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 +1,78 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Llama-3.1-8B
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: llama_8b_lima_42
+  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_42
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9002
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0356        | 0.0686 | 80   | 0.9711          |
+| 1.0348        | 0.1372 | 160  | 0.9355          |
+| 0.7212        | 0.2058 | 240  | 0.9225          |
+| 0.8077        | 0.2744 | 320  | 0.9142          |
+| 0.8442        | 0.3430 | 400  | 0.9068          |
+| 0.831         | 0.4116 | 480  | 0.9032          |
+| 0.9696        | 0.4802 | 560  | 0.8975          |
+| 0.9949        | 0.5488 | 640  | 0.8972          |
+| 0.8154        | 0.6174 | 720  | 0.8948          |
+| 0.9682        | 0.6860 | 800  | 0.8931          |
+| 0.9491        | 0.7546 | 880  | 0.9030          |
+| 1.068         | 0.8232 | 960  | 0.9022          |
+| 1.06          | 0.8918 | 1040 | 0.9013          |
+| 0.8302        | 0.9604 | 1120 | 0.9002          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb957db8c385262a44c87146f77347ee6ef7daa441c262dc2643c91c229d2b9
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef71bec7936f831e8c676aa6963d515f28404d461cb758803c528874a0b1a0c
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c000a23d1278f223d577ca618b07396373ef9ea8c4186396a3977d2cbd7bb79b
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efed0cf91e0b5761e1cf851a44b8e3f751c33f5c66917a875a1c0a8878cec11f
+size 1168138808

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,248 @@
+{"current_steps": 5, "total_steps": 1166, "loss": 1.2482, "lr": 5.000000000000001e-07, "epoch": 0.004287551807917679, "percentage": 0.43, "elapsed_time": "0:01:10", "remaining_time": "4:33:19"}
+{"current_steps": 10, "total_steps": 1166, "loss": 1.2111, "lr": 1.0000000000000002e-06, "epoch": 0.008575103615835357, "percentage": 0.86, "elapsed_time": "0:02:00", "remaining_time": "3:52:03"}
+{"current_steps": 15, "total_steps": 1166, "loss": 1.2375, "lr": 1.5e-06, "epoch": 0.012862655423753037, "percentage": 1.29, "elapsed_time": "0:02:52", "remaining_time": "3:40:25"}
+{"current_steps": 20, "total_steps": 1166, "loss": 1.0833, "lr": 2.0000000000000003e-06, "epoch": 0.017150207231670715, "percentage": 1.72, "elapsed_time": "0:03:43", "remaining_time": "3:33:25"}
+{"current_steps": 25, "total_steps": 1166, "loss": 1.0052, "lr": 2.5e-06, "epoch": 0.021437759039588396, "percentage": 2.14, "elapsed_time": "0:04:27", "remaining_time": "3:23:20"}
+{"current_steps": 30, "total_steps": 1166, "loss": 1.0283, "lr": 3e-06, "epoch": 0.025725310847506073, "percentage": 2.57, "elapsed_time": "0:05:16", "remaining_time": "3:19:26"}
+{"current_steps": 35, "total_steps": 1166, "loss": 1.0801, "lr": 3.5e-06, "epoch": 0.030012862655423755, "percentage": 3.0, "elapsed_time": "0:06:05", "remaining_time": "3:16:48"}
+{"current_steps": 40, "total_steps": 1166, "loss": 1.0753, "lr": 4.000000000000001e-06, "epoch": 0.03430041446334143, "percentage": 3.43, "elapsed_time": "0:06:53", "remaining_time": "3:14:10"}
+{"current_steps": 45, "total_steps": 1166, "loss": 0.9409, "lr": 4.5e-06, "epoch": 0.038587966271259114, "percentage": 3.86, "elapsed_time": "0:07:34", "remaining_time": "3:08:36"}
+{"current_steps": 50, "total_steps": 1166, "loss": 1.0198, "lr": 5e-06, "epoch": 0.04287551807917679, "percentage": 4.29, "elapsed_time": "0:08:18", "remaining_time": "3:05:21"}
+{"current_steps": 55, "total_steps": 1166, "loss": 1.0699, "lr": 4.926711109482401e-06, "epoch": 0.04716306988709447, "percentage": 4.72, "elapsed_time": "0:09:10", "remaining_time": "3:05:10"}
+{"current_steps": 60, "total_steps": 1166, "loss": 1.0268, "lr": 4.854242179361151e-06, "epoch": 0.05145062169501215, "percentage": 5.15, "elapsed_time": "0:09:50", "remaining_time": "3:01:28"}
+{"current_steps": 65, "total_steps": 1166, "loss": 1.2315, "lr": 4.782587680591894e-06, "epoch": 0.055738173502929825, "percentage": 5.57, "elapsed_time": "0:10:50", "remaining_time": "3:03:41"}
+{"current_steps": 70, "total_steps": 1166, "loss": 0.9914, "lr": 4.711742096614044e-06, "epoch": 0.06002572531084751, "percentage": 6.0, "elapsed_time": "0:11:37", "remaining_time": "3:01:55"}
+{"current_steps": 75, "total_steps": 1166, "loss": 0.9354, "lr": 4.641699923379107e-06, "epoch": 0.06431327711876518, "percentage": 6.43, "elapsed_time": "0:12:21", "remaining_time": "2:59:43"}
+{"current_steps": 80, "total_steps": 1166, "loss": 1.0356, "lr": 4.5724556693791996e-06, "epoch": 0.06860082892668286, "percentage": 6.86, "elapsed_time": "0:13:15", "remaining_time": "2:59:52"}
+{"current_steps": 80, "total_steps": 1166, "eval_loss": 0.9710695743560791, "epoch": 0.06860082892668286, "percentage": 6.86, "elapsed_time": "0:13:35", "remaining_time": "3:04:36"}
+{"current_steps": 85, "total_steps": 1166, "loss": 1.0218, "lr": 4.504003855675734e-06, "epoch": 0.07288838073460055, "percentage": 7.29, "elapsed_time": "0:14:23", "remaining_time": "3:03:02"}
+{"current_steps": 90, "total_steps": 1166, "loss": 0.9059, "lr": 4.436339015928335e-06, "epoch": 0.07717593254251823, "percentage": 7.72, "elapsed_time": "0:15:03", "remaining_time": "2:59:57"}
+{"current_steps": 95, "total_steps": 1166, "loss": 0.9862, "lr": 4.369455696423936e-06, "epoch": 0.0814634843504359, "percentage": 8.15, "elapsed_time": "0:15:52", "remaining_time": "2:59:02"}
+{"current_steps": 100, "total_steps": 1166, "loss": 0.9869, "lr": 4.303348456106082e-06, "epoch": 0.08575103615835358, "percentage": 8.58, "elapsed_time": "0:16:37", "remaining_time": "2:57:15"}
+{"current_steps": 105, "total_steps": 1166, "loss": 1.0137, "lr": 4.238011866604447e-06, "epoch": 0.09003858796627126, "percentage": 9.01, "elapsed_time": "0:17:35", "remaining_time": "2:57:42"}
+{"current_steps": 110, "total_steps": 1166, "loss": 0.9834, "lr": 4.173440512264544e-06, "epoch": 0.09432613977418894, "percentage": 9.43, "elapsed_time": "0:18:21", "remaining_time": "2:56:18"}
+{"current_steps": 115, "total_steps": 1166, "loss": 0.9828, "lr": 4.109628990177651e-06, "epoch": 0.09861369158210662, "percentage": 9.86, "elapsed_time": "0:19:12", "remaining_time": "2:55:31"}
+{"current_steps": 120, "total_steps": 1166, "loss": 0.9892, "lr": 4.04657191021096e-06, "epoch": 0.1029012433900243, "percentage": 10.29, "elapsed_time": "0:20:03", "remaining_time": "2:54:48"}
+{"current_steps": 125, "total_steps": 1166, "loss": 0.9903, "lr": 3.984263895037921e-06, "epoch": 0.10718879519794197, "percentage": 10.72, "elapsed_time": "0:20:54", "remaining_time": "2:54:08"}
+{"current_steps": 130, "total_steps": 1166, "loss": 1.1259, "lr": 3.9226995801688165e-06, "epoch": 0.11147634700585965, "percentage": 11.15, "elapsed_time": "0:21:48", "remaining_time": "2:53:46"}
+{"current_steps": 135, "total_steps": 1166, "loss": 0.9734, "lr": 3.8618736139815605e-06, "epoch": 0.11576389881377733, "percentage": 11.58, "elapsed_time": "0:22:42", "remaining_time": "2:53:21"}
+{"current_steps": 140, "total_steps": 1166, "loss": 1.0515, "lr": 3.8017806577526982e-06, "epoch": 0.12005145062169502, "percentage": 12.01, "elapsed_time": "0:23:44", "remaining_time": "2:54:01"}
+{"current_steps": 145, "total_steps": 1166, "loss": 0.8449, "lr": 3.7424153856886596e-06, "epoch": 0.1243390024296127, "percentage": 12.44, "elapsed_time": "0:24:26", "remaining_time": "2:52:07"}
+{"current_steps": 150, "total_steps": 1166, "loss": 0.8388, "lr": 3.6837724849572175e-06, "epoch": 0.12862655423753036, "percentage": 12.86, "elapsed_time": "0:25:06", "remaining_time": "2:50:04"}
+{"current_steps": 155, "total_steps": 1166, "loss": 1.1761, "lr": 3.6258466557191907e-06, "epoch": 0.13291410604544804, "percentage": 13.29, "elapsed_time": "0:26:10", "remaining_time": "2:50:46"}
+{"current_steps": 160, "total_steps": 1166, "loss": 1.0348, "lr": 3.5686326111603775e-06, "epoch": 0.13720165785336572, "percentage": 13.72, "elapsed_time": "0:27:03", "remaining_time": "2:50:09"}
+{"current_steps": 160, "total_steps": 1166, "eval_loss": 0.9355081915855408, "epoch": 0.13720165785336572, "percentage": 13.72, "elapsed_time": "0:27:22", "remaining_time": "2:52:09"}
+{"current_steps": 165, "total_steps": 1166, "loss": 1.0048, "lr": 3.512125077523717e-06, "epoch": 0.1414892096612834, "percentage": 14.15, "elapsed_time": "0:28:20", "remaining_time": "2:51:53"}
+{"current_steps": 170, "total_steps": 1166, "loss": 0.8126, "lr": 3.456318794141709e-06, "epoch": 0.1457767614692011, "percentage": 14.58, "elapsed_time": "0:29:04", "remaining_time": "2:50:21"}
+{"current_steps": 175, "total_steps": 1166, "loss": 0.8684, "lr": 3.4012085134690555e-06, "epoch": 0.15006431327711878, "percentage": 15.01, "elapsed_time": "0:29:51", "remaining_time": "2:49:07"}
+{"current_steps": 180, "total_steps": 1166, "loss": 1.023, "lr": 3.346789001115556e-06, "epoch": 0.15435186508503645, "percentage": 15.44, "elapsed_time": "0:30:46", "remaining_time": "2:48:34"}
+{"current_steps": 185, "total_steps": 1166, "loss": 0.979, "lr": 3.293055035879266e-06, "epoch": 0.15863941689295413, "percentage": 15.87, "elapsed_time": "0:31:36", "remaining_time": "2:47:35"}
+{"current_steps": 190, "total_steps": 1166, "loss": 0.9414, "lr": 3.2400014097798766e-06, "epoch": 0.1629269687008718, "percentage": 16.3, "elapsed_time": "0:32:25", "remaining_time": "2:46:33"}
+{"current_steps": 195, "total_steps": 1166, "loss": 1.0719, "lr": 3.187622928092377e-06, "epoch": 0.1672145205087895, "percentage": 16.72, "elapsed_time": "0:33:22", "remaining_time": "2:46:13"}
+{"current_steps": 200, "total_steps": 1166, "loss": 0.9007, "lr": 3.1359144093809653e-06, "epoch": 0.17150207231670717, "percentage": 17.15, "elapsed_time": "0:34:09", "remaining_time": "2:45:00"}
+{"current_steps": 205, "total_steps": 1166, "loss": 1.0225, "lr": 3.084870685533213e-06, "epoch": 0.17578962412462484, "percentage": 17.58, "elapsed_time": "0:34:55", "remaining_time": "2:43:43"}
+{"current_steps": 210, "total_steps": 1166, "loss": 0.8927, "lr": 3.034486601794506e-06, "epoch": 0.18007717593254252, "percentage": 18.01, "elapsed_time": "0:35:47", "remaining_time": "2:42:57"}
+{"current_steps": 215, "total_steps": 1166, "loss": 0.8904, "lr": 2.984757016802754e-06, "epoch": 0.1843647277404602, "percentage": 18.44, "elapsed_time": "0:36:39", "remaining_time": "2:42:10"}
+{"current_steps": 220, "total_steps": 1166, "loss": 0.89, "lr": 2.935676802623359e-06, "epoch": 0.18865227954837788, "percentage": 18.87, "elapsed_time": "0:37:28", "remaining_time": "2:41:08"}
+{"current_steps": 225, "total_steps": 1166, "loss": 1.0528, "lr": 2.887240844784472e-06, "epoch": 0.19293983135629555, "percentage": 19.3, "elapsed_time": "0:38:40", "remaining_time": "2:41:45"}
+{"current_steps": 230, "total_steps": 1166, "loss": 0.957, "lr": 2.8394440423125295e-06, "epoch": 0.19722738316421323, "percentage": 19.73, "elapsed_time": "0:39:26", "remaining_time": "2:40:28"}
+{"current_steps": 235, "total_steps": 1166, "loss": 0.8757, "lr": 2.7922813077680564e-06, "epoch": 0.2015149349721309, "percentage": 20.15, "elapsed_time": "0:40:15", "remaining_time": "2:39:29"}
+{"current_steps": 240, "total_steps": 1166, "loss": 0.7212, "lr": 2.7457475672817817e-06, "epoch": 0.2058024867800486, "percentage": 20.58, "elapsed_time": "0:40:57", "remaining_time": "2:38:00"}
+{"current_steps": 240, "total_steps": 1166, "eval_loss": 0.9225141406059265, "epoch": 0.2058024867800486, "percentage": 20.58, "elapsed_time": "0:41:16", "remaining_time": "2:39:14"}
+{"current_steps": 245, "total_steps": 1166, "loss": 0.7847, "lr": 2.6998377605910153e-06, "epoch": 0.21009003858796627, "percentage": 21.01, "elapsed_time": "0:42:01", "remaining_time": "2:37:59"}
+{"current_steps": 250, "total_steps": 1166, "loss": 0.7885, "lr": 2.6545468410763466e-06, "epoch": 0.21437759039588394, "percentage": 21.44, "elapsed_time": "0:42:40", "remaining_time": "2:36:23"}
+{"current_steps": 255, "total_steps": 1166, "loss": 0.9853, "lr": 2.60986977579862e-06, "epoch": 0.21866514220380162, "percentage": 21.87, "elapsed_time": "0:43:35", "remaining_time": "2:35:44"}
+{"current_steps": 260, "total_steps": 1166, "loss": 0.8693, "lr": 2.565801545536224e-06, "epoch": 0.2229526940117193, "percentage": 22.3, "elapsed_time": "0:44:22", "remaining_time": "2:34:36"}
+{"current_steps": 265, "total_steps": 1166, "loss": 0.8483, "lr": 2.52233714482269e-06, "epoch": 0.22724024581963698, "percentage": 22.73, "elapsed_time": "0:45:14", "remaining_time": "2:33:48"}
+{"current_steps": 270, "total_steps": 1166, "loss": 0.9198, "lr": 2.479471581984588e-06, "epoch": 0.23152779762755465, "percentage": 23.16, "elapsed_time": "0:46:01", "remaining_time": "2:32:43"}
+{"current_steps": 275, "total_steps": 1166, "loss": 0.8111, "lr": 2.437199879179748e-06, "epoch": 0.23581534943547233, "percentage": 23.58, "elapsed_time": "0:46:40", "remaining_time": "2:31:13"}
+{"current_steps": 280, "total_steps": 1166, "loss": 0.9249, "lr": 2.395517072435804e-06, "epoch": 0.24010290124339004, "percentage": 24.01, "elapsed_time": "0:47:31", "remaining_time": "2:30:23"}
+{"current_steps": 285, "total_steps": 1166, "loss": 0.8466, "lr": 2.35441821168905e-06, "epoch": 0.24439045305130772, "percentage": 24.44, "elapsed_time": "0:48:10", "remaining_time": "2:28:56"}
+{"current_steps": 290, "total_steps": 1166, "loss": 0.8335, "lr": 2.313898360823632e-06, "epoch": 0.2486780048592254, "percentage": 24.87, "elapsed_time": "0:48:59", "remaining_time": "2:27:59"}
+{"current_steps": 295, "total_steps": 1166, "loss": 0.9591, "lr": 2.2739525977110787e-06, "epoch": 0.25296555666714304, "percentage": 25.3, "elapsed_time": "0:50:02", "remaining_time": "2:27:45"}
+{"current_steps": 300, "total_steps": 1166, "loss": 0.8867, "lr": 2.234576014250154e-06, "epoch": 0.2572531084750607, "percentage": 25.73, "elapsed_time": "0:50:51", "remaining_time": "2:26:49"}
+{"current_steps": 305, "total_steps": 1166, "loss": 0.9301, "lr": 2.195763716407068e-06, "epoch": 0.2615406602829784, "percentage": 26.16, "elapsed_time": "0:51:36", "remaining_time": "2:25:40"}
+{"current_steps": 310, "total_steps": 1166, "loss": 0.8933, "lr": 2.15751082425603e-06, "epoch": 0.2658282120908961, "percentage": 26.59, "elapsed_time": "0:52:17", "remaining_time": "2:24:24"}
+{"current_steps": 315, "total_steps": 1166, "loss": 1.1902, "lr": 2.119812472020151e-06, "epoch": 0.27011576389881375, "percentage": 27.02, "elapsed_time": "0:53:17", "remaining_time": "2:23:59"}
+{"current_steps": 320, "total_steps": 1166, "loss": 0.8077, "lr": 2.082663808112706e-06, "epoch": 0.27440331570673143, "percentage": 27.44, "elapsed_time": "0:54:05", "remaining_time": "2:22:58"}
+{"current_steps": 320, "total_steps": 1166, "eval_loss": 0.9141628742218018, "epoch": 0.27440331570673143, "percentage": 27.44, "elapsed_time": "0:54:24", "remaining_time": "2:23:49"}
+{"current_steps": 325, "total_steps": 1166, "loss": 1.003, "lr": 2.0460599951787676e-06, "epoch": 0.2786908675146491, "percentage": 27.87, "elapsed_time": "0:55:22", "remaining_time": "2:23:18"}
+{"current_steps": 330, "total_steps": 1166, "loss": 0.9517, "lr": 2.0099962101371912e-06, "epoch": 0.2829784193225668, "percentage": 28.3, "elapsed_time": "0:56:11", "remaining_time": "2:22:21"}
+{"current_steps": 335, "total_steps": 1166, "loss": 0.8129, "lr": 1.9744676442229893e-06, "epoch": 0.2872659711304845, "percentage": 28.73, "elapsed_time": "0:56:57", "remaining_time": "2:21:17"}
+{"current_steps": 340, "total_steps": 1166, "loss": 0.9616, "lr": 1.9394695030300814e-06, "epoch": 0.2915535229384022, "percentage": 29.16, "elapsed_time": "0:57:57", "remaining_time": "2:20:48"}
+{"current_steps": 345, "total_steps": 1166, "loss": 0.9347, "lr": 1.904997006554424e-06, "epoch": 0.2958410747463199, "percentage": 29.59, "elapsed_time": "0:58:49", "remaining_time": "2:20:00"}
+{"current_steps": 350, "total_steps": 1166, "loss": 0.9365, "lr": 1.8710453892375372e-06, "epoch": 0.30012862655423755, "percentage": 30.02, "elapsed_time": "0:59:43", "remaining_time": "2:19:14"}
+{"current_steps": 355, "total_steps": 1166, "loss": 1.0678, "lr": 1.837609900010423e-06, "epoch": 0.30441617836215523, "percentage": 30.45, "elapsed_time": "1:00:47", "remaining_time": "2:18:51"}
+{"current_steps": 360, "total_steps": 1166, "loss": 0.8233, "lr": 1.8046858023378982e-06, "epoch": 0.3087037301700729, "percentage": 30.87, "elapsed_time": "1:01:34", "remaining_time": "2:17:52"}
+{"current_steps": 365, "total_steps": 1166, "loss": 1.089, "lr": 1.7722683742633203e-06, "epoch": 0.3129912819779906, "percentage": 31.3, "elapsed_time": "1:02:38", "remaining_time": "2:17:27"}
+{"current_steps": 370, "total_steps": 1166, "loss": 0.8982, "lr": 1.7403529084537394e-06, "epoch": 0.31727883378590827, "percentage": 31.73, "elapsed_time": "1:03:25", "remaining_time": "2:16:26"}
+{"current_steps": 375, "total_steps": 1166, "loss": 0.8602, "lr": 1.708934712245474e-06, "epoch": 0.32156638559382594, "percentage": 32.16, "elapsed_time": "1:04:15", "remaining_time": "2:15:33"}
+{"current_steps": 380, "total_steps": 1166, "loss": 0.9206, "lr": 1.6780091076901074e-06, "epoch": 0.3258539374017436, "percentage": 32.59, "elapsed_time": "1:05:04", "remaining_time": "2:14:36"}
+{"current_steps": 385, "total_steps": 1166, "loss": 0.9, "lr": 1.6475714316009228e-06, "epoch": 0.3301414892096613, "percentage": 33.02, "elapsed_time": "1:06:07", "remaining_time": "2:14:08"}
+{"current_steps": 390, "total_steps": 1166, "loss": 0.9077, "lr": 1.6176170355997885e-06, "epoch": 0.334429041017579, "percentage": 33.45, "elapsed_time": "1:07:05", "remaining_time": "2:13:29"}
+{"current_steps": 395, "total_steps": 1166, "loss": 0.8796, "lr": 1.5881412861644783e-06, "epoch": 0.33871659282549665, "percentage": 33.88, "elapsed_time": "1:07:56", "remaining_time": "2:12:37"}
+{"current_steps": 400, "total_steps": 1166, "loss": 0.8442, "lr": 1.559139564676459e-06, "epoch": 0.34300414463341433, "percentage": 34.31, "elapsed_time": "1:08:51", "remaining_time": "2:11:52"}
+{"current_steps": 400, "total_steps": 1166, "eval_loss": 0.9068123698234558, "epoch": 0.34300414463341433, "percentage": 34.31, "elapsed_time": "1:09:11", "remaining_time": "2:12:29"}
+{"current_steps": 405, "total_steps": 1166, "loss": 0.8776, "lr": 1.530607267469142e-06, "epoch": 0.347291696441332, "percentage": 34.73, "elapsed_time": "1:09:59", "remaining_time": "2:11:30"}
+{"current_steps": 410, "total_steps": 1166, "loss": 0.8368, "lr": 1.502539805876598e-06, "epoch": 0.3515792482492497, "percentage": 35.16, "elapsed_time": "1:10:55", "remaining_time": "2:10:46"}
+{"current_steps": 415, "total_steps": 1166, "loss": 0.8314, "lr": 1.4749326062827624e-06, "epoch": 0.35586680005716737, "percentage": 35.59, "elapsed_time": "1:11:50", "remaining_time": "2:10:01"}
+{"current_steps": 420, "total_steps": 1166, "loss": 0.8639, "lr": 1.447781110171118e-06, "epoch": 0.36015435186508504, "percentage": 36.02, "elapsed_time": "1:12:45", "remaining_time": "2:09:13"}
+{"current_steps": 425, "total_steps": 1166, "loss": 0.8738, "lr": 1.421080774174884e-06, "epoch": 0.3644419036730027, "percentage": 36.45, "elapsed_time": "1:13:45", "remaining_time": "2:08:36"}
+{"current_steps": 430, "total_steps": 1166, "loss": 0.8124, "lr": 1.3948270701276901e-06, "epoch": 0.3687294554809204, "percentage": 36.88, "elapsed_time": "1:14:27", "remaining_time": "2:07:27"}
+{"current_steps": 435, "total_steps": 1166, "loss": 0.8018, "lr": 1.3690154851147892e-06, "epoch": 0.3730170072888381, "percentage": 37.31, "elapsed_time": "1:15:19", "remaining_time": "2:06:34"}
+{"current_steps": 440, "total_steps": 1166, "loss": 0.7621, "lr": 1.3436415215247681e-06, "epoch": 0.37730455909675575, "percentage": 37.74, "elapsed_time": "1:16:10", "remaining_time": "2:05:41"}
+{"current_steps": 445, "total_steps": 1166, "loss": 0.9082, "lr": 1.3187006971017973e-06, "epoch": 0.38159211090467343, "percentage": 38.16, "elapsed_time": "1:17:11", "remaining_time": "2:05:04"}
+{"current_steps": 450, "total_steps": 1166, "loss": 0.8821, "lr": 1.2941885449984206e-06, "epoch": 0.3858796627125911, "percentage": 38.59, "elapsed_time": "1:18:09", "remaining_time": "2:04:21"}
+{"current_steps": 455, "total_steps": 1166, "loss": 0.9639, "lr": 1.2701006138288915e-06, "epoch": 0.3901672145205088, "percentage": 39.02, "elapsed_time": "1:19:02", "remaining_time": "2:03:30"}
+{"current_steps": 460, "total_steps": 1166, "loss": 0.9052, "lr": 1.2464324677230652e-06, "epoch": 0.39445476632842646, "percentage": 39.45, "elapsed_time": "1:19:59", "remaining_time": "2:02:46"}
+{"current_steps": 465, "total_steps": 1166, "loss": 0.8723, "lr": 1.22317968638086e-06, "epoch": 0.39874231813634414, "percentage": 39.88, "elapsed_time": "1:20:54", "remaining_time": "2:01:58"}
+{"current_steps": 470, "total_steps": 1166, "loss": 0.8457, "lr": 1.2003378651272997e-06, "epoch": 0.4030298699442618, "percentage": 40.31, "elapsed_time": "1:21:38", "remaining_time": "2:00:53"}
+{"current_steps": 475, "total_steps": 1166, "loss": 0.9502, "lr": 1.1779026149681347e-06, "epoch": 0.4073174217521795, "percentage": 40.74, "elapsed_time": "1:22:37", "remaining_time": "2:00:11"}
+{"current_steps": 480, "total_steps": 1166, "loss": 0.831, "lr": 1.155869562646071e-06, "epoch": 0.4116049735600972, "percentage": 41.17, "elapsed_time": "1:23:22", "remaining_time": "1:59:08"}
+{"current_steps": 480, "total_steps": 1166, "eval_loss": 0.9032189846038818, "epoch": 0.4116049735600972, "percentage": 41.17, "elapsed_time": "1:23:41", "remaining_time": "1:59:36"}
+{"current_steps": 485, "total_steps": 1166, "loss": 0.8338, "lr": 1.1342343506976044e-06, "epoch": 0.41589252536801485, "percentage": 41.6, "elapsed_time": "1:24:37", "remaining_time": "1:58:48"}
+{"current_steps": 490, "total_steps": 1166, "loss": 0.8289, "lr": 1.1129926375104734e-06, "epoch": 0.42018007717593253, "percentage": 42.02, "elapsed_time": "1:25:24", "remaining_time": "1:57:49"}
+{"current_steps": 495, "total_steps": 1166, "loss": 0.9218, "lr": 1.0921400973817452e-06, "epoch": 0.4244676289838502, "percentage": 42.45, "elapsed_time": "1:26:29", "remaining_time": "1:57:14"}
+{"current_steps": 500, "total_steps": 1166, "loss": 0.8467, "lr": 1.071672420576549e-06, "epoch": 0.4287551807917679, "percentage": 42.88, "elapsed_time": "1:27:30", "remaining_time": "1:56:33"}
+{"current_steps": 505, "total_steps": 1166, "loss": 0.8871, "lr": 1.051585313387455e-06, "epoch": 0.43304273259968556, "percentage": 43.31, "elapsed_time": "1:28:29", "remaining_time": "1:55:50"}
+{"current_steps": 510, "total_steps": 1166, "loss": 1.1172, "lr": 1.0318744981945303e-06, "epoch": 0.43733028440760324, "percentage": 43.74, "elapsed_time": "1:29:36", "remaining_time": "1:55:15"}
+{"current_steps": 515, "total_steps": 1166, "loss": 1.0281, "lr": 1.0125357135260713e-06, "epoch": 0.4416178362155209, "percentage": 44.17, "elapsed_time": "1:30:28", "remaining_time": "1:54:21"}
+{"current_steps": 520, "total_steps": 1166, "loss": 0.9027, "lr": 9.93564714120029e-07, "epoch": 0.4459053880234386, "percentage": 44.6, "elapsed_time": "1:31:33", "remaining_time": "1:53:44"}
+{"current_steps": 525, "total_steps": 1166, "loss": 0.8424, "lr": 9.749572709861371e-07, "epoch": 0.4501929398313563, "percentage": 45.03, "elapsed_time": "1:32:21", "remaining_time": "1:52:46"}
+{"current_steps": 530, "total_steps": 1166, "loss": 1.0317, "lr": 9.5670917146877e-07, "epoch": 0.45448049163927395, "percentage": 45.45, "elapsed_time": "1:33:29", "remaining_time": "1:52:11"}
+{"current_steps": 535, "total_steps": 1166, "loss": 0.9455, "lr": 9.38816219310525e-07, "epoch": 0.45876804344719163, "percentage": 45.88, "elapsed_time": "1:34:42", "remaining_time": "1:51:42"}
+{"current_steps": 540, "total_steps": 1166, "loss": 0.914, "lr": 9.212742347165562e-07, "epoch": 0.4630555952551093, "percentage": 46.31, "elapsed_time": "1:35:34", "remaining_time": "1:50:47"}
+{"current_steps": 545, "total_steps": 1166, "loss": 0.8507, "lr": 9.040790544196722e-07, "epoch": 0.467343147063027, "percentage": 46.74, "elapsed_time": "1:36:37", "remaining_time": "1:50:06"}
+{"current_steps": 550, "total_steps": 1166, "loss": 0.7923, "lr": 8.872265317462145e-07, "epoch": 0.47163069887094466, "percentage": 47.17, "elapsed_time": "1:37:32", "remaining_time": "1:49:14"}
+{"current_steps": 555, "total_steps": 1166, "loss": 0.8219, "lr": 8.707125366827236e-07, "epoch": 0.47591825067886234, "percentage": 47.6, "elapsed_time": "1:38:31", "remaining_time": "1:48:28"}
+{"current_steps": 560, "total_steps": 1166, "loss": 0.9696, "lr": 8.54532955943421e-07, "epoch": 0.4802058024867801, "percentage": 48.03, "elapsed_time": "1:39:36", "remaining_time": "1:47:47"}
+{"current_steps": 560, "total_steps": 1166, "eval_loss": 0.8974508047103882, "epoch": 0.4802058024867801, "percentage": 48.03, "elapsed_time": "1:39:55", "remaining_time": "1:48:07"}
+{"current_steps": 565, "total_steps": 1166, "loss": 0.8421, "lr": 8.386836930385165e-07, "epoch": 0.48449335429469775, "percentage": 48.46, "elapsed_time": "1:40:50", "remaining_time": "1:47:15"}
+{"current_steps": 570, "total_steps": 1166, "loss": 0.8295, "lr": 8.231606683433569e-07, "epoch": 0.48878090610261543, "percentage": 48.89, "elapsed_time": "1:41:47", "remaining_time": "1:46:25"}
+{"current_steps": 575, "total_steps": 1166, "loss": 0.8803, "lr": 8.079598191684382e-07, "epoch": 0.4930684579105331, "percentage": 49.31, "elapsed_time": "1:42:47", "remaining_time": "1:45:39"}
+{"current_steps": 580, "total_steps": 1166, "loss": 0.8343, "lr": 7.930770998302978e-07, "epoch": 0.4973560097184508, "percentage": 49.74, "elapsed_time": "1:43:59", "remaining_time": "1:45:03"}
+{"current_steps": 585, "total_steps": 1166, "loss": 0.8736, "lr": 7.785084817233009e-07, "epoch": 0.5016435615263685, "percentage": 50.17, "elapsed_time": "1:44:55", "remaining_time": "1:44:12"}
+{"current_steps": 590, "total_steps": 1166, "loss": 0.8449, "lr": 7.642499533923466e-07, "epoch": 0.5059311133342861, "percentage": 50.6, "elapsed_time": "1:45:53", "remaining_time": "1:43:22"}
+{"current_steps": 595, "total_steps": 1166, "loss": 0.9765, "lr": 7.502975206065118e-07, "epoch": 0.5102186651422038, "percentage": 51.03, "elapsed_time": "1:46:53", "remaining_time": "1:42:34"}
+{"current_steps": 600, "total_steps": 1166, "loss": 1.041, "lr": 7.366472064336485e-07, "epoch": 0.5145062169501214, "percentage": 51.46, "elapsed_time": "1:48:06", "remaining_time": "1:41:58"}
+{"current_steps": 605, "total_steps": 1166, "loss": 0.7932, "lr": 7.232950513159591e-07, "epoch": 0.5187937687580392, "percentage": 51.89, "elapsed_time": "1:48:59", "remaining_time": "1:41:03"}
+{"current_steps": 610, "total_steps": 1166, "loss": 0.8704, "lr": 7.102371131465766e-07, "epoch": 0.5230813205659568, "percentage": 52.32, "elapsed_time": "1:50:03", "remaining_time": "1:40:18"}
+{"current_steps": 615, "total_steps": 1166, "loss": 0.8656, "lr": 6.974694673471581e-07, "epoch": 0.5273688723738745, "percentage": 52.74, "elapsed_time": "1:50:59", "remaining_time": "1:39:26"}
+{"current_steps": 620, "total_steps": 1166, "loss": 0.8775, "lr": 6.849882069465297e-07, "epoch": 0.5316564241817922, "percentage": 53.17, "elapsed_time": "1:52:04", "remaining_time": "1:38:41"}
+{"current_steps": 625, "total_steps": 1166, "loss": 0.9558, "lr": 6.727894426603947e-07, "epoch": 0.5359439759897099, "percentage": 53.6, "elapsed_time": "1:52:59", "remaining_time": "1:37:47"}
+{"current_steps": 630, "total_steps": 1166, "loss": 1.0649, "lr": 6.608693029721375e-07, "epoch": 0.5402315277976275, "percentage": 54.03, "elapsed_time": "1:54:09", "remaining_time": "1:37:07"}
+{"current_steps": 635, "total_steps": 1166, "loss": 0.9116, "lr": 6.492239342147439e-07, "epoch": 0.5445190796055452, "percentage": 54.46, "elapsed_time": "1:55:08", "remaining_time": "1:36:17"}
+{"current_steps": 640, "total_steps": 1166, "loss": 0.9949, "lr": 6.378495006538639e-07, "epoch": 0.5488066314134629, "percentage": 54.89, "elapsed_time": "1:56:12", "remaining_time": "1:35:30"}
+{"current_steps": 640, "total_steps": 1166, "eval_loss": 0.8972450494766235, "epoch": 0.5488066314134629, "percentage": 54.89, "elapsed_time": "1:56:31", "remaining_time": "1:35:46"}
+{"current_steps": 645, "total_steps": 1166, "loss": 0.9208, "lr": 6.267421845720492e-07, "epoch": 0.5530941832213806, "percentage": 55.32, "elapsed_time": "1:57:26", "remaining_time": "1:34:52"}
+{"current_steps": 650, "total_steps": 1166, "loss": 0.8782, "lr": 6.158981863541822e-07, "epoch": 0.5573817350292982, "percentage": 55.75, "elapsed_time": "1:58:17", "remaining_time": "1:33:54"}
+{"current_steps": 655, "total_steps": 1166, "loss": 0.8848, "lr": 6.053137245741388e-07, "epoch": 0.561669286837216, "percentage": 56.17, "elapsed_time": "1:59:23", "remaining_time": "1:33:08"}
+{"current_steps": 660, "total_steps": 1166, "loss": 0.8214, "lr": 5.949850360827048e-07, "epoch": 0.5659568386451336, "percentage": 56.6, "elapsed_time": "2:00:24", "remaining_time": "1:32:18"}
+{"current_steps": 665, "total_steps": 1166, "loss": 0.9232, "lr": 5.849083760967786e-07, "epoch": 0.5702443904530513, "percentage": 57.03, "elapsed_time": "2:01:30", "remaining_time": "1:31:32"}
+{"current_steps": 670, "total_steps": 1166, "loss": 0.9599, "lr": 5.750800182898949e-07, "epoch": 0.574531942260969, "percentage": 57.46, "elapsed_time": "2:02:29", "remaining_time": "1:30:41"}
+{"current_steps": 675, "total_steps": 1166, "loss": 0.957, "lr": 5.654962548840998e-07, "epoch": 0.5788194940688867, "percentage": 57.89, "elapsed_time": "2:03:33", "remaining_time": "1:29:52"}
+{"current_steps": 680, "total_steps": 1166, "loss": 0.8544, "lr": 5.561533967432111e-07, "epoch": 0.5831070458768044, "percentage": 58.32, "elapsed_time": "2:04:32", "remaining_time": "1:29:00"}
+{"current_steps": 685, "total_steps": 1166, "loss": 0.9022, "lr": 5.470477734675006e-07, "epoch": 0.587394597684722, "percentage": 58.75, "elapsed_time": "2:05:30", "remaining_time": "1:28:07"}
+{"current_steps": 690, "total_steps": 1166, "loss": 0.8607, "lr": 5.381757334898326e-07, "epoch": 0.5916821494926398, "percentage": 59.18, "elapsed_time": "2:06:21", "remaining_time": "1:27:10"}
+{"current_steps": 695, "total_steps": 1166, "loss": 0.9483, "lr": 5.295336441732995e-07, "epoch": 0.5959697013005574, "percentage": 59.61, "elapsed_time": "2:07:18", "remaining_time": "1:26:16"}
+{"current_steps": 700, "total_steps": 1166, "loss": 0.8484, "lr": 5.211178919103908e-07, "epoch": 0.6002572531084751, "percentage": 60.03, "elapsed_time": "2:08:20", "remaining_time": "1:25:26"}
+{"current_steps": 705, "total_steps": 1166, "loss": 0.8153, "lr": 5.129248822237369e-07, "epoch": 0.6045448049163927, "percentage": 60.46, "elapsed_time": "2:09:17", "remaining_time": "1:24:32"}
+{"current_steps": 710, "total_steps": 1166, "loss": 0.8865, "lr": 5.049510398684706e-07, "epoch": 0.6088323567243105, "percentage": 60.89, "elapsed_time": "2:10:36", "remaining_time": "1:23:53"}
+{"current_steps": 715, "total_steps": 1166, "loss": 0.8288, "lr": 4.97192808936251e-07, "epoch": 0.6131199085322281, "percentage": 61.32, "elapsed_time": "2:11:29", "remaining_time": "1:22:56"}
+{"current_steps": 720, "total_steps": 1166, "loss": 0.8154, "lr": 4.896466529609901e-07, "epoch": 0.6174074603401458, "percentage": 61.75, "elapsed_time": "2:12:28", "remaining_time": "1:22:03"}
+{"current_steps": 720, "total_steps": 1166, "eval_loss": 0.8948369026184082, "epoch": 0.6174074603401458, "percentage": 61.75, "elapsed_time": "2:12:47", "remaining_time": "1:22:15"}
+{"current_steps": 725, "total_steps": 1166, "loss": 0.8132, "lr": 4.823090550263373e-07, "epoch": 0.6216950121480634, "percentage": 62.18, "elapsed_time": "2:13:51", "remaining_time": "1:21:25"}
+{"current_steps": 730, "total_steps": 1166, "loss": 0.8563, "lr": 4.7517651787496393e-07, "epoch": 0.6259825639559812, "percentage": 62.61, "elapsed_time": "2:14:57", "remaining_time": "1:20:36"}
+{"current_steps": 735, "total_steps": 1166, "loss": 0.83, "lr": 4.682455640197012e-07, "epoch": 0.6302701157638988, "percentage": 63.04, "elapsed_time": "2:15:54", "remaining_time": "1:19:41"}
+{"current_steps": 740, "total_steps": 1166, "loss": 0.7722, "lr": 4.6151273585658703e-07, "epoch": 0.6345576675718165, "percentage": 63.46, "elapsed_time": "2:16:43", "remaining_time": "1:18:42"}
+{"current_steps": 745, "total_steps": 1166, "loss": 0.9013, "lr": 4.549745957798709e-07, "epoch": 0.6388452193797342, "percentage": 63.89, "elapsed_time": "2:17:42", "remaining_time": "1:17:49"}
+{"current_steps": 750, "total_steps": 1166, "loss": 0.8061, "lr": 4.486277262990414e-07, "epoch": 0.6431327711876519, "percentage": 64.32, "elapsed_time": "2:19:00", "remaining_time": "1:17:05"}
+{"current_steps": 755, "total_steps": 1166, "loss": 0.8018, "lr": 4.424687301579312e-07, "epoch": 0.6474203229955695, "percentage": 64.75, "elapsed_time": "2:19:56", "remaining_time": "1:16:11"}
+{"current_steps": 760, "total_steps": 1166, "loss": 0.97, "lr": 4.364942304559619e-07, "epoch": 0.6517078748034872, "percentage": 65.18, "elapsed_time": "2:21:15", "remaining_time": "1:15:27"}
+{"current_steps": 765, "total_steps": 1166, "loss": 0.8424, "lr": 4.307008707715972e-07, "epoch": 0.6559954266114049, "percentage": 65.61, "elapsed_time": "2:22:13", "remaining_time": "1:14:33"}
+{"current_steps": 770, "total_steps": 1166, "loss": 0.9495, "lr": 4.250853152880694e-07, "epoch": 0.6602829784193226, "percentage": 66.04, "elapsed_time": "2:23:09", "remaining_time": "1:13:37"}
+{"current_steps": 775, "total_steps": 1166, "loss": 0.9217, "lr": 4.1964424892144836e-07, "epoch": 0.6645705302272402, "percentage": 66.47, "elapsed_time": "2:24:29", "remaining_time": "1:12:53"}
+{"current_steps": 780, "total_steps": 1166, "loss": 0.7872, "lr": 4.143743774511321e-07, "epoch": 0.668858082035158, "percentage": 66.9, "elapsed_time": "2:25:23", "remaining_time": "1:11:57"}
+{"current_steps": 785, "total_steps": 1166, "loss": 0.9516, "lr": 4.0927242765282987e-07, "epoch": 0.6731456338430756, "percentage": 67.32, "elapsed_time": "2:26:12", "remaining_time": "1:10:57"}
+{"current_steps": 790, "total_steps": 1166, "loss": 0.918, "lr": 4.043351474341226e-07, "epoch": 0.6774331856509933, "percentage": 67.75, "elapsed_time": "2:27:15", "remaining_time": "1:10:05"}
+{"current_steps": 795, "total_steps": 1166, "loss": 0.8869, "lr": 3.995593059726841e-07, "epoch": 0.6817207374589109, "percentage": 68.18, "elapsed_time": "2:28:18", "remaining_time": "1:09:12"}
+{"current_steps": 800, "total_steps": 1166, "loss": 0.9682, "lr": 3.9494169385724855e-07, "epoch": 0.6860082892668287, "percentage": 68.61, "elapsed_time": "2:29:28", "remaining_time": "1:08:22"}
+{"current_steps": 800, "total_steps": 1166, "eval_loss": 0.8931262493133545, "epoch": 0.6860082892668287, "percentage": 68.61, "elapsed_time": "2:29:47", "remaining_time": "1:08:31"}
+{"current_steps": 805, "total_steps": 1166, "loss": 0.9497, "lr": 3.904791232314207e-07, "epoch": 0.6902958410747463, "percentage": 69.04, "elapsed_time": "2:30:38", "remaining_time": "1:07:33"}
+{"current_steps": 810, "total_steps": 1166, "loss": 0.9616, "lr": 3.861684279404229e-07, "epoch": 0.694583392882664, "percentage": 69.47, "elapsed_time": "2:31:25", "remaining_time": "1:06:33"}
+{"current_steps": 815, "total_steps": 1166, "loss": 1.0817, "lr": 3.820064636808802e-07, "epoch": 0.6988709446905816, "percentage": 69.9, "elapsed_time": "2:32:39", "remaining_time": "1:05:44"}
+{"current_steps": 820, "total_steps": 1166, "loss": 0.9003, "lr": 3.7799010815375107e-07, "epoch": 0.7031584964984994, "percentage": 70.33, "elapsed_time": "2:33:37", "remaining_time": "1:04:49"}
+{"current_steps": 825, "total_steps": 1166, "loss": 1.1193, "lr": 3.741162612205157e-07, "epoch": 0.707446048306417, "percentage": 70.75, "elapsed_time": "2:35:01", "remaining_time": "1:04:04"}
+{"current_steps": 830, "total_steps": 1166, "loss": 0.8603, "lr": 3.703818450627364e-07, "epoch": 0.7117336001143347, "percentage": 71.18, "elapsed_time": "2:36:10", "remaining_time": "1:03:13"}
+{"current_steps": 835, "total_steps": 1166, "loss": 1.012, "lr": 3.6678380434511737e-07, "epoch": 0.7160211519222524, "percentage": 71.61, "elapsed_time": "2:37:15", "remaining_time": "1:02:20"}
+{"current_steps": 840, "total_steps": 1166, "loss": 1.0174, "lr": 3.6331910638219e-07, "epoch": 0.7203087037301701, "percentage": 72.04, "elapsed_time": "2:38:41", "remaining_time": "1:01:35"}
+{"current_steps": 845, "total_steps": 1166, "loss": 0.982, "lr": 3.5998474130876195e-07, "epoch": 0.7245962555380877, "percentage": 72.47, "elapsed_time": "2:40:02", "remaining_time": "1:00:47"}
+{"current_steps": 850, "total_steps": 1166, "loss": 0.9954, "lr": 3.567777222542744e-07, "epoch": 0.7288838073460054, "percentage": 72.9, "elapsed_time": "2:41:13", "remaining_time": "0:59:56"}
+{"current_steps": 855, "total_steps": 1166, "loss": 0.9349, "lr": 3.536950855212165e-07, "epoch": 0.7331713591539231, "percentage": 73.33, "elapsed_time": "2:42:26", "remaining_time": "0:59:05"}
+{"current_steps": 860, "total_steps": 1166, "loss": 1.1525, "lr": 3.5073389076775976e-07, "epoch": 0.7374589109618408, "percentage": 73.76, "elapsed_time": "2:43:46", "remaining_time": "0:58:16"}
+{"current_steps": 865, "total_steps": 1166, "loss": 1.0404, "lr": 3.4789122119478064e-07, "epoch": 0.7417464627697584, "percentage": 74.19, "elapsed_time": "2:45:22", "remaining_time": "0:57:32"}
+{"current_steps": 870, "total_steps": 1166, "loss": 1.1018, "lr": 3.451641837374477e-07, "epoch": 0.7460340145776762, "percentage": 74.61, "elapsed_time": "2:46:35", "remaining_time": "0:56:40"}
+{"current_steps": 875, "total_steps": 1166, "loss": 1.0088, "lr": 3.425499092615662e-07, "epoch": 0.7503215663855938, "percentage": 75.04, "elapsed_time": "2:47:48", "remaining_time": "0:55:48"}
+{"current_steps": 880, "total_steps": 1166, "loss": 0.9491, "lr": 3.4004555276487614e-07, "epoch": 0.7546091181935115, "percentage": 75.47, "elapsed_time": "2:48:58", "remaining_time": "0:54:54"}
+{"current_steps": 880, "total_steps": 1166, "eval_loss": 0.9030270576477051, "epoch": 0.7546091181935115, "percentage": 75.47, "elapsed_time": "2:49:17", "remaining_time": "0:55:01"}
+{"current_steps": 885, "total_steps": 1166, "loss": 1.0566, "lr": 3.376482935835186e-07, "epoch": 0.7588966700014291, "percentage": 75.9, "elapsed_time": "2:50:37", "remaining_time": "0:54:10"}
+{"current_steps": 890, "total_steps": 1166, "loss": 1.0203, "lr": 3.3535533560389486e-07, "epoch": 0.7631842218093469, "percentage": 76.33, "elapsed_time": "2:51:48", "remaining_time": "0:53:16"}
+{"current_steps": 895, "total_steps": 1166, "loss": 0.9489, "lr": 3.331639074801548e-07, "epoch": 0.7674717736172646, "percentage": 76.76, "elapsed_time": "2:53:01", "remaining_time": "0:52:23"}
+{"current_steps": 900, "total_steps": 1166, "loss": 0.9057, "lr": 3.3107126285757256e-07, "epoch": 0.7717593254251822, "percentage": 77.19, "elapsed_time": "2:54:08", "remaining_time": "0:51:27"}
+{"current_steps": 905, "total_steps": 1166, "loss": 0.9441, "lr": 3.290746806020766e-07, "epoch": 0.7760468772331, "percentage": 77.62, "elapsed_time": "2:55:29", "remaining_time": "0:50:36"}
+{"current_steps": 910, "total_steps": 1166, "loss": 1.0213, "lr": 3.271714650362233e-07, "epoch": 0.7803344290410176, "percentage": 78.04, "elapsed_time": "2:56:53", "remaining_time": "0:49:45"}
+{"current_steps": 915, "total_steps": 1166, "loss": 0.9689, "lr": 3.2535894618192186e-07, "epoch": 0.7846219808489353, "percentage": 78.47, "elapsed_time": "2:58:06", "remaining_time": "0:48:51"}
+{"current_steps": 920, "total_steps": 1166, "loss": 0.8944, "lr": 3.236344800102375e-07, "epoch": 0.7889095326568529, "percentage": 78.9, "elapsed_time": "2:59:10", "remaining_time": "0:47:54"}
+{"current_steps": 925, "total_steps": 1166, "loss": 1.0624, "lr": 3.2199544869862547e-07, "epoch": 0.7931970844647707, "percentage": 79.33, "elapsed_time": "3:00:41", "remaining_time": "0:47:04"}
+{"current_steps": 930, "total_steps": 1166, "loss": 0.9327, "lr": 3.204392608959703e-07, "epoch": 0.7974846362726883, "percentage": 79.76, "elapsed_time": "3:02:13", "remaining_time": "0:46:14"}
+{"current_steps": 935, "total_steps": 1166, "loss": 0.9159, "lr": 3.1896335199583363e-07, "epoch": 0.801772188080606, "percentage": 80.19, "elapsed_time": "3:03:43", "remaining_time": "0:45:23"}
+{"current_steps": 940, "total_steps": 1166, "loss": 1.0248, "lr": 3.1756518441834397e-07, "epoch": 0.8060597398885236, "percentage": 80.62, "elapsed_time": "3:05:00", "remaining_time": "0:44:28"}
+{"current_steps": 945, "total_steps": 1166, "loss": 1.0413, "lr": 3.151927901941027e-07, "epoch": 0.8103472916964414, "percentage": 81.05, "elapsed_time": "3:06:14", "remaining_time": "0:43:33"}
+{"current_steps": 950, "total_steps": 1166, "loss": 1.1134, "lr": 3.1032417503134016e-07, "epoch": 0.814634843504359, "percentage": 81.48, "elapsed_time": "3:07:45", "remaining_time": "0:42:41"}
+{"current_steps": 955, "total_steps": 1166, "loss": 0.9336, "lr": 3.054555598685777e-07, "epoch": 0.8189223953122767, "percentage": 81.9, "elapsed_time": "3:08:54", "remaining_time": "0:41:44"}
+{"current_steps": 960, "total_steps": 1166, "loss": 1.068, "lr": 3.0058694470581514e-07, "epoch": 0.8232099471201944, "percentage": 82.33, "elapsed_time": "3:10:21", "remaining_time": "0:40:50"}
+{"current_steps": 960, "total_steps": 1166, "eval_loss": 0.9022178053855896, "epoch": 0.8232099471201944, "percentage": 82.33, "elapsed_time": "3:10:40", "remaining_time": "0:40:55"}
+{"current_steps": 965, "total_steps": 1166, "loss": 1.0307, "lr": 2.9571832954305265e-07, "epoch": 0.8274974989281121, "percentage": 82.76, "elapsed_time": "3:11:48", "remaining_time": "0:39:57"}
+{"current_steps": 970, "total_steps": 1166, "loss": 0.9962, "lr": 2.9084971438029017e-07, "epoch": 0.8317850507360297, "percentage": 83.19, "elapsed_time": "3:13:17", "remaining_time": "0:39:03"}
+{"current_steps": 975, "total_steps": 1166, "loss": 1.0143, "lr": 2.8598109921752763e-07, "epoch": 0.8360726025439474, "percentage": 83.62, "elapsed_time": "3:14:40", "remaining_time": "0:38:08"}
+{"current_steps": 980, "total_steps": 1166, "loss": 0.9869, "lr": 2.8111248405476515e-07, "epoch": 0.8403601543518651, "percentage": 84.05, "elapsed_time": "3:16:10", "remaining_time": "0:37:14"}
+{"current_steps": 985, "total_steps": 1166, "loss": 1.0683, "lr": 2.7624386889200266e-07, "epoch": 0.8446477061597828, "percentage": 84.48, "elapsed_time": "3:17:17", "remaining_time": "0:36:15"}
+{"current_steps": 990, "total_steps": 1166, "loss": 0.9797, "lr": 2.713752537292401e-07, "epoch": 0.8489352579677004, "percentage": 84.91, "elapsed_time": "3:18:43", "remaining_time": "0:35:19"}
+{"current_steps": 995, "total_steps": 1166, "loss": 1.0389, "lr": 2.6650663856647764e-07, "epoch": 0.8532228097756182, "percentage": 85.33, "elapsed_time": "3:19:55", "remaining_time": "0:34:21"}
+{"current_steps": 1000, "total_steps": 1166, "loss": 1.0267, "lr": 2.616380234037151e-07, "epoch": 0.8575103615835358, "percentage": 85.76, "elapsed_time": "3:21:34", "remaining_time": "0:33:27"}
+{"current_steps": 1005, "total_steps": 1166, "loss": 0.9329, "lr": 2.567694082409526e-07, "epoch": 0.8617979133914535, "percentage": 86.19, "elapsed_time": "3:22:57", "remaining_time": "0:32:30"}
+{"current_steps": 1010, "total_steps": 1166, "loss": 0.9386, "lr": 2.5190079307819013e-07, "epoch": 0.8660854651993711, "percentage": 86.62, "elapsed_time": "3:24:16", "remaining_time": "0:31:33"}
+{"current_steps": 1015, "total_steps": 1166, "loss": 1.0709, "lr": 2.4703217791542765e-07, "epoch": 0.8703730170072889, "percentage": 87.05, "elapsed_time": "3:25:40", "remaining_time": "0:30:35"}
+{"current_steps": 1020, "total_steps": 1166, "loss": 0.8629, "lr": 2.421635627526651e-07, "epoch": 0.8746605688152065, "percentage": 87.48, "elapsed_time": "3:27:21", "remaining_time": "0:29:40"}
+{"current_steps": 1025, "total_steps": 1166, "loss": 0.9564, "lr": 2.3729494758990262e-07, "epoch": 0.8789481206231242, "percentage": 87.91, "elapsed_time": "3:28:30", "remaining_time": "0:28:40"}
+{"current_steps": 1030, "total_steps": 1166, "loss": 0.9884, "lr": 2.3242633242714014e-07, "epoch": 0.8832356724310418, "percentage": 88.34, "elapsed_time": "3:30:05", "remaining_time": "0:27:44"}
+{"current_steps": 1035, "total_steps": 1166, "loss": 1.1607, "lr": 2.275577172643776e-07, "epoch": 0.8875232242389596, "percentage": 88.77, "elapsed_time": "3:31:49", "remaining_time": "0:26:48"}
+{"current_steps": 1040, "total_steps": 1166, "loss": 1.06, "lr": 2.2268910210161506e-07, "epoch": 0.8918107760468772, "percentage": 89.19, "elapsed_time": "3:33:25", "remaining_time": "0:25:51"}
+{"current_steps": 1040, "total_steps": 1166, "eval_loss": 0.9013447761535645, "epoch": 0.8918107760468772, "percentage": 89.19, "elapsed_time": "3:33:45", "remaining_time": "0:25:53"}
+{"current_steps": 1045, "total_steps": 1166, "loss": 0.8408, "lr": 2.1782048693885258e-07, "epoch": 0.8960983278547949, "percentage": 89.62, "elapsed_time": "3:35:11", "remaining_time": "0:24:55"}
+{"current_steps": 1050, "total_steps": 1166, "loss": 0.9585, "lr": 2.129518717760901e-07, "epoch": 0.9003858796627126, "percentage": 90.05, "elapsed_time": "3:36:49", "remaining_time": "0:23:57"}
+{"current_steps": 1055, "total_steps": 1166, "loss": 1.0169, "lr": 2.0808325661332756e-07, "epoch": 0.9046734314706303, "percentage": 90.48, "elapsed_time": "3:38:15", "remaining_time": "0:22:57"}
+{"current_steps": 1060, "total_steps": 1166, "loss": 1.0411, "lr": 2.0321464145056507e-07, "epoch": 0.9089609832785479, "percentage": 90.91, "elapsed_time": "3:39:57", "remaining_time": "0:21:59"}
+{"current_steps": 1065, "total_steps": 1166, "loss": 1.0731, "lr": 1.9834602628780256e-07, "epoch": 0.9132485350864656, "percentage": 91.34, "elapsed_time": "3:41:32", "remaining_time": "0:21:00"}
+{"current_steps": 1070, "total_steps": 1166, "loss": 0.9489, "lr": 1.934774111250401e-07, "epoch": 0.9175360868943833, "percentage": 91.77, "elapsed_time": "3:42:53", "remaining_time": "0:19:59"}
+{"current_steps": 1075, "total_steps": 1166, "loss": 1.0331, "lr": 1.8860879596227757e-07, "epoch": 0.921823638702301, "percentage": 92.2, "elapsed_time": "3:44:17", "remaining_time": "0:18:59"}
+{"current_steps": 1080, "total_steps": 1166, "loss": 0.7678, "lr": 1.8374018079951505e-07, "epoch": 0.9261111905102186, "percentage": 92.62, "elapsed_time": "3:45:42", "remaining_time": "0:17:58"}
+{"current_steps": 1085, "total_steps": 1166, "loss": 1.0268, "lr": 1.788715656367526e-07, "epoch": 0.9303987423181364, "percentage": 93.05, "elapsed_time": "3:47:18", "remaining_time": "0:16:58"}
+{"current_steps": 1090, "total_steps": 1166, "loss": 1.0499, "lr": 1.7400295047399006e-07, "epoch": 0.934686294126054, "percentage": 93.48, "elapsed_time": "3:48:43", "remaining_time": "0:15:56"}
+{"current_steps": 1095, "total_steps": 1166, "loss": 0.8984, "lr": 1.6913433531122752e-07, "epoch": 0.9389738459339717, "percentage": 93.91, "elapsed_time": "3:50:07", "remaining_time": "0:14:55"}
+{"current_steps": 1100, "total_steps": 1166, "loss": 1.0244, "lr": 1.6426572014846504e-07, "epoch": 0.9432613977418893, "percentage": 94.34, "elapsed_time": "3:51:25", "remaining_time": "0:13:53"}
+{"current_steps": 1105, "total_steps": 1166, "loss": 0.8251, "lr": 1.5939710498570255e-07, "epoch": 0.9475489495498071, "percentage": 94.77, "elapsed_time": "3:52:51", "remaining_time": "0:12:51"}
+{"current_steps": 1110, "total_steps": 1166, "loss": 0.9794, "lr": 1.5452848982294004e-07, "epoch": 0.9518365013577247, "percentage": 95.2, "elapsed_time": "3:54:28", "remaining_time": "0:11:49"}
+{"current_steps": 1115, "total_steps": 1166, "loss": 0.972, "lr": 1.4965987466017753e-07, "epoch": 0.9561240531656424, "percentage": 95.63, "elapsed_time": "3:55:41", "remaining_time": "0:10:46"}
+{"current_steps": 1120, "total_steps": 1166, "loss": 0.8302, "lr": 1.4479125949741505e-07, "epoch": 0.9604116049735602, "percentage": 96.05, "elapsed_time": "3:56:41", "remaining_time": "0:09:43"}
+{"current_steps": 1120, "total_steps": 1166, "eval_loss": 0.9002277851104736, "epoch": 0.9604116049735602, "percentage": 96.05, "elapsed_time": "3:57:00", "remaining_time": "0:09:44"}
+{"current_steps": 1125, "total_steps": 1166, "loss": 0.8849, "lr": 1.3992264433465253e-07, "epoch": 0.9646991567814778, "percentage": 96.48, "elapsed_time": "3:58:27", "remaining_time": "0:08:41"}
+{"current_steps": 1130, "total_steps": 1166, "loss": 0.9591, "lr": 1.3505402917189002e-07, "epoch": 0.9689867085893955, "percentage": 96.91, "elapsed_time": "3:59:52", "remaining_time": "0:07:38"}
+{"current_steps": 1135, "total_steps": 1166, "loss": 1.0343, "lr": 1.301854140091275e-07, "epoch": 0.9732742603973131, "percentage": 97.34, "elapsed_time": "4:01:16", "remaining_time": "0:06:35"}
+{"current_steps": 1140, "total_steps": 1166, "loss": 1.0543, "lr": 1.2531679884636503e-07, "epoch": 0.9775618122052309, "percentage": 97.77, "elapsed_time": "4:02:53", "remaining_time": "0:05:32"}
+{"current_steps": 1145, "total_steps": 1166, "loss": 0.8641, "lr": 1.2044818368360252e-07, "epoch": 0.9818493640131485, "percentage": 98.2, "elapsed_time": "4:04:16", "remaining_time": "0:04:28"}
+{"current_steps": 1150, "total_steps": 1166, "loss": 1.0326, "lr": 1.1557956852084e-07, "epoch": 0.9861369158210662, "percentage": 98.63, "elapsed_time": "4:06:19", "remaining_time": "0:03:25"}
+{"current_steps": 1155, "total_steps": 1166, "loss": 1.0289, "lr": 1.1071095335807752e-07, "epoch": 0.9904244676289838, "percentage": 99.06, "elapsed_time": "4:08:03", "remaining_time": "0:02:21"}
+{"current_steps": 1160, "total_steps": 1166, "loss": 0.939, "lr": 1.0584233819531501e-07, "epoch": 0.9947120194369016, "percentage": 99.49, "elapsed_time": "4:09:33", "remaining_time": "0:01:17"}
+{"current_steps": 1165, "total_steps": 1166, "loss": 1.0486, "lr": 1.009737230325525e-07, "epoch": 0.9989995712448192, "percentage": 99.91, "elapsed_time": "4:10:59", "remaining_time": "0:00:12"}
+{"current_steps": 1166, "total_steps": 1166, "epoch": 0.9998570816064027, "percentage": 100.0, "elapsed_time": "4:11:39", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b7800b46a3d2e4d7f1b9f91a86df91cd2c4642c6019bcce37c25e65efe0a2a
+size 7288