}
+{"current_steps": 510, "total_steps": 821, "loss": 0.9758, "lr": 8.37363756240493e-07, "epoch": 0.6210675867667952, "percentage": 62.12, "elapsed_time": "0:55:17", "remaining_time": "0:33:43"}
+{"current_steps": 515, "total_steps": 821, "loss": 0.9379, "lr": 8.160252640097203e-07, "epoch": 0.6271564846762736, "percentage": 62.73, "elapsed_time": "0:55:54", "remaining_time": "0:33:13"}
+{"current_steps": 520, "total_steps": 821, "loss": 1.0445, "lr": 7.952034224197429e-07, "epoch": 0.633245382585752, "percentage": 63.34, "elapsed_time": "0:56:25", "remaining_time": "0:32:39"}
+{"current_steps": 525, "total_steps": 821, "loss": 0.9693, "lr": 7.748939929881281e-07, "epoch": 0.6393342804952303, "percentage": 63.95, "elapsed_time": "0:57:01", "remaining_time": "0:32:09"}
+{"current_steps": 530, "total_steps": 821, "loss": 1.1654, "lr": 7.5509270187801e-07, "epoch": 0.6454231784047088, "percentage": 64.56, "elapsed_time": "0:57:37", "remaining_time": "0:31:38"}
+{"current_steps": 535, "total_steps": 821, "loss": 1.0812, "lr": 7.357952389983003e-07, "epoch": 0.6515120763141872, "percentage": 65.16, "elapsed_time": "0:58:15", "remaining_time": "0:31:08"}
+{"current_steps": 540, "total_steps": 821, "loss": 1.0663, "lr": 7.169972570650695e-07, "epoch": 0.6576009742236655, "percentage": 65.77, "elapsed_time": "0:58:50", "remaining_time": "0:30:37"}
+{"current_steps": 545, "total_steps": 821, "loss": 1.2464, "lr": 6.986943706217093e-07, "epoch": 0.6636898721331439, "percentage": 66.38, "elapsed_time": "0:59:28", "remaining_time": "0:30:07"}
+{"current_steps": 550, "total_steps": 821, "loss": 1.1615, "lr": 6.808821550153036e-07, "epoch": 0.6697787700426223, "percentage": 66.99, "elapsed_time": "1:00:14", "remaining_time": "0:29:41"}
+{"current_steps": 555, "total_steps": 821, "loss": 1.2256, "lr": 6.635561453264081e-07, "epoch": 0.6758676679521006, "percentage": 67.6, "elapsed_time": "1:01:00", "remaining_time": "0:29:14"}
+{"current_steps": 560, "total_steps": 821, "loss": 1.1531, "lr": 6.467118352492235e-07, "epoch": 0.681956565861579, "percentage": 68.21, "elapsed_time": "1:01:52", "remaining_time": "0:28:50"}
+{"current_steps": 560, "total_steps": 821, "eval_loss": 0.9038890600204468, "epoch": 0.681956565861579, "percentage": 68.21, "elapsed_time": "1:02:02", "remaining_time": "0:28:54"}
+{"current_steps": 565, "total_steps": 821, "loss": 1.1032, "lr": 6.303446759188759e-07, "epoch": 0.6880454637710575, "percentage": 68.82, "elapsed_time": "1:02:46", "remaining_time": "0:28:26"}
+{"current_steps": 570, "total_steps": 821, "loss": 1.0247, "lr": 6.14450074682243e-07, "epoch": 0.6941343616805358, "percentage": 69.43, "elapsed_time": "1:03:29", "remaining_time": "0:27:57"}
+{"current_steps": 575, "total_steps": 821, "loss": 0.9957, "lr": 5.990233938084431e-07, "epoch": 0.7002232595900142, "percentage": 70.04, "elapsed_time": "1:04:04", "remaining_time": "0:27:24"}
+{"current_steps": 580, "total_steps": 821, "loss": 1.073, "lr": 5.840599491347582e-07, "epoch": 0.7063121574994926, "percentage": 70.65, "elapsed_time": "1:04:39", "remaining_time": "0:26:51"}
+{"current_steps": 585, "total_steps": 821, "loss": 1.17, "lr": 5.695550086433726e-07, "epoch": 0.712401055408971, "percentage": 71.25, "elapsed_time": "1:05:28", "remaining_time": "0:26:24"}
+{"current_steps": 590, "total_steps": 821, "loss": 1.0394, "lr": 5.555037909638744e-07, "epoch": 0.7184899533184493, "percentage": 71.86, "elapsed_time": "1:06:11", "remaining_time": "0:25:55"}
+{"current_steps": 595, "total_steps": 821, "loss": 1.1472, "lr": 5.419014637959808e-07, "epoch": 0.7245788512279278, "percentage": 72.47, "elapsed_time": "1:06:45", "remaining_time": "0:25:21"}
+{"current_steps": 600, "total_steps": 821, "loss": 1.0496, "lr": 5.287431422464098e-07, "epoch": 0.7306677491374062, "percentage": 73.08, "elapsed_time": "1:07:26", "remaining_time": "0:24:50"}
+{"current_steps": 605, "total_steps": 821, "loss": 0.9907, "lr": 5.160238870732056e-07, "epoch": 0.7367566470468845, "percentage": 73.69, "elapsed_time": "1:08:10", "remaining_time": "0:24:20"}
+{"current_steps": 610, "total_steps": 821, "loss": 1.3347, "lr": 5.037387028301462e-07, "epoch": 0.7428455449563629, "percentage": 74.3, "elapsed_time": "1:08:56", "remaining_time": "0:23:50"}
+{"current_steps": 615, "total_steps": 821, "loss": 1.1386, "lr": 4.918825359030837e-07, "epoch": 0.7489344428658413, "percentage": 74.91, "elapsed_time": "1:09:37", "remaining_time": "0:23:19"}
+{"current_steps": 620, "total_steps": 821, "loss": 1.1201, "lr": 4.804502724291952e-07, "epoch": 0.7550233407753196, "percentage": 75.52, "elapsed_time": "1:10:12", "remaining_time": "0:22:45"}
+{"current_steps": 625, "total_steps": 821, "loss": 1.0354, "lr": 4.6943673608912795e-07, "epoch": 0.761112238684798, "percentage": 76.13, "elapsed_time": "1:10:49", "remaining_time": "0:22:12"}
+{"current_steps": 630, "total_steps": 821, "loss": 0.9314, "lr": 4.588366857608947e-07, "epoch": 0.7672011365942765, "percentage": 76.74, "elapsed_time": "1:11:25", "remaining_time": "0:21:39"}
+{"current_steps": 635, "total_steps": 821, "loss": 1.3016, "lr": 4.4864481302308764e-07, "epoch": 0.7732900345037548, "percentage": 77.34, "elapsed_time": "1:12:13", "remaining_time": "0:21:09"}
+{"current_steps": 640, "total_steps": 821, "loss": 1.2698, "lr": 4.388557394934996e-07, "epoch": 0.7793789324132332, "percentage": 77.95, "elapsed_time": "1:13:11", "remaining_time": "0:20:41"}
+{"current_steps": 640, "total_steps": 821, "eval_loss": 0.9068670868873596, "epoch": 0.7793789324132332, "percentage": 77.95, "elapsed_time": "1:13:21", "remaining_time": "0:20:44"}
+{"current_steps": 645, "total_steps": 821, "loss": 1.0936, "lr": 4.2946401398754887e-07, "epoch": 0.7854678303227116, "percentage": 78.56, "elapsed_time": "1:14:08", "remaining_time": "0:20:13"}
+{"current_steps": 650, "total_steps": 821, "loss": 1.0688, "lr": 4.20464109478947e-07, "epoch": 0.7915567282321899, "percentage": 79.17, "elapsed_time": "1:14:47", "remaining_time": "0:19:40"}
+{"current_steps": 655, "total_steps": 821, "loss": 1.2066, "lr": 4.118504198427839e-07, "epoch": 0.7976456261416683, "percentage": 79.78, "elapsed_time": "1:15:27", "remaining_time": "0:19:07"}
+{"current_steps": 660, "total_steps": 821, "loss": 1.0209, "lr": 4.036172563585779e-07, "epoch": 0.8037345240511468, "percentage": 80.39, "elapsed_time": "1:16:13", "remaining_time": "0:18:35"}
+{"current_steps": 665, "total_steps": 821, "loss": 1.1583, "lr": 3.957588439477604e-07, "epoch": 0.8098234219606252, "percentage": 81.0, "elapsed_time": "1:16:47", "remaining_time": "0:18:00"}
+{"current_steps": 670, "total_steps": 821, "loss": 1.0352, "lr": 3.8826931711647146e-07, "epoch": 0.8159123198701035, "percentage": 81.61, "elapsed_time": "1:17:29", "remaining_time": "0:17:27"}
+{"current_steps": 675, "total_steps": 821, "loss": 1.1568, "lr": 3.8114271557029493e-07, "epoch": 0.8220012177795819, "percentage": 82.22, "elapsed_time": "1:18:14", "remaining_time": "0:16:55"}
+{"current_steps": 680, "total_steps": 821, "loss": 1.0868, "lr": 3.74372979462545e-07, "epoch": 0.8280901156890603, "percentage": 82.83, "elapsed_time": "1:19:01", "remaining_time": "0:16:23"}
+{"current_steps": 685, "total_steps": 821, "loss": 1.1053, "lr": 3.679539442317327e-07, "epoch": 0.8341790135985386, "percentage": 83.43, "elapsed_time": "1:19:45", "remaining_time": "0:15:50"}
+{"current_steps": 690, "total_steps": 821, "loss": 1.1503, "lr": 3.6187933497668937e-07, "epoch": 0.840267911508017, "percentage": 84.04, "elapsed_time": "1:20:27", "remaining_time": "0:15:16"}
+{"current_steps": 695, "total_steps": 821, "loss": 1.0148, "lr": 3.5614276030919706e-07, "epoch": 0.8463568094174955, "percentage": 84.65, "elapsed_time": "1:21:06", "remaining_time": "0:14:42"}
+{"current_steps": 700, "total_steps": 821, "loss": 1.0533, "lr": 3.507377056135281e-07, "epoch": 0.8524457073269738, "percentage": 85.26, "elapsed_time": "1:21:51", "remaining_time": "0:14:08"}
+{"current_steps": 705, "total_steps": 821, "loss": 0.9223, "lr": 3.456575256295274e-07, "epoch": 0.8585346052364522, "percentage": 85.87, "elapsed_time": "1:22:29", "remaining_time": "0:13:34"}
+{"current_steps": 710, "total_steps": 821, "loss": 1.1612, "lr": 3.408954362601715e-07, "epoch": 0.8646235031459306, "percentage": 86.48, "elapsed_time": "1:23:23", "remaining_time": "0:13:02"}
+{"current_steps": 715, "total_steps": 821, "loss": 1.1011, "lr": 3.364445054850564e-07, "epoch": 0.8707124010554089, "percentage": 87.09, "elapsed_time": "1:24:10", "remaining_time": "0:12:28"}
+{"current_steps": 720, "total_steps": 821, "loss": 1.1988, "lr": 3.322976432368887e-07, "epoch": 0.8768012989648873, "percentage": 87.7, "elapsed_time": "1:25:01", "remaining_time": "0:11:55"}
+{"current_steps": 720, "total_steps": 821, "eval_loss": 0.9062988758087158, "epoch": 0.8768012989648873, "percentage": 87.7, "elapsed_time": "1:25:11", "remaining_time": "0:11:57"}
+{"current_steps": 725, "total_steps": 821, "loss": 1.217, "lr": 3.284475900672534e-07, "epoch": 0.8828901968743658, "percentage": 88.31, "elapsed_time": "1:25:58", "remaining_time": "0:11:23"}
+{"current_steps": 730, "total_steps": 821, "loss": 1.05, "lr": 3.2488690438860155e-07, "epoch": 0.8889790947838441, "percentage": 88.92, "elapsed_time": "1:26:45", "remaining_time": "0:10:48"}
+{"current_steps": 735, "total_steps": 821, "loss": 1.083, "lr": 3.216079480286014e-07, "epoch": 0.8950679926933225, "percentage": 89.52, "elapsed_time": "1:27:31", "remaining_time": "0:10:14"}
+{"current_steps": 740, "total_steps": 821, "loss": 0.9577, "lr": 3.186028697665536e-07, "epoch": 0.9011568906028009, "percentage": 90.13, "elapsed_time": "1:28:14", "remaining_time": "0:09:39"}
+{"current_steps": 745, "total_steps": 821, "loss": 1.0405, "lr": 3.1586358643344154e-07, "epoch": 0.9072457885122793, "percentage": 90.74, "elapsed_time": "1:28:55", "remaining_time": "0:09:04"}
+{"current_steps": 750, "total_steps": 821, "loss": 1.1779, "lr": 3.1338176103847303e-07, "epoch": 0.9133346864217576, "percentage": 91.35, "elapsed_time": "1:29:48", "remaining_time": "0:08:30"}
+{"current_steps": 755, "total_steps": 821, "loss": 1.1676, "lr": 3.111487772222592e-07, "epoch": 0.919423584331236, "percentage": 91.96, "elapsed_time": "1:30:38", "remaining_time": "0:07:55"}
+{"current_steps": 760, "total_steps": 821, "loss": 1.0719, "lr": 3.0915570910938297e-07, "epoch": 0.9255124822407145, "percentage": 92.57, "elapsed_time": "1:31:18", "remaining_time": "0:07:19"}
+{"current_steps": 765, "total_steps": 821, "loss": 1.0105, "lr": 3.07393285308207e-07, "epoch": 0.9316013801501928, "percentage": 93.18, "elapsed_time": "1:31:57", "remaining_time": "0:06:43"}
+{"current_steps": 770, "total_steps": 821, "loss": 1.0721, "lr": 3.0585184532967033e-07, "epoch": 0.9376902780596712, "percentage": 93.79, "elapsed_time": "1:32:46", "remaining_time": "0:06:08"}
+{"current_steps": 775, "total_steps": 821, "loss": 1.0933, "lr": 3.045212859784411e-07, "epoch": 0.9437791759691496, "percentage": 94.4, "elapsed_time": "1:33:38", "remaining_time": "0:05:33"}
+{"current_steps": 780, "total_steps": 821, "loss": 0.9671, "lr": 3.033909941480833e-07, "epoch": 0.9498680738786279, "percentage": 95.01, "elapsed_time": "1:34:24", "remaining_time": "0:04:57"}
+{"current_steps": 785, "total_steps": 821, "loss": 1.1151, "lr": 3.024497606276943e-07, "epoch": 0.9559569717881063, "percentage": 95.62, "elapsed_time": "1:35:06", "remaining_time": "0:04:21"}
+{"current_steps": 790, "total_steps": 821, "loss": 0.9727, "lr": 3.016856664111943e-07, "epoch": 0.9620458696975848, "percentage": 96.22, "elapsed_time": "1:35:56", "remaining_time": "0:03:45"}
+{"current_steps": 795, "total_steps": 821, "loss": 1.1713, "lr": 3.0108592734273526e-07, "epoch": 0.9681347676070631, "percentage": 96.83, "elapsed_time": "1:36:36", "remaining_time": "0:03:09"}
+{"current_steps": 800, "total_steps": 821, "loss": 1.1649, "lr": 3.006366718310598e-07, "epoch": 0.9742236655165415, "percentage": 97.44, "elapsed_time": "1:37:18", "remaining_time": "0:02:33"}
+{"current_steps": 800, "total_steps": 821, "eval_loss": 0.9046012759208679, "epoch": 0.9742236655165415, "percentage": 97.44, "elapsed_time": "1:37:29", "remaining_time": "0:02:33"}
+{"current_steps": 805, "total_steps": 821, "loss": 1.0695, "lr": 3.00322602222577e-07, "epoch": 0.9803125634260199, "percentage": 98.05, "elapsed_time": "1:38:18", "remaining_time": "0:01:57"}
+{"current_steps": 810, "total_steps": 821, "loss": 0.9731, "lr": 3.001264297011597e-07, "epoch": 0.9864014613354982, "percentage": 98.66, "elapsed_time": "1:38:59", "remaining_time": "0:01:20"}
+{"current_steps": 815, "total_steps": 821, "loss": 0.9058, "lr": 3.00027780849675e-07, "epoch": 0.9924903592449766, "percentage": 99.27, "elapsed_time": "1:39:34", "remaining_time": "0:00:43"}
+{"current_steps": 820, "total_steps": 821, "loss": 1.2194, "lr": 3.0000031504123295e-07, "epoch": 0.9985792571544551, "percentage": 99.88, "elapsed_time": "1:40:24", "remaining_time": "0:00:07"}
+{"current_steps": 821, "total_steps": 821, "epoch": 0.9997970367363507, "percentage": 100.0, "elapsed_time": "1:41:01", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19cc20bad5cbfc58042c15c47ff3a9bd10e6f11acb93b2e5057667680cc69f91
+size 7288