Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: NousResearch/Meta-Llama-3-8B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the identity and the iplaw20241002 datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.1582
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 12.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0713        | 6.8376 | 1000 | 0.1959          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 11.97948717948718,
+    "eval_loss": 0.15816539525985718,
+    "eval_runtime": 5.1001,
+    "eval_samples_per_second": 25.49,
+    "eval_steps_per_second": 25.49,
+    "total_flos": 9.576163802677248e+16,
+    "train_loss": 0.4554890414942311,
+    "train_runtime": 1838.2954,
+    "train_samples_per_second": 7.638,
+    "train_steps_per_second": 0.953
+}

checkpoint-1752/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-1752/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

checkpoint-1752/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe05c06b89afebeafa100ffbe507d79134c25eb638947329eca936942ab1b15
+size 4976698672

checkpoint-1752/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b70695a492341b12903d9bcd47b9942f6d74795024e10b467258da3cbbc9f20
+size 4999802720

checkpoint-1752/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486570a07a8bb7226708b53c6c2b1a75b6343a05fff48dd58e9953f9e3b03a4c
+size 4915916176

checkpoint-1752/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71f0946f4d698548ee8c6b7d1ce3056866312401aed66d68aa92306ef0a03f5
+size 1168138808

checkpoint-1752/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"
+  }
+}

checkpoint-1752/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e934720030cc7c49c703fa688b4dbe43bc56ab1b3531e1326046c47333e07e4b
+size 1744904195

checkpoint-1752/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7682299c566684ea51cf26f0c86b6ffaa3c0bc63cbdf84674b29a2c62ac72143
+size 14244

checkpoint-1752/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7417060a4fe47abb2608162afef26f0754f08735efdf9e2a86d17f981aac9a7d
+size 1064

checkpoint-1752/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|>"
+}

checkpoint-1752/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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-1752/trainer_state.json

@@ -0,0 +1,1266 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.97948717948718,
+  "eval_steps": 1000,
+  "global_step": 1752,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 10.4375,
+      "learning_rate": 5.681818181818182e-07,
+      "loss": 2.6042,
+      "step": 10
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 12.75,
+      "learning_rate": 1.1363636363636364e-06,
+      "loss": 2.577,
+      "step": 20
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.7045454545454546e-06,
+      "loss": 2.4842,
+      "step": 30
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 15.4375,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 2.4127,
+      "step": 40
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 21.75,
+      "learning_rate": 2.8409090909090916e-06,
+      "loss": 2.2065,
+      "step": 50
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 28.125,
+      "learning_rate": 3.409090909090909e-06,
+      "loss": 2.2638,
+      "step": 60
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 29.5,
+      "learning_rate": 3.9772727272727275e-06,
+      "loss": 2.0591,
+      "step": 70
+    },
+    {
+      "epoch": 0.5470085470085471,
+      "grad_norm": 20.5,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.9693,
+      "step": 80
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 19.875,
+      "learning_rate": 5.113636363636364e-06,
+      "loss": 1.9559,
+      "step": 90
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 5.125,
+      "learning_rate": 5.681818181818183e-06,
+      "loss": 1.8579,
+      "step": 100
+    },
+    {
+      "epoch": 0.7521367521367521,
+      "grad_norm": 5.5625,
+      "learning_rate": 6.25e-06,
+      "loss": 1.8601,
+      "step": 110
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.7222,
+      "step": 120
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 6.03125,
+      "learning_rate": 7.386363636363637e-06,
+      "loss": 1.7724,
+      "step": 130
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 5.6875,
+      "learning_rate": 7.954545454545455e-06,
+      "loss": 1.8647,
+      "step": 140
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 5.0625,
+      "learning_rate": 8.522727272727273e-06,
+      "loss": 1.7017,
+      "step": 150
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 4.5625,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.6883,
+      "step": 160
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 5.3125,
+      "learning_rate": 9.65909090909091e-06,
+      "loss": 1.5485,
+      "step": 170
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.999841055681184e-06,
+      "loss": 1.5548,
+      "step": 180
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.998053048145735e-06,
+      "loss": 1.602,
+      "step": 190
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 3.671875,
+      "learning_rate": 9.994279065509094e-06,
+      "loss": 1.5151,
+      "step": 200
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.988520607362297e-06,
+      "loss": 1.4208,
+      "step": 210
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 5.90625,
+      "learning_rate": 9.98077996182722e-06,
+      "loss": 1.4954,
+      "step": 220
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.971060204647384e-06,
+      "loss": 1.3399,
+      "step": 230
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 5.5,
+      "learning_rate": 9.959365197965824e-06,
+      "loss": 1.2554,
+      "step": 240
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 6.65625,
+      "learning_rate": 9.945699588790455e-06,
+      "loss": 1.3161,
+      "step": 250
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 7.5625,
+      "learning_rate": 9.930068807147585e-06,
+      "loss": 1.3603,
+      "step": 260
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 6.375,
+      "learning_rate": 9.912479063924309e-06,
+      "loss": 1.2576,
+      "step": 270
+    },
+    {
+      "epoch": 1.9145299145299144,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.8929373484006e-06,
+      "loss": 1.207,
+      "step": 280
+    },
+    {
+      "epoch": 1.982905982905983,
+      "grad_norm": 4.90625,
+      "learning_rate": 9.871451425472128e-06,
+      "loss": 1.232,
+      "step": 290
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 7.125,
+      "learning_rate": 9.848029832564875e-06,
+      "loss": 1.0106,
+      "step": 300
+    },
+    {
+      "epoch": 2.1196581196581197,
+      "grad_norm": 6.65625,
+      "learning_rate": 9.822681876242797e-06,
+      "loss": 0.9484,
+      "step": 310
+    },
+    {
+      "epoch": 2.1880341880341883,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.795417628509857e-06,
+      "loss": 1.0094,
+      "step": 320
+    },
+    {
+      "epoch": 2.2564102564102564,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.766247922807927e-06,
+      "loss": 0.9317,
+      "step": 330
+    },
+    {
+      "epoch": 2.324786324786325,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.73518434971211e-06,
+      "loss": 0.8936,
+      "step": 340
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 7.375,
+      "learning_rate": 9.702239252325237e-06,
+      "loss": 0.9004,
+      "step": 350
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.667425721373333e-06,
+      "loss": 0.9335,
+      "step": 360
+    },
+    {
+      "epoch": 2.52991452991453,
+      "grad_norm": 7.0625,
+      "learning_rate": 9.630757590004023e-06,
+      "loss": 0.8982,
+      "step": 370
+    },
+    {
+      "epoch": 2.5982905982905984,
+      "grad_norm": 4.40625,
+      "learning_rate": 9.592249428289935e-06,
+      "loss": 0.8541,
+      "step": 380
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 6.5625,
+      "learning_rate": 9.551916537439282e-06,
+      "loss": 0.8105,
+      "step": 390
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 5.125,
+      "learning_rate": 9.50977494371594e-06,
+      "loss": 0.8308,
+      "step": 400
+    },
+    {
+      "epoch": 2.8034188034188032,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.465841392071396e-06,
+      "loss": 0.8515,
+      "step": 410
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.420133339491171e-06,
+      "loss": 0.6671,
+      "step": 420
+    },
+    {
+      "epoch": 2.9401709401709404,
+      "grad_norm": 6.21875,
+      "learning_rate": 9.372668948058276e-06,
+      "loss": 0.7728,
+      "step": 430
+    },
+    {
+      "epoch": 3.0085470085470085,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.323467077736513e-06,
+      "loss": 0.6978,
+      "step": 440
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 5.9375,
+      "learning_rate": 9.272547278876475e-06,
+      "loss": 0.561,
+      "step": 450
+    },
+    {
+      "epoch": 3.1452991452991452,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.219929784447232e-06,
+      "loss": 0.5354,
+      "step": 460
+    },
+    {
+      "epoch": 3.213675213675214,
+      "grad_norm": 4.90625,
+      "learning_rate": 9.16563550199674e-06,
+      "loss": 0.5613,
+      "step": 470
+    },
+    {
+      "epoch": 3.282051282051282,
+      "grad_norm": 6.5,
+      "learning_rate": 9.109686005344258e-06,
+      "loss": 0.576,
+      "step": 480
+    },
+    {
+      "epoch": 3.3504273504273505,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.052103526007976e-06,
+      "loss": 0.492,
+      "step": 490
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 7.5,
+      "learning_rate": 8.992910944371343e-06,
+      "loss": 0.5087,
+      "step": 500
+    },
+    {
+      "epoch": 3.4871794871794872,
+      "grad_norm": 6.59375,
+      "learning_rate": 8.932131780591542e-06,
+      "loss": 0.476,
+      "step": 510
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 4.4375,
+      "learning_rate": 8.869790185253766e-06,
+      "loss": 0.4111,
+      "step": 520
+    },
+    {
+      "epoch": 3.623931623931624,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.805910929774989e-06,
+      "loss": 0.4426,
+      "step": 530
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 4.46875,
+      "learning_rate": 8.740519396561045e-06,
+      "loss": 0.4171,
+      "step": 540
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 5.28125,
+      "learning_rate": 8.673641568920944e-06,
+      "loss": 0.445,
+      "step": 550
+    },
+    {
+      "epoch": 3.8290598290598292,
+      "grad_norm": 5.75,
+      "learning_rate": 8.60530402074241e-06,
+      "loss": 0.4653,
+      "step": 560
+    },
+    {
+      "epoch": 3.8974358974358974,
+      "grad_norm": 2.984375,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.4276,
+      "step": 570
+    },
+    {
+      "epoch": 3.965811965811966,
+      "grad_norm": 3.9375,
+      "learning_rate": 8.46435894762922e-06,
+      "loss": 0.423,
+      "step": 580
+    },
+    {
+      "epoch": 4.034188034188034,
+      "grad_norm": 2.96875,
+      "learning_rate": 8.39180742718334e-06,
+      "loss": 0.3372,
+      "step": 590
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 3.25,
+      "learning_rate": 8.317908172923207e-06,
+      "loss": 0.29,
+      "step": 600
+    },
+    {
+      "epoch": 4.170940170940171,
+      "grad_norm": 3.84375,
+      "learning_rate": 8.242690548698611e-06,
+      "loss": 0.2464,
+      "step": 610
+    },
+    {
+      "epoch": 4.239316239316239,
+      "grad_norm": 4.28125,
+      "learning_rate": 8.166184442213314e-06,
+      "loss": 0.2754,
+      "step": 620
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 2.796875,
+      "learning_rate": 8.088420253149173e-06,
+      "loss": 0.2699,
+      "step": 630
+    },
+    {
+      "epoch": 4.3760683760683765,
+      "grad_norm": 2.796875,
+      "learning_rate": 8.009428881086836e-06,
+      "loss": 0.2621,
+      "step": 640
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 4.125,
+      "learning_rate": 7.9292417132278e-06,
+      "loss": 0.2688,
+      "step": 650
+    },
+    {
+      "epoch": 4.512820512820513,
+      "grad_norm": 2.9375,
+      "learning_rate": 7.847890611922721e-06,
+      "loss": 0.2871,
+      "step": 660
+    },
+    {
+      "epoch": 4.581196581196581,
+      "grad_norm": 2.78125,
+      "learning_rate": 7.76540790201091e-06,
+      "loss": 0.2439,
+      "step": 670
+    },
+    {
+      "epoch": 4.64957264957265,
+      "grad_norm": 5.5625,
+      "learning_rate": 7.68182635797606e-06,
+      "loss": 0.2478,
+      "step": 680
+    },
+    {
+      "epoch": 4.717948717948718,
+      "grad_norm": 5.09375,
+      "learning_rate": 7.597179190923343e-06,
+      "loss": 0.2385,
+      "step": 690
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 2.53125,
+      "learning_rate": 7.511500035382943e-06,
+      "loss": 0.2525,
+      "step": 700
+    },
+    {
+      "epoch": 4.854700854700854,
+      "grad_norm": 3.734375,
+      "learning_rate": 7.424822935945416e-06,
+      "loss": 0.2448,
+      "step": 710
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 2.453125,
+      "learning_rate": 7.33718233373407e-06,
+      "loss": 0.2173,
+      "step": 720
+    },
+    {
+      "epoch": 4.9914529914529915,
+      "grad_norm": 2.0625,
+      "learning_rate": 7.248613052719793e-06,
+      "loss": 0.1926,
+      "step": 730
+    },
+    {
+      "epoch": 5.05982905982906,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.159150285883757e-06,
+      "loss": 0.1754,
+      "step": 740
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 2.4375,
+      "learning_rate": 7.0688295812334995e-06,
+      "loss": 0.1334,
+      "step": 750
+    },
+    {
+      "epoch": 5.196581196581197,
+      "grad_norm": 1.84375,
+      "learning_rate": 6.977686827677926e-06,
+      "loss": 0.147,
+      "step": 760
+    },
+    {
+      "epoch": 5.264957264957265,
+      "grad_norm": 1.65625,
+      "learning_rate": 6.885758240766867e-06,
+      "loss": 0.1549,
+      "step": 770
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.793080348300834e-06,
+      "loss": 0.1312,
+      "step": 780
+    },
+    {
+      "epoch": 5.401709401709402,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.69968997581671e-06,
+      "loss": 0.1403,
+      "step": 790
+    },
+    {
+      "epoch": 5.47008547008547,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.6056242319551315e-06,
+      "loss": 0.1237,
+      "step": 800
+    },
+    {
+      "epoch": 5.538461538461538,
+      "grad_norm": 3.046875,
+      "learning_rate": 6.510920493715381e-06,
+      "loss": 0.1233,
+      "step": 810
+    },
+    {
+      "epoch": 5.6068376068376065,
+      "grad_norm": 0.87109375,
+      "learning_rate": 6.415616391603639e-06,
+      "loss": 0.1667,
+      "step": 820
+    },
+    {
+      "epoch": 5.6752136752136755,
+      "grad_norm": 1.25,
+      "learning_rate": 6.3197497946805205e-06,
+      "loss": 0.1224,
+      "step": 830
+    },
+    {
+      "epoch": 5.743589743589744,
+      "grad_norm": 2.421875,
+      "learning_rate": 6.223358795513812e-06,
+      "loss": 0.118,
+      "step": 840
+    },
+    {
+      "epoch": 5.811965811965812,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.126481695042392e-06,
+      "loss": 0.0897,
+      "step": 850
+    },
+    {
+      "epoch": 5.880341880341881,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.029156987357373e-06,
+      "loss": 0.1142,
+      "step": 860
+    },
+    {
+      "epoch": 5.948717948717949,
+      "grad_norm": 1.78125,
+      "learning_rate": 5.931423344406478e-06,
+      "loss": 0.1542,
+      "step": 870
+    },
+    {
+      "epoch": 6.017094017094017,
+      "grad_norm": 1.2890625,
+      "learning_rate": 5.8333196006277536e-06,
+      "loss": 0.0937,
+      "step": 880
+    },
+    {
+      "epoch": 6.085470085470085,
+      "grad_norm": 1.75,
+      "learning_rate": 5.734884737518714e-06,
+      "loss": 0.0699,
+      "step": 890
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.96484375,
+      "learning_rate": 5.636157868147054e-06,
+      "loss": 0.0757,
+      "step": 900
+    },
+    {
+      "epoch": 6.222222222222222,
+      "grad_norm": 0.84765625,
+      "learning_rate": 5.537178221609088e-06,
+      "loss": 0.0657,
+      "step": 910
+    },
+    {
+      "epoch": 6.2905982905982905,
+      "grad_norm": 2.328125,
+      "learning_rate": 5.437985127442065e-06,
+      "loss": 0.0838,
+      "step": 920
+    },
+    {
+      "epoch": 6.358974358974359,
+      "grad_norm": 1.015625,
+      "learning_rate": 5.338617999996603e-06,
+      "loss": 0.0876,
+      "step": 930
+    },
+    {
+      "epoch": 6.427350427350428,
+      "grad_norm": 1.0,
+      "learning_rate": 5.239116322775392e-06,
+      "loss": 0.0652,
+      "step": 940
+    },
+    {
+      "epoch": 6.495726495726496,
+      "grad_norm": 0.96484375,
+      "learning_rate": 5.139519632744443e-06,
+      "loss": 0.0843,
+      "step": 950
+    },
+    {
+      "epoch": 6.564102564102564,
+      "grad_norm": 1.3828125,
+      "learning_rate": 5.039867504623084e-06,
+      "loss": 0.0677,
+      "step": 960
+    },
+    {
+      "epoch": 6.632478632478632,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.940199535158954e-06,
+      "loss": 0.0764,
+      "step": 970
+    },
+    {
+      "epoch": 6.700854700854701,
+      "grad_norm": 0.828125,
+      "learning_rate": 4.8405553273942415e-06,
+      "loss": 0.0642,
+      "step": 980
+    },
+    {
+      "epoch": 6.769230769230769,
+      "grad_norm": 1.1796875,
+      "learning_rate": 4.740974474929438e-06,
+      "loss": 0.0444,
+      "step": 990
+    },
+    {
+      "epoch": 6.837606837606837,
+      "grad_norm": 0.83203125,
+      "learning_rate": 4.641496546190813e-06,
+      "loss": 0.0713,
+      "step": 1000
+    },
+    {
+      "epoch": 6.837606837606837,
+      "eval_loss": 0.19593119621276855,
+      "eval_runtime": 5.1008,
+      "eval_samples_per_second": 25.486,
+      "eval_steps_per_second": 25.486,
+      "step": 1000
+    },
+    {
+      "epoch": 6.905982905982906,
+      "grad_norm": 0.4765625,
+      "learning_rate": 4.542161068707927e-06,
+      "loss": 0.0494,
+      "step": 1010
+    },
+    {
+      "epoch": 6.9743589743589745,
+      "grad_norm": 0.78125,
+      "learning_rate": 4.443007513407368e-06,
+      "loss": 0.0492,
+      "step": 1020
+    },
+    {
+      "epoch": 7.042735042735043,
+      "grad_norm": 0.73046875,
+      "learning_rate": 4.344075278928989e-06,
+      "loss": 0.1084,
+      "step": 1030
+    },
+    {
+      "epoch": 7.111111111111111,
+      "grad_norm": 0.78515625,
+      "learning_rate": 4.245403675970877e-06,
+      "loss": 0.0605,
+      "step": 1040
+    },
+    {
+      "epoch": 7.17948717948718,
+      "grad_norm": 0.79296875,
+      "learning_rate": 4.147031911669243e-06,
+      "loss": 0.0422,
+      "step": 1050
+    },
+    {
+      "epoch": 7.247863247863248,
+      "grad_norm": 1.796875,
+      "learning_rate": 4.048999074019493e-06,
+      "loss": 0.0388,
+      "step": 1060
+    },
+    {
+      "epoch": 7.316239316239316,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.951344116344606e-06,
+      "loss": 0.0295,
+      "step": 1070
+    },
+    {
+      "epoch": 7.384615384615385,
+      "grad_norm": 0.44140625,
+      "learning_rate": 3.854105841817056e-06,
+      "loss": 0.0545,
+      "step": 1080
+    },
+    {
+      "epoch": 7.452991452991453,
+      "grad_norm": 0.64453125,
+      "learning_rate": 3.7573228880403734e-06,
+      "loss": 0.0337,
+      "step": 1090
+    },
+    {
+      "epoch": 7.521367521367521,
+      "grad_norm": 0.5703125,
+      "learning_rate": 3.661033711696501e-06,
+      "loss": 0.0507,
+      "step": 1100
+    },
+    {
+      "epoch": 7.589743589743589,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.5652765732650523e-06,
+      "loss": 0.0419,
+      "step": 1110
+    },
+    {
+      "epoch": 7.6581196581196584,
+      "grad_norm": 1.21875,
+      "learning_rate": 3.4700895218205026e-06,
+      "loss": 0.0423,
+      "step": 1120
+    },
+    {
+      "epoch": 7.726495726495727,
+      "grad_norm": 1.234375,
+      "learning_rate": 3.375510379913418e-06,
+      "loss": 0.0488,
+      "step": 1130
+    },
+    {
+      "epoch": 7.794871794871795,
+      "grad_norm": 0.4140625,
+      "learning_rate": 3.2815767285416576e-06,
+      "loss": 0.0388,
+      "step": 1140
+    },
+    {
+      "epoch": 7.863247863247864,
+      "grad_norm": 0.462890625,
+      "learning_rate": 3.188325892217587e-06,
+      "loss": 0.0197,
+      "step": 1150
+    },
+    {
+      "epoch": 7.931623931623932,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.0957949241371845e-06,
+      "loss": 0.0326,
+      "step": 1160
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.0040205914569664e-06,
+      "loss": 0.0383,
+      "step": 1170
+    },
+    {
+      "epoch": 8.068376068376068,
+      "grad_norm": 0.40234375,
+      "learning_rate": 2.913039360684565e-06,
+      "loss": 0.0296,
+      "step": 1180
+    },
+    {
+      "epoch": 8.136752136752136,
+      "grad_norm": 0.482421875,
+      "learning_rate": 2.822887383188775e-06,
+      "loss": 0.0564,
+      "step": 1190
+    },
+    {
+      "epoch": 8.205128205128204,
+      "grad_norm": 0.435546875,
+      "learning_rate": 2.7336004808348094e-06,
+      "loss": 0.0295,
+      "step": 1200
+    },
+    {
+      "epoch": 8.273504273504274,
+      "grad_norm": 0.435546875,
+      "learning_rate": 2.645214131750498e-06,
+      "loss": 0.0194,
+      "step": 1210
+    },
+    {
+      "epoch": 8.341880341880342,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 2.5577634562290567e-06,
+      "loss": 0.0261,
+      "step": 1220
+    },
+    {
+      "epoch": 8.41025641025641,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.4712832027740545e-06,
+      "loss": 0.0237,
+      "step": 1230
+    },
+    {
+      "epoch": 8.478632478632479,
+      "grad_norm": 0.15625,
+      "learning_rate": 2.385807734292097e-06,
+      "loss": 0.037,
+      "step": 1240
+    },
+    {
+      "epoch": 8.547008547008547,
+      "grad_norm": 0.63671875,
+      "learning_rate": 2.3013710144387374e-06,
+      "loss": 0.0241,
+      "step": 1250
+    },
+    {
+      "epoch": 8.615384615384615,
+      "grad_norm": 0.53515625,
+      "learning_rate": 2.218006594123028e-06,
+      "loss": 0.0258,
+      "step": 1260
+    },
+    {
+      "epoch": 8.683760683760683,
+      "grad_norm": 0.73828125,
+      "learning_rate": 2.1357475981760704e-06,
+      "loss": 0.0361,
+      "step": 1270
+    },
+    {
+      "epoch": 8.752136752136753,
+      "grad_norm": 0.333984375,
+      "learning_rate": 2.0546267121888863e-06,
+      "loss": 0.0243,
+      "step": 1280
+    },
+    {
+      "epoch": 8.820512820512821,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.9746761695247803e-06,
+      "loss": 0.0404,
+      "step": 1290
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.50390625,
+      "learning_rate": 1.8959277385114516e-06,
+      "loss": 0.0284,
+      "step": 1300
+    },
+    {
+      "epoch": 8.957264957264957,
+      "grad_norm": 0.265625,
+      "learning_rate": 1.8184127098178288e-06,
+      "loss": 0.028,
+      "step": 1310
+    },
+    {
+      "epoch": 9.025641025641026,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.7421618840207576e-06,
+      "loss": 0.0174,
+      "step": 1320
+    },
+    {
+      "epoch": 9.094017094017094,
+      "grad_norm": 0.47265625,
+      "learning_rate": 1.667205559366372e-06,
+      "loss": 0.0293,
+      "step": 1330
+    },
+    {
+      "epoch": 9.162393162393162,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.5935735197311204e-06,
+      "loss": 0.0459,
+      "step": 1340
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.12890625,
+      "learning_rate": 1.5212950227871292e-06,
+      "loss": 0.0197,
+      "step": 1350
+    },
+    {
+      "epoch": 9.2991452991453,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 1.4503987883766857e-06,
+      "loss": 0.0208,
+      "step": 1360
+    },
+    {
+      "epoch": 9.367521367521368,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.3809129871004113e-06,
+      "loss": 0.0332,
+      "step": 1370
+    },
+    {
+      "epoch": 9.435897435897436,
+      "grad_norm": 0.625,
+      "learning_rate": 1.312865229123681e-06,
+      "loss": 0.0186,
+      "step": 1380
+    },
+    {
+      "epoch": 9.504273504273504,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.2462825532057394e-06,
+      "loss": 0.0365,
+      "step": 1390
+    },
+    {
+      "epoch": 9.572649572649572,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.1811914159558374e-06,
+      "loss": 0.0172,
+      "step": 1400
+    },
+    {
+      "epoch": 9.64102564102564,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.117617681320729e-06,
+      "loss": 0.0307,
+      "step": 1410
+    },
+    {
+      "epoch": 9.709401709401709,
+      "grad_norm": 0.177734375,
+      "learning_rate": 1.0555866103076212e-06,
+      "loss": 0.0138,
+      "step": 1420
+    },
+    {
+      "epoch": 9.777777777777779,
+      "grad_norm": 0.369140625,
+      "learning_rate": 9.951228509467248e-07,
+      "loss": 0.0204,
+      "step": 1430
+    },
+    {
+      "epoch": 9.846153846153847,
+      "grad_norm": 0.2421875,
+      "learning_rate": 9.362504284973683e-07,
+      "loss": 0.017,
+      "step": 1440
+    },
+    {
+      "epoch": 9.914529914529915,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 8.789927359015643e-07,
+      "loss": 0.0236,
+      "step": 1450
+    },
+    {
+      "epoch": 9.982905982905983,
+      "grad_norm": 0.296875,
+      "learning_rate": 8.233725244888291e-07,
+      "loss": 0.0234,
+      "step": 1460
+    },
+    {
+      "epoch": 10.051282051282051,
+      "grad_norm": 0.3828125,
+      "learning_rate": 7.694118949359553e-07,
+      "loss": 0.015,
+      "step": 1470
+    },
+    {
+      "epoch": 10.11965811965812,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 7.171322884852988e-07,
+      "loss": 0.0209,
+      "step": 1480
+    },
+    {
+      "epoch": 10.188034188034187,
+      "grad_norm": 0.20703125,
+      "learning_rate": 6.665544784251232e-07,
+      "loss": 0.0156,
+      "step": 1490
+    },
+    {
+      "epoch": 10.256410256410255,
+      "grad_norm": 0.380859375,
+      "learning_rate": 6.176985618353282e-07,
+      "loss": 0.0245,
+      "step": 1500
+    },
+    {
+      "epoch": 10.324786324786325,
+      "grad_norm": 0.5234375,
+      "learning_rate": 5.705839516018818e-07,
+      "loss": 0.0143,
+      "step": 1510
+    },
+    {
+      "epoch": 10.393162393162394,
+      "grad_norm": 0.9375,
+      "learning_rate": 5.252293687031196e-07,
+      "loss": 0.0279,
+      "step": 1520
+    },
+    {
+      "epoch": 10.461538461538462,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 4.816528347709614e-07,
+      "loss": 0.0215,
+      "step": 1530
+    },
+    {
+      "epoch": 10.52991452991453,
+      "grad_norm": 0.84765625,
+      "learning_rate": 4.398716649300311e-07,
+      "loss": 0.0145,
+      "step": 1540
+    },
+    {
+      "epoch": 10.598290598290598,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.999024609174812e-07,
+      "loss": 0.0196,
+      "step": 1550
+    },
+    {
+      "epoch": 10.666666666666666,
+      "grad_norm": 1.3671875,
+      "learning_rate": 3.61761104486314e-07,
+      "loss": 0.0271,
+      "step": 1560
+    },
+    {
+      "epoch": 10.735042735042736,
+      "grad_norm": 0.70703125,
+      "learning_rate": 3.2546275109475554e-07,
+      "loss": 0.0179,
+      "step": 1570
+    },
+    {
+      "epoch": 10.803418803418804,
+      "grad_norm": 0.796875,
+      "learning_rate": 2.9102182388425106e-07,
+      "loss": 0.0228,
+      "step": 1580
+    },
+    {
+      "epoch": 10.871794871794872,
+      "grad_norm": 0.451171875,
+      "learning_rate": 2.5845200794842154e-07,
+      "loss": 0.0217,
+      "step": 1590
+    },
+    {
+      "epoch": 10.94017094017094,
+      "grad_norm": 0.95703125,
+      "learning_rate": 2.2776624489530664e-07,
+      "loss": 0.0212,
+      "step": 1600
+    },
+    {
+      "epoch": 11.008547008547009,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.9897672770501198e-07,
+      "loss": 0.0492,
+      "step": 1610
+    },
+    {
+      "epoch": 11.076923076923077,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.7209489588483396e-07,
+      "loss": 0.0265,
+      "step": 1620
+    },
+    {
+      "epoch": 11.145299145299145,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.4713143092377534e-07,
+      "loss": 0.0188,
+      "step": 1630
+    },
+    {
+      "epoch": 11.213675213675213,
+      "grad_norm": 2.625,
+      "learning_rate": 1.2409625204825802e-07,
+      "loss": 0.025,
+      "step": 1640
+    },
+    {
+      "epoch": 11.282051282051283,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.0299851228072089e-07,
+      "loss": 0.0186,
+      "step": 1650
+    },
+    {
+      "epoch": 11.350427350427351,
+      "grad_norm": 5.40625,
+      "learning_rate": 8.384659480266733e-08,
+      "loss": 0.0257,
+      "step": 1660
+    },
+    {
+      "epoch": 11.418803418803419,
+      "grad_norm": 4.09375,
+      "learning_rate": 6.664810962361268e-08,
+      "loss": 0.0213,
+      "step": 1670
+    },
+    {
+      "epoch": 11.487179487179487,
+      "grad_norm": 3.125,
+      "learning_rate": 5.1409890557246876e-08,
+      "loss": 0.0137,
+      "step": 1680
+    },
+    {
+      "epoch": 11.555555555555555,
+      "grad_norm": 5.21875,
+      "learning_rate": 3.813799250602046e-08,
+      "loss": 0.0164,
+      "step": 1690
+    },
+    {
+      "epoch": 11.623931623931623,
+      "grad_norm": 0.328125,
+      "learning_rate": 2.683768905523243e-08,
+      "loss": 0.0197,
+      "step": 1700
+    },
+    {
+      "epoch": 11.692307692307692,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.7513470377570896e-08,
+      "loss": 0.0246,
+      "step": 1710
+    },
+    {
+      "epoch": 11.760683760683762,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.016904144894304e-08,
+      "loss": 0.0295,
+      "step": 1720
+    },
+    {
+      "epoch": 11.82905982905983,
+      "grad_norm": 1.3671875,
+      "learning_rate": 4.807320576307728e-09,
+      "loss": 0.029,
+      "step": 1730
+    },
+    {
+      "epoch": 11.897435897435898,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.4304382380819771e-09,
+      "loss": 0.0177,
+      "step": 1740
+    },
+    {
+      "epoch": 11.965811965811966,
+      "grad_norm": 1.0234375,
+      "learning_rate": 3.9736237600895846e-11,
+      "loss": 0.0261,
+      "step": 1750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1752,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.576163802677248e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1752/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab620514947fb9d397c617b77e3f66b34339ff4de9840ac3d96ae1f32ebae0a
+size 5304

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 11.97948717948718,
+    "eval_loss": 0.15816539525985718,
+    "eval_runtime": 5.1001,
+    "eval_samples_per_second": 25.49,
+    "eval_steps_per_second": 25.49
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe05c06b89afebeafa100ffbe507d79134c25eb638947329eca936942ab1b15
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b70695a492341b12903d9bcd47b9942f6d74795024e10b467258da3cbbc9f20
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486570a07a8bb7226708b53c6c2b1a75b6343a05fff48dd58e9953f9e3b03a4c
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71f0946f4d698548ee8c6b7d1ce3056866312401aed66d68aa92306ef0a03f5
+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"
+  }
+}

runs/Oct02_10-18-30_3f5d7219a43f/events.out.tfevents.1727864395.3f5d7219a43f.4325.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9728fc94ffcf6339d35328abea595dc3bffd356b198823bf064270c730d52192
+size 42668

runs/Oct02_10-18-30_3f5d7219a43f/events.out.tfevents.1727866311.3f5d7219a43f.4325.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96c225f921b1fa06f847b3bc6fd6b156eb05420c7d802fe24311cea964ac416
+size 359

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_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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.97948717948718,
+    "total_flos": 9.576163802677248e+16,
+    "train_loss": 0.4554890414942311,
+    "train_runtime": 1838.2954,
+    "train_samples_per_second": 7.638,
+    "train_steps_per_second": 0.953
+}

trainer_log.jsonl

@@ -0,0 +1,177 @@
+{"current_steps": 10, "total_steps": 1752, "loss": 2.6042, "learning_rate": 5.681818181818182e-07, "epoch": 0.06837606837606838, "percentage": 0.57, "elapsed_time": "0:00:16", "remaining_time": "0:46:48"}
+{"current_steps": 20, "total_steps": 1752, "loss": 2.577, "learning_rate": 1.1363636363636364e-06, "epoch": 0.13675213675213677, "percentage": 1.14, "elapsed_time": "0:00:30", "remaining_time": "0:43:48"}
+{"current_steps": 30, "total_steps": 1752, "loss": 2.4842, "learning_rate": 1.7045454545454546e-06, "epoch": 0.20512820512820512, "percentage": 1.71, "elapsed_time": "0:00:44", "remaining_time": "0:42:36"}
+{"current_steps": 40, "total_steps": 1752, "loss": 2.4127, "learning_rate": 2.2727272727272728e-06, "epoch": 0.27350427350427353, "percentage": 2.28, "elapsed_time": "0:00:58", "remaining_time": "0:41:53"}
+{"current_steps": 50, "total_steps": 1752, "loss": 2.2065, "learning_rate": 2.8409090909090916e-06, "epoch": 0.3418803418803419, "percentage": 2.85, "elapsed_time": "0:01:13", "remaining_time": "0:41:33"}
+{"current_steps": 60, "total_steps": 1752, "loss": 2.2638, "learning_rate": 3.409090909090909e-06, "epoch": 0.41025641025641024, "percentage": 3.42, "elapsed_time": "0:01:27", "remaining_time": "0:41:02"}
+{"current_steps": 70, "total_steps": 1752, "loss": 2.0591, "learning_rate": 3.9772727272727275e-06, "epoch": 0.47863247863247865, "percentage": 4.0, "elapsed_time": "0:01:41", "remaining_time": "0:40:32"}
+{"current_steps": 80, "total_steps": 1752, "loss": 1.9693, "learning_rate": 4.5454545454545455e-06, "epoch": 0.5470085470085471, "percentage": 4.57, "elapsed_time": "0:01:55", "remaining_time": "0:40:08"}
+{"current_steps": 90, "total_steps": 1752, "loss": 1.9559, "learning_rate": 5.113636363636364e-06, "epoch": 0.6153846153846154, "percentage": 5.14, "elapsed_time": "0:02:09", "remaining_time": "0:39:49"}
+{"current_steps": 100, "total_steps": 1752, "loss": 1.8579, "learning_rate": 5.681818181818183e-06, "epoch": 0.6837606837606838, "percentage": 5.71, "elapsed_time": "0:02:23", "remaining_time": "0:39:34"}
+{"current_steps": 110, "total_steps": 1752, "loss": 1.8601, "learning_rate": 6.25e-06, "epoch": 0.7521367521367521, "percentage": 6.28, "elapsed_time": "0:02:37", "remaining_time": "0:39:06"}
+{"current_steps": 120, "total_steps": 1752, "loss": 1.7222, "learning_rate": 6.818181818181818e-06, "epoch": 0.8205128205128205, "percentage": 6.85, "elapsed_time": "0:02:51", "remaining_time": "0:38:45"}
+{"current_steps": 130, "total_steps": 1752, "loss": 1.7724, "learning_rate": 7.386363636363637e-06, "epoch": 0.8888888888888888, "percentage": 7.42, "elapsed_time": "0:03:04", "remaining_time": "0:38:21"}
+{"current_steps": 140, "total_steps": 1752, "loss": 1.8647, "learning_rate": 7.954545454545455e-06, "epoch": 0.9572649572649573, "percentage": 7.99, "elapsed_time": "0:03:18", "remaining_time": "0:38:02"}
+{"current_steps": 150, "total_steps": 1752, "loss": 1.7017, "learning_rate": 8.522727272727273e-06, "epoch": 1.0256410256410255, "percentage": 8.56, "elapsed_time": "0:03:32", "remaining_time": "0:37:46"}
+{"current_steps": 160, "total_steps": 1752, "loss": 1.6883, "learning_rate": 9.090909090909091e-06, "epoch": 1.0940170940170941, "percentage": 9.13, "elapsed_time": "0:03:45", "remaining_time": "0:37:22"}
+{"current_steps": 170, "total_steps": 1752, "loss": 1.5485, "learning_rate": 9.65909090909091e-06, "epoch": 1.1623931623931625, "percentage": 9.7, "elapsed_time": "0:03:58", "remaining_time": "0:37:01"}
+{"current_steps": 180, "total_steps": 1752, "loss": 1.5548, "learning_rate": 9.999841055681184e-06, "epoch": 1.2307692307692308, "percentage": 10.27, "elapsed_time": "0:04:12", "remaining_time": "0:36:42"}
+{"current_steps": 190, "total_steps": 1752, "loss": 1.602, "learning_rate": 9.998053048145735e-06, "epoch": 1.2991452991452992, "percentage": 10.84, "elapsed_time": "0:04:25", "remaining_time": "0:36:23"}
+{"current_steps": 200, "total_steps": 1752, "loss": 1.5151, "learning_rate": 9.994279065509094e-06, "epoch": 1.3675213675213675, "percentage": 11.42, "elapsed_time": "0:04:39", "remaining_time": "0:36:05"}
+{"current_steps": 210, "total_steps": 1752, "loss": 1.4208, "learning_rate": 9.988520607362297e-06, "epoch": 1.435897435897436, "percentage": 11.99, "elapsed_time": "0:04:52", "remaining_time": "0:35:44"}
+{"current_steps": 220, "total_steps": 1752, "loss": 1.4954, "learning_rate": 9.98077996182722e-06, "epoch": 1.5042735042735043, "percentage": 12.56, "elapsed_time": "0:05:05", "remaining_time": "0:35:25"}
+{"current_steps": 230, "total_steps": 1752, "loss": 1.3399, "learning_rate": 9.971060204647384e-06, "epoch": 1.5726495726495726, "percentage": 13.13, "elapsed_time": "0:05:18", "remaining_time": "0:35:05"}
+{"current_steps": 240, "total_steps": 1752, "loss": 1.2554, "learning_rate": 9.959365197965824e-06, "epoch": 1.641025641025641, "percentage": 13.7, "elapsed_time": "0:05:31", "remaining_time": "0:34:46"}
+{"current_steps": 250, "total_steps": 1752, "loss": 1.3161, "learning_rate": 9.945699588790455e-06, "epoch": 1.7094017094017095, "percentage": 14.27, "elapsed_time": "0:05:44", "remaining_time": "0:34:30"}
+{"current_steps": 260, "total_steps": 1752, "loss": 1.3603, "learning_rate": 9.930068807147585e-06, "epoch": 1.7777777777777777, "percentage": 14.84, "elapsed_time": "0:05:57", "remaining_time": "0:34:11"}
+{"current_steps": 270, "total_steps": 1752, "loss": 1.2576, "learning_rate": 9.912479063924309e-06, "epoch": 1.8461538461538463, "percentage": 15.41, "elapsed_time": "0:06:10", "remaining_time": "0:33:51"}
+{"current_steps": 280, "total_steps": 1752, "loss": 1.207, "learning_rate": 9.8929373484006e-06, "epoch": 1.9145299145299144, "percentage": 15.98, "elapsed_time": "0:06:22", "remaining_time": "0:33:32"}
+{"current_steps": 290, "total_steps": 1752, "loss": 1.232, "learning_rate": 9.871451425472128e-06, "epoch": 1.982905982905983, "percentage": 16.55, "elapsed_time": "0:06:35", "remaining_time": "0:33:14"}
+{"current_steps": 300, "total_steps": 1752, "loss": 1.0106, "learning_rate": 9.848029832564875e-06, "epoch": 2.051282051282051, "percentage": 17.12, "elapsed_time": "0:06:48", "remaining_time": "0:32:57"}
+{"current_steps": 310, "total_steps": 1752, "loss": 0.9484, "learning_rate": 9.822681876242797e-06, "epoch": 2.1196581196581197, "percentage": 17.69, "elapsed_time": "0:07:01", "remaining_time": "0:32:38"}
+{"current_steps": 320, "total_steps": 1752, "loss": 1.0094, "learning_rate": 9.795417628509857e-06, "epoch": 2.1880341880341883, "percentage": 18.26, "elapsed_time": "0:07:13", "remaining_time": "0:32:20"}
+{"current_steps": 330, "total_steps": 1752, "loss": 0.9317, "learning_rate": 9.766247922807927e-06, "epoch": 2.2564102564102564, "percentage": 18.84, "elapsed_time": "0:07:26", "remaining_time": "0:32:02"}
+{"current_steps": 340, "total_steps": 1752, "loss": 0.8936, "learning_rate": 9.73518434971211e-06, "epoch": 2.324786324786325, "percentage": 19.41, "elapsed_time": "0:07:38", "remaining_time": "0:31:44"}
+{"current_steps": 350, "total_steps": 1752, "loss": 0.9004, "learning_rate": 9.702239252325237e-06, "epoch": 2.393162393162393, "percentage": 19.98, "elapsed_time": "0:07:51", "remaining_time": "0:31:28"}
+{"current_steps": 360, "total_steps": 1752, "loss": 0.9335, "learning_rate": 9.667425721373333e-06, "epoch": 2.4615384615384617, "percentage": 20.55, "elapsed_time": "0:08:03", "remaining_time": "0:31:09"}
+{"current_steps": 370, "total_steps": 1752, "loss": 0.8982, "learning_rate": 9.630757590004023e-06, "epoch": 2.52991452991453, "percentage": 21.12, "elapsed_time": "0:08:15", "remaining_time": "0:30:51"}
+{"current_steps": 380, "total_steps": 1752, "loss": 0.8541, "learning_rate": 9.592249428289935e-06, "epoch": 2.5982905982905984, "percentage": 21.69, "elapsed_time": "0:08:27", "remaining_time": "0:30:33"}
+{"current_steps": 390, "total_steps": 1752, "loss": 0.8105, "learning_rate": 9.551916537439282e-06, "epoch": 2.6666666666666665, "percentage": 22.26, "elapsed_time": "0:08:40", "remaining_time": "0:30:16"}
+{"current_steps": 400, "total_steps": 1752, "loss": 0.8308, "learning_rate": 9.50977494371594e-06, "epoch": 2.735042735042735, "percentage": 22.83, "elapsed_time": "0:08:52", "remaining_time": "0:29:59"}
+{"current_steps": 410, "total_steps": 1752, "loss": 0.8515, "learning_rate": 9.465841392071396e-06, "epoch": 2.8034188034188032, "percentage": 23.4, "elapsed_time": "0:09:04", "remaining_time": "0:29:41"}
+{"current_steps": 420, "total_steps": 1752, "loss": 0.6671, "learning_rate": 9.420133339491171e-06, "epoch": 2.871794871794872, "percentage": 23.97, "elapsed_time": "0:09:16", "remaining_time": "0:29:23"}
+{"current_steps": 430, "total_steps": 1752, "loss": 0.7728, "learning_rate": 9.372668948058276e-06, "epoch": 2.9401709401709404, "percentage": 24.54, "elapsed_time": "0:09:27", "remaining_time": "0:29:05"}
+{"current_steps": 440, "total_steps": 1752, "loss": 0.6978, "learning_rate": 9.323467077736513e-06, "epoch": 3.0085470085470085, "percentage": 25.11, "elapsed_time": "0:09:39", "remaining_time": "0:28:48"}
+{"current_steps": 450, "total_steps": 1752, "loss": 0.561, "learning_rate": 9.272547278876475e-06, "epoch": 3.076923076923077, "percentage": 25.68, "elapsed_time": "0:09:52", "remaining_time": "0:28:33"}
+{"current_steps": 460, "total_steps": 1752, "loss": 0.5354, "learning_rate": 9.219929784447232e-06, "epoch": 3.1452991452991452, "percentage": 26.26, "elapsed_time": "0:10:03", "remaining_time": "0:28:16"}
+{"current_steps": 470, "total_steps": 1752, "loss": 0.5613, "learning_rate": 9.16563550199674e-06, "epoch": 3.213675213675214, "percentage": 26.83, "elapsed_time": "0:10:15", "remaining_time": "0:27:59"}
+{"current_steps": 480, "total_steps": 1752, "loss": 0.576, "learning_rate": 9.109686005344258e-06, "epoch": 3.282051282051282, "percentage": 27.4, "elapsed_time": "0:10:27", "remaining_time": "0:27:41"}
+{"current_steps": 490, "total_steps": 1752, "loss": 0.492, "learning_rate": 9.052103526007976e-06, "epoch": 3.3504273504273505, "percentage": 27.97, "elapsed_time": "0:10:38", "remaining_time": "0:27:24"}
+{"current_steps": 500, "total_steps": 1752, "loss": 0.5087, "learning_rate": 8.992910944371343e-06, "epoch": 3.4188034188034186, "percentage": 28.54, "elapsed_time": "0:10:50", "remaining_time": "0:27:08"}
+{"current_steps": 510, "total_steps": 1752, "loss": 0.476, "learning_rate": 8.932131780591542e-06, "epoch": 3.4871794871794872, "percentage": 29.11, "elapsed_time": "0:11:01", "remaining_time": "0:26:51"}
+{"current_steps": 520, "total_steps": 1752, "loss": 0.4111, "learning_rate": 8.869790185253766e-06, "epoch": 3.5555555555555554, "percentage": 29.68, "elapsed_time": "0:11:13", "remaining_time": "0:26:34"}
+{"current_steps": 530, "total_steps": 1752, "loss": 0.4426, "learning_rate": 8.805910929774989e-06, "epoch": 3.623931623931624, "percentage": 30.25, "elapsed_time": "0:11:24", "remaining_time": "0:26:17"}
+{"current_steps": 540, "total_steps": 1752, "loss": 0.4171, "learning_rate": 8.740519396561045e-06, "epoch": 3.6923076923076925, "percentage": 30.82, "elapsed_time": "0:11:35", "remaining_time": "0:26:01"}
+{"current_steps": 550, "total_steps": 1752, "loss": 0.445, "learning_rate": 8.673641568920944e-06, "epoch": 3.7606837606837606, "percentage": 31.39, "elapsed_time": "0:11:47", "remaining_time": "0:25:45"}
+{"current_steps": 560, "total_steps": 1752, "loss": 0.4653, "learning_rate": 8.60530402074241e-06, "epoch": 3.8290598290598292, "percentage": 31.96, "elapsed_time": "0:11:58", "remaining_time": "0:25:28"}
+{"current_steps": 570, "total_steps": 1752, "loss": 0.4276, "learning_rate": 8.535533905932739e-06, "epoch": 3.8974358974358974, "percentage": 32.53, "elapsed_time": "0:12:08", "remaining_time": "0:25:11"}
+{"current_steps": 580, "total_steps": 1752, "loss": 0.423, "learning_rate": 8.46435894762922e-06, "epoch": 3.965811965811966, "percentage": 33.11, "elapsed_time": "0:12:19", "remaining_time": "0:24:54"}
+{"current_steps": 590, "total_steps": 1752, "loss": 0.3372, "learning_rate": 8.39180742718334e-06, "epoch": 4.034188034188034, "percentage": 33.68, "elapsed_time": "0:12:30", "remaining_time": "0:24:38"}
+{"current_steps": 600, "total_steps": 1752, "loss": 0.29, "learning_rate": 8.317908172923207e-06, "epoch": 4.102564102564102, "percentage": 34.25, "elapsed_time": "0:12:42", "remaining_time": "0:24:23"}
+{"current_steps": 610, "total_steps": 1752, "loss": 0.2464, "learning_rate": 8.242690548698611e-06, "epoch": 4.170940170940171, "percentage": 34.82, "elapsed_time": "0:12:52", "remaining_time": "0:24:06"}
+{"current_steps": 620, "total_steps": 1752, "loss": 0.2754, "learning_rate": 8.166184442213314e-06, "epoch": 4.239316239316239, "percentage": 35.39, "elapsed_time": "0:13:03", "remaining_time": "0:23:50"}
+{"current_steps": 630, "total_steps": 1752, "loss": 0.2699, "learning_rate": 8.088420253149173e-06, "epoch": 4.3076923076923075, "percentage": 35.96, "elapsed_time": "0:13:13", "remaining_time": "0:23:34"}
+{"current_steps": 640, "total_steps": 1752, "loss": 0.2621, "learning_rate": 8.009428881086836e-06, "epoch": 4.3760683760683765, "percentage": 36.53, "elapsed_time": "0:13:24", "remaining_time": "0:23:17"}
+{"current_steps": 650, "total_steps": 1752, "loss": 0.2688, "learning_rate": 7.9292417132278e-06, "epoch": 4.444444444444445, "percentage": 37.1, "elapsed_time": "0:13:35", "remaining_time": "0:23:02"}
+{"current_steps": 660, "total_steps": 1752, "loss": 0.2871, "learning_rate": 7.847890611922721e-06, "epoch": 4.512820512820513, "percentage": 37.67, "elapsed_time": "0:13:46", "remaining_time": "0:22:46"}
+{"current_steps": 670, "total_steps": 1752, "loss": 0.2439, "learning_rate": 7.76540790201091e-06, "epoch": 4.581196581196581, "percentage": 38.24, "elapsed_time": "0:13:56", "remaining_time": "0:22:30"}
+{"current_steps": 680, "total_steps": 1752, "loss": 0.2478, "learning_rate": 7.68182635797606e-06, "epoch": 4.64957264957265, "percentage": 38.81, "elapsed_time": "0:14:06", "remaining_time": "0:22:14"}
+{"current_steps": 690, "total_steps": 1752, "loss": 0.2385, "learning_rate": 7.597179190923343e-06, "epoch": 4.717948717948718, "percentage": 39.38, "elapsed_time": "0:14:16", "remaining_time": "0:21:58"}
+{"current_steps": 700, "total_steps": 1752, "loss": 0.2525, "learning_rate": 7.511500035382943e-06, "epoch": 4.786324786324786, "percentage": 39.95, "elapsed_time": "0:14:27", "remaining_time": "0:21:44"}
+{"current_steps": 710, "total_steps": 1752, "loss": 0.2448, "learning_rate": 7.424822935945416e-06, "epoch": 4.854700854700854, "percentage": 40.53, "elapsed_time": "0:14:37", "remaining_time": "0:21:28"}
+{"current_steps": 720, "total_steps": 1752, "loss": 0.2173, "learning_rate": 7.33718233373407e-06, "epoch": 4.923076923076923, "percentage": 41.1, "elapsed_time": "0:14:47", "remaining_time": "0:21:12"}
+{"current_steps": 730, "total_steps": 1752, "loss": 0.1926, "learning_rate": 7.248613052719793e-06, "epoch": 4.9914529914529915, "percentage": 41.67, "elapsed_time": "0:14:57", "remaining_time": "0:20:56"}
+{"current_steps": 740, "total_steps": 1752, "loss": 0.1754, "learning_rate": 7.159150285883757e-06, "epoch": 5.05982905982906, "percentage": 42.24, "elapsed_time": "0:15:07", "remaining_time": "0:20:41"}
+{"current_steps": 750, "total_steps": 1752, "loss": 0.1334, "learning_rate": 7.0688295812334995e-06, "epoch": 5.128205128205128, "percentage": 42.81, "elapsed_time": "0:15:18", "remaining_time": "0:20:26"}
+{"current_steps": 760, "total_steps": 1752, "loss": 0.147, "learning_rate": 6.977686827677926e-06, "epoch": 5.196581196581197, "percentage": 43.38, "elapsed_time": "0:15:27", "remaining_time": "0:20:11"}
+{"current_steps": 770, "total_steps": 1752, "loss": 0.1549, "learning_rate": 6.885758240766867e-06, "epoch": 5.264957264957265, "percentage": 43.95, "elapsed_time": "0:15:37", "remaining_time": "0:19:55"}
+{"current_steps": 780, "total_steps": 1752, "loss": 0.1312, "learning_rate": 6.793080348300834e-06, "epoch": 5.333333333333333, "percentage": 44.52, "elapsed_time": "0:15:47", "remaining_time": "0:19:40"}
+{"current_steps": 790, "total_steps": 1752, "loss": 0.1403, "learning_rate": 6.69968997581671e-06, "epoch": 5.401709401709402, "percentage": 45.09, "elapsed_time": "0:15:57", "remaining_time": "0:19:25"}
+{"current_steps": 800, "total_steps": 1752, "loss": 0.1237, "learning_rate": 6.6056242319551315e-06, "epoch": 5.47008547008547, "percentage": 45.66, "elapsed_time": "0:16:07", "remaining_time": "0:19:11"}
+{"current_steps": 810, "total_steps": 1752, "loss": 0.1233, "learning_rate": 6.510920493715381e-06, "epoch": 5.538461538461538, "percentage": 46.23, "elapsed_time": "0:16:16", "remaining_time": "0:18:55"}
+{"current_steps": 820, "total_steps": 1752, "loss": 0.1667, "learning_rate": 6.415616391603639e-06, "epoch": 5.6068376068376065, "percentage": 46.8, "elapsed_time": "0:16:26", "remaining_time": "0:18:40"}
+{"current_steps": 830, "total_steps": 1752, "loss": 0.1224, "learning_rate": 6.3197497946805205e-06, "epoch": 5.6752136752136755, "percentage": 47.37, "elapsed_time": "0:16:35", "remaining_time": "0:18:26"}
+{"current_steps": 840, "total_steps": 1752, "loss": 0.118, "learning_rate": 6.223358795513812e-06, "epoch": 5.743589743589744, "percentage": 47.95, "elapsed_time": "0:16:45", "remaining_time": "0:18:11"}
+{"current_steps": 850, "total_steps": 1752, "loss": 0.0897, "learning_rate": 6.126481695042392e-06, "epoch": 5.811965811965812, "percentage": 48.52, "elapsed_time": "0:16:55", "remaining_time": "0:17:57"}
+{"current_steps": 860, "total_steps": 1752, "loss": 0.1142, "learning_rate": 6.029156987357373e-06, "epoch": 5.880341880341881, "percentage": 49.09, "elapsed_time": "0:17:04", "remaining_time": "0:17:42"}
+{"current_steps": 870, "total_steps": 1752, "loss": 0.1542, "learning_rate": 5.931423344406478e-06, "epoch": 5.948717948717949, "percentage": 49.66, "elapsed_time": "0:17:13", "remaining_time": "0:17:27"}
+{"current_steps": 880, "total_steps": 1752, "loss": 0.0937, "learning_rate": 5.8333196006277536e-06, "epoch": 6.017094017094017, "percentage": 50.23, "elapsed_time": "0:17:22", "remaining_time": "0:17:13"}
+{"current_steps": 890, "total_steps": 1752, "loss": 0.0699, "learning_rate": 5.734884737518714e-06, "epoch": 6.085470085470085, "percentage": 50.8, "elapsed_time": "0:17:31", "remaining_time": "0:16:58"}
+{"current_steps": 900, "total_steps": 1752, "loss": 0.0757, "learning_rate": 5.636157868147054e-06, "epoch": 6.153846153846154, "percentage": 51.37, "elapsed_time": "0:17:41", "remaining_time": "0:16:44"}
+{"current_steps": 910, "total_steps": 1752, "loss": 0.0657, "learning_rate": 5.537178221609088e-06, "epoch": 6.222222222222222, "percentage": 51.94, "elapsed_time": "0:17:50", "remaining_time": "0:16:30"}
+{"current_steps": 920, "total_steps": 1752, "loss": 0.0838, "learning_rate": 5.437985127442065e-06, "epoch": 6.2905982905982905, "percentage": 52.51, "elapsed_time": "0:17:59", "remaining_time": "0:16:16"}
+{"current_steps": 930, "total_steps": 1752, "loss": 0.0876, "learning_rate": 5.338617999996603e-06, "epoch": 6.358974358974359, "percentage": 53.08, "elapsed_time": "0:18:08", "remaining_time": "0:16:01"}
+{"current_steps": 940, "total_steps": 1752, "loss": 0.0652, "learning_rate": 5.239116322775392e-06, "epoch": 6.427350427350428, "percentage": 53.65, "elapsed_time": "0:18:17", "remaining_time": "0:15:47"}
+{"current_steps": 950, "total_steps": 1752, "loss": 0.0843, "learning_rate": 5.139519632744443e-06, "epoch": 6.495726495726496, "percentage": 54.22, "elapsed_time": "0:18:26", "remaining_time": "0:15:33"}
+{"current_steps": 960, "total_steps": 1752, "loss": 0.0677, "learning_rate": 5.039867504623084e-06, "epoch": 6.564102564102564, "percentage": 54.79, "elapsed_time": "0:18:34", "remaining_time": "0:15:19"}
+{"current_steps": 970, "total_steps": 1752, "loss": 0.0764, "learning_rate": 4.940199535158954e-06, "epoch": 6.632478632478632, "percentage": 55.37, "elapsed_time": "0:18:43", "remaining_time": "0:15:05"}
+{"current_steps": 980, "total_steps": 1752, "loss": 0.0642, "learning_rate": 4.8405553273942415e-06, "epoch": 6.700854700854701, "percentage": 55.94, "elapsed_time": "0:18:51", "remaining_time": "0:14:51"}
+{"current_steps": 990, "total_steps": 1752, "loss": 0.0444, "learning_rate": 4.740974474929438e-06, "epoch": 6.769230769230769, "percentage": 56.51, "elapsed_time": "0:19:00", "remaining_time": "0:14:37"}
+{"current_steps": 1000, "total_steps": 1752, "loss": 0.0713, "learning_rate": 4.641496546190813e-06, "epoch": 6.837606837606837, "percentage": 57.08, "elapsed_time": "0:19:09", "remaining_time": "0:14:24"}
+{"current_steps": 1000, "total_steps": 1752, "eval_loss": 0.19593119621276855, "epoch": 6.837606837606837, "percentage": 57.08, "elapsed_time": "0:19:14", "remaining_time": "0:14:28"}
+{"current_steps": 1010, "total_steps": 1752, "loss": 0.0494, "learning_rate": 4.542161068707927e-06, "epoch": 6.905982905982906, "percentage": 57.65, "elapsed_time": "0:19:22", "remaining_time": "0:14:14"}
+{"current_steps": 1020, "total_steps": 1752, "loss": 0.0492, "learning_rate": 4.443007513407368e-06, "epoch": 6.9743589743589745, "percentage": 58.22, "elapsed_time": "0:19:30", "remaining_time": "0:14:00"}
+{"current_steps": 1030, "total_steps": 1752, "loss": 0.1084, "learning_rate": 4.344075278928989e-06, "epoch": 7.042735042735043, "percentage": 58.79, "elapsed_time": "0:19:39", "remaining_time": "0:13:46"}
+{"current_steps": 1040, "total_steps": 1752, "loss": 0.0605, "learning_rate": 4.245403675970877e-06, "epoch": 7.111111111111111, "percentage": 59.36, "elapsed_time": "0:19:47", "remaining_time": "0:13:33"}
+{"current_steps": 1050, "total_steps": 1752, "loss": 0.0422, "learning_rate": 4.147031911669243e-06, "epoch": 7.17948717948718, "percentage": 59.93, "elapsed_time": "0:19:56", "remaining_time": "0:13:19"}
+{"current_steps": 1060, "total_steps": 1752, "loss": 0.0388, "learning_rate": 4.048999074019493e-06, "epoch": 7.247863247863248, "percentage": 60.5, "elapsed_time": "0:20:04", "remaining_time": "0:13:06"}
+{"current_steps": 1070, "total_steps": 1752, "loss": 0.0295, "learning_rate": 3.951344116344606e-06, "epoch": 7.316239316239316, "percentage": 61.07, "elapsed_time": "0:20:11", "remaining_time": "0:12:52"}
+{"current_steps": 1080, "total_steps": 1752, "loss": 0.0545, "learning_rate": 3.854105841817056e-06, "epoch": 7.384615384615385, "percentage": 61.64, "elapsed_time": "0:20:19", "remaining_time": "0:12:39"}
+{"current_steps": 1090, "total_steps": 1752, "loss": 0.0337, "learning_rate": 3.7573228880403734e-06, "epoch": 7.452991452991453, "percentage": 62.21, "elapsed_time": "0:20:27", "remaining_time": "0:12:25"}
+{"current_steps": 1100, "total_steps": 1752, "loss": 0.0507, "learning_rate": 3.661033711696501e-06, "epoch": 7.521367521367521, "percentage": 62.79, "elapsed_time": "0:20:35", "remaining_time": "0:12:12"}
+{"current_steps": 1110, "total_steps": 1752, "loss": 0.0419, "learning_rate": 3.5652765732650523e-06, "epoch": 7.589743589743589, "percentage": 63.36, "elapsed_time": "0:20:43", "remaining_time": "0:11:59"}
+{"current_steps": 1120, "total_steps": 1752, "loss": 0.0423, "learning_rate": 3.4700895218205026e-06, "epoch": 7.6581196581196584, "percentage": 63.93, "elapsed_time": "0:20:51", "remaining_time": "0:11:46"}
+{"current_steps": 1130, "total_steps": 1752, "loss": 0.0488, "learning_rate": 3.375510379913418e-06, "epoch": 7.726495726495727, "percentage": 64.5, "elapsed_time": "0:20:58", "remaining_time": "0:11:32"}
+{"current_steps": 1140, "total_steps": 1752, "loss": 0.0388, "learning_rate": 3.2815767285416576e-06, "epoch": 7.794871794871795, "percentage": 65.07, "elapsed_time": "0:21:06", "remaining_time": "0:11:20"}
+{"current_steps": 1150, "total_steps": 1752, "loss": 0.0197, "learning_rate": 3.188325892217587e-06, "epoch": 7.863247863247864, "percentage": 65.64, "elapsed_time": "0:21:14", "remaining_time": "0:11:07"}
+{"current_steps": 1160, "total_steps": 1752, "loss": 0.0326, "learning_rate": 3.0957949241371845e-06, "epoch": 7.931623931623932, "percentage": 66.21, "elapsed_time": "0:21:21", "remaining_time": "0:10:54"}
+{"current_steps": 1170, "total_steps": 1752, "loss": 0.0383, "learning_rate": 3.0040205914569664e-06, "epoch": 8.0, "percentage": 66.78, "elapsed_time": "0:21:29", "remaining_time": "0:10:41"}
+{"current_steps": 1180, "total_steps": 1752, "loss": 0.0296, "learning_rate": 2.913039360684565e-06, "epoch": 8.068376068376068, "percentage": 67.35, "elapsed_time": "0:21:36", "remaining_time": "0:10:28"}
+{"current_steps": 1190, "total_steps": 1752, "loss": 0.0564, "learning_rate": 2.822887383188775e-06, "epoch": 8.136752136752136, "percentage": 67.92, "elapsed_time": "0:21:44", "remaining_time": "0:10:15"}
+{"current_steps": 1200, "total_steps": 1752, "loss": 0.0295, "learning_rate": 2.7336004808348094e-06, "epoch": 8.205128205128204, "percentage": 68.49, "elapsed_time": "0:21:51", "remaining_time": "0:10:03"}
+{"current_steps": 1210, "total_steps": 1752, "loss": 0.0194, "learning_rate": 2.645214131750498e-06, "epoch": 8.273504273504274, "percentage": 69.06, "elapsed_time": "0:21:58", "remaining_time": "0:09:50"}
+{"current_steps": 1220, "total_steps": 1752, "loss": 0.0261, "learning_rate": 2.5577634562290567e-06, "epoch": 8.341880341880342, "percentage": 69.63, "elapsed_time": "0:22:05", "remaining_time": "0:09:38"}
+{"current_steps": 1230, "total_steps": 1752, "loss": 0.0237, "learning_rate": 2.4712832027740545e-06, "epoch": 8.41025641025641, "percentage": 70.21, "elapsed_time": "0:22:12", "remaining_time": "0:09:25"}
+{"current_steps": 1240, "total_steps": 1752, "loss": 0.037, "learning_rate": 2.385807734292097e-06, "epoch": 8.478632478632479, "percentage": 70.78, "elapsed_time": "0:22:20", "remaining_time": "0:09:13"}
+{"current_steps": 1250, "total_steps": 1752, "loss": 0.0241, "learning_rate": 2.3013710144387374e-06, "epoch": 8.547008547008547, "percentage": 71.35, "elapsed_time": "0:22:27", "remaining_time": "0:09:01"}
+{"current_steps": 1260, "total_steps": 1752, "loss": 0.0258, "learning_rate": 2.218006594123028e-06, "epoch": 8.615384615384615, "percentage": 71.92, "elapsed_time": "0:22:34", "remaining_time": "0:08:48"}
+{"current_steps": 1270, "total_steps": 1752, "loss": 0.0361, "learning_rate": 2.1357475981760704e-06, "epoch": 8.683760683760683, "percentage": 72.49, "elapsed_time": "0:22:41", "remaining_time": "0:08:36"}
+{"current_steps": 1280, "total_steps": 1752, "loss": 0.0243, "learning_rate": 2.0546267121888863e-06, "epoch": 8.752136752136753, "percentage": 73.06, "elapsed_time": "0:22:47", "remaining_time": "0:08:24"}
+{"current_steps": 1290, "total_steps": 1752, "loss": 0.0404, "learning_rate": 1.9746761695247803e-06, "epoch": 8.820512820512821, "percentage": 73.63, "elapsed_time": "0:22:54", "remaining_time": "0:08:12"}
+{"current_steps": 1300, "total_steps": 1752, "loss": 0.0284, "learning_rate": 1.8959277385114516e-06, "epoch": 8.88888888888889, "percentage": 74.2, "elapsed_time": "0:23:01", "remaining_time": "0:08:00"}
+{"current_steps": 1310, "total_steps": 1752, "loss": 0.028, "learning_rate": 1.8184127098178288e-06, "epoch": 8.957264957264957, "percentage": 74.77, "elapsed_time": "0:23:08", "remaining_time": "0:07:48"}
+{"current_steps": 1320, "total_steps": 1752, "loss": 0.0174, "learning_rate": 1.7421618840207576e-06, "epoch": 9.025641025641026, "percentage": 75.34, "elapsed_time": "0:23:14", "remaining_time": "0:07:36"}
+{"current_steps": 1330, "total_steps": 1752, "loss": 0.0293, "learning_rate": 1.667205559366372e-06, "epoch": 9.094017094017094, "percentage": 75.91, "elapsed_time": "0:23:21", "remaining_time": "0:07:24"}
+{"current_steps": 1340, "total_steps": 1752, "loss": 0.0459, "learning_rate": 1.5935735197311204e-06, "epoch": 9.162393162393162, "percentage": 76.48, "elapsed_time": "0:23:28", "remaining_time": "0:07:12"}
+{"current_steps": 1350, "total_steps": 1752, "loss": 0.0197, "learning_rate": 1.5212950227871292e-06, "epoch": 9.23076923076923, "percentage": 77.05, "elapsed_time": "0:23:34", "remaining_time": "0:07:01"}
+{"current_steps": 1360, "total_steps": 1752, "loss": 0.0208, "learning_rate": 1.4503987883766857e-06, "epoch": 9.2991452991453, "percentage": 77.63, "elapsed_time": "0:23:40", "remaining_time": "0:06:49"}
+{"current_steps": 1370, "total_steps": 1752, "loss": 0.0332, "learning_rate": 1.3809129871004113e-06, "epoch": 9.367521367521368, "percentage": 78.2, "elapsed_time": "0:23:47", "remaining_time": "0:06:37"}
+{"current_steps": 1380, "total_steps": 1752, "loss": 0.0186, "learning_rate": 1.312865229123681e-06, "epoch": 9.435897435897436, "percentage": 78.77, "elapsed_time": "0:23:53", "remaining_time": "0:06:26"}
+{"current_steps": 1390, "total_steps": 1752, "loss": 0.0365, "learning_rate": 1.2462825532057394e-06, "epoch": 9.504273504273504, "percentage": 79.34, "elapsed_time": "0:23:59", "remaining_time": "0:06:14"}
+{"current_steps": 1400, "total_steps": 1752, "loss": 0.0172, "learning_rate": 1.1811914159558374e-06, "epoch": 9.572649572649572, "percentage": 79.91, "elapsed_time": "0:24:05", "remaining_time": "0:06:03"}
+{"current_steps": 1410, "total_steps": 1752, "loss": 0.0307, "learning_rate": 1.117617681320729e-06, "epoch": 9.64102564102564, "percentage": 80.48, "elapsed_time": "0:24:11", "remaining_time": "0:05:52"}
+{"current_steps": 1420, "total_steps": 1752, "loss": 0.0138, "learning_rate": 1.0555866103076212e-06, "epoch": 9.709401709401709, "percentage": 81.05, "elapsed_time": "0:24:17", "remaining_time": "0:05:40"}
+{"current_steps": 1430, "total_steps": 1752, "loss": 0.0204, "learning_rate": 9.951228509467248e-07, "epoch": 9.777777777777779, "percentage": 81.62, "elapsed_time": "0:24:23", "remaining_time": "0:05:29"}
+{"current_steps": 1440, "total_steps": 1752, "loss": 0.017, "learning_rate": 9.362504284973683e-07, "epoch": 9.846153846153847, "percentage": 82.19, "elapsed_time": "0:24:29", "remaining_time": "0:05:18"}
+{"current_steps": 1450, "total_steps": 1752, "loss": 0.0236, "learning_rate": 8.789927359015643e-07, "epoch": 9.914529914529915, "percentage": 82.76, "elapsed_time": "0:24:35", "remaining_time": "0:05:07"}
+{"current_steps": 1460, "total_steps": 1752, "loss": 0.0234, "learning_rate": 8.233725244888291e-07, "epoch": 9.982905982905983, "percentage": 83.33, "elapsed_time": "0:24:41", "remaining_time": "0:04:56"}
+{"current_steps": 1470, "total_steps": 1752, "loss": 0.015, "learning_rate": 7.694118949359553e-07, "epoch": 10.051282051282051, "percentage": 83.9, "elapsed_time": "0:24:46", "remaining_time": "0:04:45"}
+{"current_steps": 1480, "total_steps": 1752, "loss": 0.0209, "learning_rate": 7.171322884852988e-07, "epoch": 10.11965811965812, "percentage": 84.47, "elapsed_time": "0:24:52", "remaining_time": "0:04:34"}
+{"current_steps": 1490, "total_steps": 1752, "loss": 0.0156, "learning_rate": 6.665544784251232e-07, "epoch": 10.188034188034187, "percentage": 85.05, "elapsed_time": "0:24:57", "remaining_time": "0:04:23"}
+{"current_steps": 1500, "total_steps": 1752, "loss": 0.0245, "learning_rate": 6.176985618353282e-07, "epoch": 10.256410256410255, "percentage": 85.62, "elapsed_time": "0:25:03", "remaining_time": "0:04:12"}
+{"current_steps": 1510, "total_steps": 1752, "loss": 0.0143, "learning_rate": 5.705839516018818e-07, "epoch": 10.324786324786325, "percentage": 86.19, "elapsed_time": "0:25:09", "remaining_time": "0:04:01"}
+{"current_steps": 1520, "total_steps": 1752, "loss": 0.0279, "learning_rate": 5.252293687031196e-07, "epoch": 10.393162393162394, "percentage": 86.76, "elapsed_time": "0:25:14", "remaining_time": "0:03:51"}
+{"current_steps": 1530, "total_steps": 1752, "loss": 0.0215, "learning_rate": 4.816528347709614e-07, "epoch": 10.461538461538462, "percentage": 87.33, "elapsed_time": "0:25:19", "remaining_time": "0:03:40"}
+{"current_steps": 1540, "total_steps": 1752, "loss": 0.0145, "learning_rate": 4.398716649300311e-07, "epoch": 10.52991452991453, "percentage": 87.9, "elapsed_time": "0:25:24", "remaining_time": "0:03:29"}
+{"current_steps": 1550, "total_steps": 1752, "loss": 0.0196, "learning_rate": 3.999024609174812e-07, "epoch": 10.598290598290598, "percentage": 88.47, "elapsed_time": "0:25:30", "remaining_time": "0:03:19"}
+{"current_steps": 1560, "total_steps": 1752, "loss": 0.0271, "learning_rate": 3.61761104486314e-07, "epoch": 10.666666666666666, "percentage": 89.04, "elapsed_time": "0:25:35", "remaining_time": "0:03:08"}
+{"current_steps": 1570, "total_steps": 1752, "loss": 0.0179, "learning_rate": 3.2546275109475554e-07, "epoch": 10.735042735042736, "percentage": 89.61, "elapsed_time": "0:25:40", "remaining_time": "0:02:58"}
+{"current_steps": 1580, "total_steps": 1752, "loss": 0.0228, "learning_rate": 2.9102182388425106e-07, "epoch": 10.803418803418804, "percentage": 90.18, "elapsed_time": "0:25:45", "remaining_time": "0:02:48"}
+{"current_steps": 1590, "total_steps": 1752, "loss": 0.0217, "learning_rate": 2.5845200794842154e-07, "epoch": 10.871794871794872, "percentage": 90.75, "elapsed_time": "0:25:50", "remaining_time": "0:02:37"}
+{"current_steps": 1600, "total_steps": 1752, "loss": 0.0212, "learning_rate": 2.2776624489530664e-07, "epoch": 10.94017094017094, "percentage": 91.32, "elapsed_time": "0:25:56", "remaining_time": "0:02:27"}
+{"current_steps": 1610, "total_steps": 1752, "loss": 0.0492, "learning_rate": 1.9897672770501198e-07, "epoch": 11.008547008547009, "percentage": 91.89, "elapsed_time": "0:26:11", "remaining_time": "0:02:18"}
+{"current_steps": 1620, "total_steps": 1752, "loss": 0.0265, "learning_rate": 1.7209489588483396e-07, "epoch": 11.076923076923077, "percentage": 92.47, "elapsed_time": "0:26:25", "remaining_time": "0:02:09"}
+{"current_steps": 1630, "total_steps": 1752, "loss": 0.0188, "learning_rate": 1.4713143092377534e-07, "epoch": 11.145299145299145, "percentage": 93.04, "elapsed_time": "0:26:40", "remaining_time": "0:01:59"}
+{"current_steps": 1640, "total_steps": 1752, "loss": 0.025, "learning_rate": 1.2409625204825802e-07, "epoch": 11.213675213675213, "percentage": 93.61, "elapsed_time": "0:26:54", "remaining_time": "0:01:50"}
+{"current_steps": 1650, "total_steps": 1752, "loss": 0.0186, "learning_rate": 1.0299851228072089e-07, "epoch": 11.282051282051283, "percentage": 94.18, "elapsed_time": "0:27:09", "remaining_time": "0:01:40"}
+{"current_steps": 1660, "total_steps": 1752, "loss": 0.0257, "learning_rate": 8.384659480266733e-08, "epoch": 11.350427350427351, "percentage": 94.75, "elapsed_time": "0:27:23", "remaining_time": "0:01:31"}
+{"current_steps": 1670, "total_steps": 1752, "loss": 0.0213, "learning_rate": 6.664810962361268e-08, "epoch": 11.418803418803419, "percentage": 95.32, "elapsed_time": "0:27:36", "remaining_time": "0:01:21"}
+{"current_steps": 1680, "total_steps": 1752, "loss": 0.0137, "learning_rate": 5.1409890557246876e-08, "epoch": 11.487179487179487, "percentage": 95.89, "elapsed_time": "0:27:50", "remaining_time": "0:01:11"}
+{"current_steps": 1690, "total_steps": 1752, "loss": 0.0164, "learning_rate": 3.813799250602046e-08, "epoch": 11.555555555555555, "percentage": 96.46, "elapsed_time": "0:28:04", "remaining_time": "0:01:01"}
+{"current_steps": 1700, "total_steps": 1752, "loss": 0.0197, "learning_rate": 2.683768905523243e-08, "epoch": 11.623931623931623, "percentage": 97.03, "elapsed_time": "0:28:19", "remaining_time": "0:00:51"}
+{"current_steps": 1710, "total_steps": 1752, "loss": 0.0246, "learning_rate": 1.7513470377570896e-08, "epoch": 11.692307692307692, "percentage": 97.6, "elapsed_time": "0:28:32", "remaining_time": "0:00:42"}
+{"current_steps": 1720, "total_steps": 1752, "loss": 0.0295, "learning_rate": 1.016904144894304e-08, "epoch": 11.760683760683762, "percentage": 98.17, "elapsed_time": "0:28:46", "remaining_time": "0:00:32"}
+{"current_steps": 1730, "total_steps": 1752, "loss": 0.029, "learning_rate": 4.807320576307728e-09, "epoch": 11.82905982905983, "percentage": 98.74, "elapsed_time": "0:28:59", "remaining_time": "0:00:22"}
+{"current_steps": 1740, "total_steps": 1752, "loss": 0.0177, "learning_rate": 1.4304382380819771e-09, "epoch": 11.897435897435898, "percentage": 99.32, "elapsed_time": "0:29:13", "remaining_time": "0:00:12"}
+{"current_steps": 1750, "total_steps": 1752, "loss": 0.0261, "learning_rate": 3.9736237600895846e-11, "epoch": 11.965811965811966, "percentage": 99.89, "elapsed_time": "0:29:27", "remaining_time": "0:00:02"}
+{"current_steps": 1752, "total_steps": 1752, "epoch": 11.97948717948718, "percentage": 100.0, "elapsed_time": "0:30:38", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1275 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.97948717948718,
+  "eval_steps": 1000,
+  "global_step": 1752,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 10.4375,
+      "learning_rate": 5.681818181818182e-07,
+      "loss": 2.6042,
+      "step": 10
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 12.75,
+      "learning_rate": 1.1363636363636364e-06,
+      "loss": 2.577,
+      "step": 20
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.7045454545454546e-06,
+      "loss": 2.4842,
+      "step": 30
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 15.4375,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 2.4127,
+      "step": 40
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 21.75,
+      "learning_rate": 2.8409090909090916e-06,
+      "loss": 2.2065,
+      "step": 50
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 28.125,
+      "learning_rate": 3.409090909090909e-06,
+      "loss": 2.2638,
+      "step": 60
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 29.5,
+      "learning_rate": 3.9772727272727275e-06,
+      "loss": 2.0591,
+      "step": 70
+    },
+    {
+      "epoch": 0.5470085470085471,
+      "grad_norm": 20.5,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.9693,
+      "step": 80
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 19.875,
+      "learning_rate": 5.113636363636364e-06,
+      "loss": 1.9559,
+      "step": 90
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 5.125,
+      "learning_rate": 5.681818181818183e-06,
+      "loss": 1.8579,
+      "step": 100
+    },
+    {
+      "epoch": 0.7521367521367521,
+      "grad_norm": 5.5625,
+      "learning_rate": 6.25e-06,
+      "loss": 1.8601,
+      "step": 110
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.7222,
+      "step": 120
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 6.03125,
+      "learning_rate": 7.386363636363637e-06,
+      "loss": 1.7724,
+      "step": 130
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 5.6875,
+      "learning_rate": 7.954545454545455e-06,
+      "loss": 1.8647,
+      "step": 140
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 5.0625,
+      "learning_rate": 8.522727272727273e-06,
+      "loss": 1.7017,
+      "step": 150
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 4.5625,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.6883,
+      "step": 160
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 5.3125,
+      "learning_rate": 9.65909090909091e-06,
+      "loss": 1.5485,
+      "step": 170
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.999841055681184e-06,
+      "loss": 1.5548,
+      "step": 180
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.998053048145735e-06,
+      "loss": 1.602,
+      "step": 190
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 3.671875,
+      "learning_rate": 9.994279065509094e-06,
+      "loss": 1.5151,
+      "step": 200
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.988520607362297e-06,
+      "loss": 1.4208,
+      "step": 210
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 5.90625,
+      "learning_rate": 9.98077996182722e-06,
+      "loss": 1.4954,
+      "step": 220
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.971060204647384e-06,
+      "loss": 1.3399,
+      "step": 230
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 5.5,
+      "learning_rate": 9.959365197965824e-06,
+      "loss": 1.2554,
+      "step": 240
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 6.65625,
+      "learning_rate": 9.945699588790455e-06,
+      "loss": 1.3161,
+      "step": 250
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 7.5625,
+      "learning_rate": 9.930068807147585e-06,
+      "loss": 1.3603,
+      "step": 260
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 6.375,
+      "learning_rate": 9.912479063924309e-06,
+      "loss": 1.2576,
+      "step": 270
+    },
+    {
+      "epoch": 1.9145299145299144,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.8929373484006e-06,
+      "loss": 1.207,
+      "step": 280
+    },
+    {
+      "epoch": 1.982905982905983,
+      "grad_norm": 4.90625,
+      "learning_rate": 9.871451425472128e-06,
+      "loss": 1.232,
+      "step": 290
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 7.125,
+      "learning_rate": 9.848029832564875e-06,
+      "loss": 1.0106,
+      "step": 300
+    },
+    {
+      "epoch": 2.1196581196581197,
+      "grad_norm": 6.65625,
+      "learning_rate": 9.822681876242797e-06,
+      "loss": 0.9484,
+      "step": 310
+    },
+    {
+      "epoch": 2.1880341880341883,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.795417628509857e-06,
+      "loss": 1.0094,
+      "step": 320
+    },
+    {
+      "epoch": 2.2564102564102564,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.766247922807927e-06,
+      "loss": 0.9317,
+      "step": 330
+    },
+    {
+      "epoch": 2.324786324786325,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.73518434971211e-06,
+      "loss": 0.8936,
+      "step": 340
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 7.375,
+      "learning_rate": 9.702239252325237e-06,
+      "loss": 0.9004,
+      "step": 350
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.667425721373333e-06,
+      "loss": 0.9335,
+      "step": 360
+    },
+    {
+      "epoch": 2.52991452991453,
+      "grad_norm": 7.0625,
+      "learning_rate": 9.630757590004023e-06,
+      "loss": 0.8982,
+      "step": 370
+    },
+    {
+      "epoch": 2.5982905982905984,
+      "grad_norm": 4.40625,
+      "learning_rate": 9.592249428289935e-06,
+      "loss": 0.8541,
+      "step": 380
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 6.5625,
+      "learning_rate": 9.551916537439282e-06,
+      "loss": 0.8105,
+      "step": 390
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 5.125,
+      "learning_rate": 9.50977494371594e-06,
+      "loss": 0.8308,
+      "step": 400
+    },
+    {
+      "epoch": 2.8034188034188032,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.465841392071396e-06,
+      "loss": 0.8515,
+      "step": 410
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.420133339491171e-06,
+      "loss": 0.6671,
+      "step": 420
+    },
+    {
+      "epoch": 2.9401709401709404,
+      "grad_norm": 6.21875,
+      "learning_rate": 9.372668948058276e-06,
+      "loss": 0.7728,
+      "step": 430
+    },
+    {
+      "epoch": 3.0085470085470085,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.323467077736513e-06,
+      "loss": 0.6978,
+      "step": 440
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 5.9375,
+      "learning_rate": 9.272547278876475e-06,
+      "loss": 0.561,
+      "step": 450
+    },
+    {
+      "epoch": 3.1452991452991452,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.219929784447232e-06,
+      "loss": 0.5354,
+      "step": 460
+    },
+    {
+      "epoch": 3.213675213675214,
+      "grad_norm": 4.90625,
+      "learning_rate": 9.16563550199674e-06,
+      "loss": 0.5613,
+      "step": 470
+    },
+    {
+      "epoch": 3.282051282051282,
+      "grad_norm": 6.5,
+      "learning_rate": 9.109686005344258e-06,
+      "loss": 0.576,
+      "step": 480
+    },
+    {
+      "epoch": 3.3504273504273505,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.052103526007976e-06,
+      "loss": 0.492,
+      "step": 490
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 7.5,
+      "learning_rate": 8.992910944371343e-06,
+      "loss": 0.5087,
+      "step": 500
+    },
+    {
+      "epoch": 3.4871794871794872,
+      "grad_norm": 6.59375,
+      "learning_rate": 8.932131780591542e-06,
+      "loss": 0.476,
+      "step": 510
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 4.4375,
+      "learning_rate": 8.869790185253766e-06,
+      "loss": 0.4111,
+      "step": 520
+    },
+    {
+      "epoch": 3.623931623931624,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.805910929774989e-06,
+      "loss": 0.4426,
+      "step": 530
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 4.46875,
+      "learning_rate": 8.740519396561045e-06,
+      "loss": 0.4171,
+      "step": 540
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 5.28125,
+      "learning_rate": 8.673641568920944e-06,
+      "loss": 0.445,
+      "step": 550
+    },
+    {
+      "epoch": 3.8290598290598292,
+      "grad_norm": 5.75,
+      "learning_rate": 8.60530402074241e-06,
+      "loss": 0.4653,
+      "step": 560
+    },
+    {
+      "epoch": 3.8974358974358974,
+      "grad_norm": 2.984375,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.4276,
+      "step": 570
+    },
+    {
+      "epoch": 3.965811965811966,
+      "grad_norm": 3.9375,
+      "learning_rate": 8.46435894762922e-06,
+      "loss": 0.423,
+      "step": 580
+    },
+    {
+      "epoch": 4.034188034188034,
+      "grad_norm": 2.96875,
+      "learning_rate": 8.39180742718334e-06,
+      "loss": 0.3372,
+      "step": 590
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 3.25,
+      "learning_rate": 8.317908172923207e-06,
+      "loss": 0.29,
+      "step": 600
+    },
+    {
+      "epoch": 4.170940170940171,
+      "grad_norm": 3.84375,
+      "learning_rate": 8.242690548698611e-06,
+      "loss": 0.2464,
+      "step": 610
+    },
+    {
+      "epoch": 4.239316239316239,
+      "grad_norm": 4.28125,
+      "learning_rate": 8.166184442213314e-06,
+      "loss": 0.2754,
+      "step": 620
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 2.796875,
+      "learning_rate": 8.088420253149173e-06,
+      "loss": 0.2699,
+      "step": 630
+    },
+    {
+      "epoch": 4.3760683760683765,
+      "grad_norm": 2.796875,
+      "learning_rate": 8.009428881086836e-06,
+      "loss": 0.2621,
+      "step": 640
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 4.125,
+      "learning_rate": 7.9292417132278e-06,
+      "loss": 0.2688,
+      "step": 650
+    },
+    {
+      "epoch": 4.512820512820513,
+      "grad_norm": 2.9375,
+      "learning_rate": 7.847890611922721e-06,
+      "loss": 0.2871,
+      "step": 660
+    },
+    {
+      "epoch": 4.581196581196581,
+      "grad_norm": 2.78125,
+      "learning_rate": 7.76540790201091e-06,
+      "loss": 0.2439,
+      "step": 670
+    },
+    {
+      "epoch": 4.64957264957265,
+      "grad_norm": 5.5625,
+      "learning_rate": 7.68182635797606e-06,
+      "loss": 0.2478,
+      "step": 680
+    },
+    {
+      "epoch": 4.717948717948718,
+      "grad_norm": 5.09375,
+      "learning_rate": 7.597179190923343e-06,
+      "loss": 0.2385,
+      "step": 690
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 2.53125,
+      "learning_rate": 7.511500035382943e-06,
+      "loss": 0.2525,
+      "step": 700
+    },
+    {
+      "epoch": 4.854700854700854,
+      "grad_norm": 3.734375,
+      "learning_rate": 7.424822935945416e-06,
+      "loss": 0.2448,
+      "step": 710
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 2.453125,
+      "learning_rate": 7.33718233373407e-06,
+      "loss": 0.2173,
+      "step": 720
+    },
+    {
+      "epoch": 4.9914529914529915,
+      "grad_norm": 2.0625,
+      "learning_rate": 7.248613052719793e-06,
+      "loss": 0.1926,
+      "step": 730
+    },
+    {
+      "epoch": 5.05982905982906,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.159150285883757e-06,
+      "loss": 0.1754,
+      "step": 740
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 2.4375,
+      "learning_rate": 7.0688295812334995e-06,
+      "loss": 0.1334,
+      "step": 750
+    },
+    {
+      "epoch": 5.196581196581197,
+      "grad_norm": 1.84375,
+      "learning_rate": 6.977686827677926e-06,
+      "loss": 0.147,
+      "step": 760
+    },
+    {
+      "epoch": 5.264957264957265,
+      "grad_norm": 1.65625,
+      "learning_rate": 6.885758240766867e-06,
+      "loss": 0.1549,
+      "step": 770
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.793080348300834e-06,
+      "loss": 0.1312,
+      "step": 780
+    },
+    {
+      "epoch": 5.401709401709402,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.69968997581671e-06,
+      "loss": 0.1403,
+      "step": 790
+    },
+    {
+      "epoch": 5.47008547008547,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.6056242319551315e-06,
+      "loss": 0.1237,
+      "step": 800
+    },
+    {
+      "epoch": 5.538461538461538,
+      "grad_norm": 3.046875,
+      "learning_rate": 6.510920493715381e-06,
+      "loss": 0.1233,
+      "step": 810
+    },
+    {
+      "epoch": 5.6068376068376065,
+      "grad_norm": 0.87109375,
+      "learning_rate": 6.415616391603639e-06,
+      "loss": 0.1667,
+      "step": 820
+    },
+    {
+      "epoch": 5.6752136752136755,
+      "grad_norm": 1.25,
+      "learning_rate": 6.3197497946805205e-06,
+      "loss": 0.1224,
+      "step": 830
+    },
+    {
+      "epoch": 5.743589743589744,
+      "grad_norm": 2.421875,
+      "learning_rate": 6.223358795513812e-06,
+      "loss": 0.118,
+      "step": 840
+    },
+    {
+      "epoch": 5.811965811965812,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.126481695042392e-06,
+      "loss": 0.0897,
+      "step": 850
+    },
+    {
+      "epoch": 5.880341880341881,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.029156987357373e-06,
+      "loss": 0.1142,
+      "step": 860
+    },
+    {
+      "epoch": 5.948717948717949,
+      "grad_norm": 1.78125,
+      "learning_rate": 5.931423344406478e-06,
+      "loss": 0.1542,
+      "step": 870
+    },
+    {
+      "epoch": 6.017094017094017,
+      "grad_norm": 1.2890625,
+      "learning_rate": 5.8333196006277536e-06,
+      "loss": 0.0937,
+      "step": 880
+    },
+    {
+      "epoch": 6.085470085470085,
+      "grad_norm": 1.75,
+      "learning_rate": 5.734884737518714e-06,
+      "loss": 0.0699,
+      "step": 890
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.96484375,
+      "learning_rate": 5.636157868147054e-06,
+      "loss": 0.0757,
+      "step": 900
+    },
+    {
+      "epoch": 6.222222222222222,
+      "grad_norm": 0.84765625,
+      "learning_rate": 5.537178221609088e-06,
+      "loss": 0.0657,
+      "step": 910
+    },
+    {
+      "epoch": 6.2905982905982905,
+      "grad_norm": 2.328125,
+      "learning_rate": 5.437985127442065e-06,
+      "loss": 0.0838,
+      "step": 920
+    },
+    {
+      "epoch": 6.358974358974359,
+      "grad_norm": 1.015625,
+      "learning_rate": 5.338617999996603e-06,
+      "loss": 0.0876,
+      "step": 930
+    },
+    {
+      "epoch": 6.427350427350428,
+      "grad_norm": 1.0,
+      "learning_rate": 5.239116322775392e-06,
+      "loss": 0.0652,
+      "step": 940
+    },
+    {
+      "epoch": 6.495726495726496,
+      "grad_norm": 0.96484375,
+      "learning_rate": 5.139519632744443e-06,
+      "loss": 0.0843,
+      "step": 950
+    },
+    {
+      "epoch": 6.564102564102564,
+      "grad_norm": 1.3828125,
+      "learning_rate": 5.039867504623084e-06,
+      "loss": 0.0677,
+      "step": 960
+    },
+    {
+      "epoch": 6.632478632478632,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.940199535158954e-06,
+      "loss": 0.0764,
+      "step": 970
+    },
+    {
+      "epoch": 6.700854700854701,
+      "grad_norm": 0.828125,
+      "learning_rate": 4.8405553273942415e-06,
+      "loss": 0.0642,
+      "step": 980
+    },
+    {
+      "epoch": 6.769230769230769,
+      "grad_norm": 1.1796875,
+      "learning_rate": 4.740974474929438e-06,
+      "loss": 0.0444,
+      "step": 990
+    },
+    {
+      "epoch": 6.837606837606837,
+      "grad_norm": 0.83203125,
+      "learning_rate": 4.641496546190813e-06,
+      "loss": 0.0713,
+      "step": 1000
+    },
+    {
+      "epoch": 6.837606837606837,
+      "eval_loss": 0.19593119621276855,
+      "eval_runtime": 5.1008,
+      "eval_samples_per_second": 25.486,
+      "eval_steps_per_second": 25.486,
+      "step": 1000
+    },
+    {
+      "epoch": 6.905982905982906,
+      "grad_norm": 0.4765625,
+      "learning_rate": 4.542161068707927e-06,
+      "loss": 0.0494,
+      "step": 1010
+    },
+    {
+      "epoch": 6.9743589743589745,
+      "grad_norm": 0.78125,
+      "learning_rate": 4.443007513407368e-06,
+      "loss": 0.0492,
+      "step": 1020
+    },
+    {
+      "epoch": 7.042735042735043,
+      "grad_norm": 0.73046875,
+      "learning_rate": 4.344075278928989e-06,
+      "loss": 0.1084,
+      "step": 1030
+    },
+    {
+      "epoch": 7.111111111111111,
+      "grad_norm": 0.78515625,
+      "learning_rate": 4.245403675970877e-06,
+      "loss": 0.0605,
+      "step": 1040
+    },
+    {
+      "epoch": 7.17948717948718,
+      "grad_norm": 0.79296875,
+      "learning_rate": 4.147031911669243e-06,
+      "loss": 0.0422,
+      "step": 1050
+    },
+    {
+      "epoch": 7.247863247863248,
+      "grad_norm": 1.796875,
+      "learning_rate": 4.048999074019493e-06,
+      "loss": 0.0388,
+      "step": 1060
+    },
+    {
+      "epoch": 7.316239316239316,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.951344116344606e-06,
+      "loss": 0.0295,
+      "step": 1070
+    },
+    {
+      "epoch": 7.384615384615385,
+      "grad_norm": 0.44140625,
+      "learning_rate": 3.854105841817056e-06,
+      "loss": 0.0545,
+      "step": 1080
+    },
+    {
+      "epoch": 7.452991452991453,
+      "grad_norm": 0.64453125,
+      "learning_rate": 3.7573228880403734e-06,
+      "loss": 0.0337,
+      "step": 1090
+    },
+    {
+      "epoch": 7.521367521367521,
+      "grad_norm": 0.5703125,
+      "learning_rate": 3.661033711696501e-06,
+      "loss": 0.0507,
+      "step": 1100
+    },
+    {
+      "epoch": 7.589743589743589,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.5652765732650523e-06,
+      "loss": 0.0419,
+      "step": 1110
+    },
+    {
+      "epoch": 7.6581196581196584,
+      "grad_norm": 1.21875,
+      "learning_rate": 3.4700895218205026e-06,
+      "loss": 0.0423,
+      "step": 1120
+    },
+    {
+      "epoch": 7.726495726495727,
+      "grad_norm": 1.234375,
+      "learning_rate": 3.375510379913418e-06,
+      "loss": 0.0488,
+      "step": 1130
+    },
+    {
+      "epoch": 7.794871794871795,
+      "grad_norm": 0.4140625,
+      "learning_rate": 3.2815767285416576e-06,
+      "loss": 0.0388,
+      "step": 1140
+    },
+    {
+      "epoch": 7.863247863247864,
+      "grad_norm": 0.462890625,
+      "learning_rate": 3.188325892217587e-06,
+      "loss": 0.0197,
+      "step": 1150
+    },
+    {
+      "epoch": 7.931623931623932,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.0957949241371845e-06,
+      "loss": 0.0326,
+      "step": 1160
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.0040205914569664e-06,
+      "loss": 0.0383,
+      "step": 1170
+    },
+    {
+      "epoch": 8.068376068376068,
+      "grad_norm": 0.40234375,
+      "learning_rate": 2.913039360684565e-06,
+      "loss": 0.0296,
+      "step": 1180
+    },
+    {
+      "epoch": 8.136752136752136,
+      "grad_norm": 0.482421875,
+      "learning_rate": 2.822887383188775e-06,
+      "loss": 0.0564,
+      "step": 1190
+    },
+    {
+      "epoch": 8.205128205128204,
+      "grad_norm": 0.435546875,
+      "learning_rate": 2.7336004808348094e-06,
+      "loss": 0.0295,
+      "step": 1200
+    },
+    {
+      "epoch": 8.273504273504274,
+      "grad_norm": 0.435546875,
+      "learning_rate": 2.645214131750498e-06,
+      "loss": 0.0194,
+      "step": 1210
+    },
+    {
+      "epoch": 8.341880341880342,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 2.5577634562290567e-06,
+      "loss": 0.0261,
+      "step": 1220
+    },
+    {
+      "epoch": 8.41025641025641,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.4712832027740545e-06,
+      "loss": 0.0237,
+      "step": 1230
+    },
+    {
+      "epoch": 8.478632478632479,
+      "grad_norm": 0.15625,
+      "learning_rate": 2.385807734292097e-06,
+      "loss": 0.037,
+      "step": 1240
+    },
+    {
+      "epoch": 8.547008547008547,
+      "grad_norm": 0.63671875,
+      "learning_rate": 2.3013710144387374e-06,
+      "loss": 0.0241,
+      "step": 1250
+    },
+    {
+      "epoch": 8.615384615384615,
+      "grad_norm": 0.53515625,
+      "learning_rate": 2.218006594123028e-06,
+      "loss": 0.0258,
+      "step": 1260
+    },
+    {
+      "epoch": 8.683760683760683,
+      "grad_norm": 0.73828125,
+      "learning_rate": 2.1357475981760704e-06,
+      "loss": 0.0361,
+      "step": 1270
+    },
+    {
+      "epoch": 8.752136752136753,
+      "grad_norm": 0.333984375,
+      "learning_rate": 2.0546267121888863e-06,
+      "loss": 0.0243,
+      "step": 1280
+    },
+    {
+      "epoch": 8.820512820512821,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.9746761695247803e-06,
+      "loss": 0.0404,
+      "step": 1290
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.50390625,
+      "learning_rate": 1.8959277385114516e-06,
+      "loss": 0.0284,
+      "step": 1300
+    },
+    {
+      "epoch": 8.957264957264957,
+      "grad_norm": 0.265625,
+      "learning_rate": 1.8184127098178288e-06,
+      "loss": 0.028,
+      "step": 1310
+    },
+    {
+      "epoch": 9.025641025641026,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.7421618840207576e-06,
+      "loss": 0.0174,
+      "step": 1320
+    },
+    {
+      "epoch": 9.094017094017094,
+      "grad_norm": 0.47265625,
+      "learning_rate": 1.667205559366372e-06,
+      "loss": 0.0293,
+      "step": 1330
+    },
+    {
+      "epoch": 9.162393162393162,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.5935735197311204e-06,
+      "loss": 0.0459,
+      "step": 1340
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.12890625,
+      "learning_rate": 1.5212950227871292e-06,
+      "loss": 0.0197,
+      "step": 1350
+    },
+    {
+      "epoch": 9.2991452991453,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 1.4503987883766857e-06,
+      "loss": 0.0208,
+      "step": 1360
+    },
+    {
+      "epoch": 9.367521367521368,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.3809129871004113e-06,
+      "loss": 0.0332,
+      "step": 1370
+    },
+    {
+      "epoch": 9.435897435897436,
+      "grad_norm": 0.625,
+      "learning_rate": 1.312865229123681e-06,
+      "loss": 0.0186,
+      "step": 1380
+    },
+    {
+      "epoch": 9.504273504273504,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.2462825532057394e-06,
+      "loss": 0.0365,
+      "step": 1390
+    },
+    {
+      "epoch": 9.572649572649572,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.1811914159558374e-06,
+      "loss": 0.0172,
+      "step": 1400
+    },
+    {
+      "epoch": 9.64102564102564,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.117617681320729e-06,
+      "loss": 0.0307,
+      "step": 1410
+    },
+    {
+      "epoch": 9.709401709401709,
+      "grad_norm": 0.177734375,
+      "learning_rate": 1.0555866103076212e-06,
+      "loss": 0.0138,
+      "step": 1420
+    },
+    {
+      "epoch": 9.777777777777779,
+      "grad_norm": 0.369140625,
+      "learning_rate": 9.951228509467248e-07,
+      "loss": 0.0204,
+      "step": 1430
+    },
+    {
+      "epoch": 9.846153846153847,
+      "grad_norm": 0.2421875,
+      "learning_rate": 9.362504284973683e-07,
+      "loss": 0.017,
+      "step": 1440
+    },
+    {
+      "epoch": 9.914529914529915,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 8.789927359015643e-07,
+      "loss": 0.0236,
+      "step": 1450
+    },
+    {
+      "epoch": 9.982905982905983,
+      "grad_norm": 0.296875,
+      "learning_rate": 8.233725244888291e-07,
+      "loss": 0.0234,
+      "step": 1460
+    },
+    {
+      "epoch": 10.051282051282051,
+      "grad_norm": 0.3828125,
+      "learning_rate": 7.694118949359553e-07,
+      "loss": 0.015,
+      "step": 1470
+    },
+    {
+      "epoch": 10.11965811965812,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 7.171322884852988e-07,
+      "loss": 0.0209,
+      "step": 1480
+    },
+    {
+      "epoch": 10.188034188034187,
+      "grad_norm": 0.20703125,
+      "learning_rate": 6.665544784251232e-07,
+      "loss": 0.0156,
+      "step": 1490
+    },
+    {
+      "epoch": 10.256410256410255,
+      "grad_norm": 0.380859375,
+      "learning_rate": 6.176985618353282e-07,
+      "loss": 0.0245,
+      "step": 1500
+    },
+    {
+      "epoch": 10.324786324786325,
+      "grad_norm": 0.5234375,
+      "learning_rate": 5.705839516018818e-07,
+      "loss": 0.0143,
+      "step": 1510
+    },
+    {
+      "epoch": 10.393162393162394,
+      "grad_norm": 0.9375,
+      "learning_rate": 5.252293687031196e-07,
+      "loss": 0.0279,
+      "step": 1520
+    },
+    {
+      "epoch": 10.461538461538462,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 4.816528347709614e-07,
+      "loss": 0.0215,
+      "step": 1530
+    },
+    {
+      "epoch": 10.52991452991453,
+      "grad_norm": 0.84765625,
+      "learning_rate": 4.398716649300311e-07,
+      "loss": 0.0145,
+      "step": 1540
+    },
+    {
+      "epoch": 10.598290598290598,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.999024609174812e-07,
+      "loss": 0.0196,
+      "step": 1550
+    },
+    {
+      "epoch": 10.666666666666666,
+      "grad_norm": 1.3671875,
+      "learning_rate": 3.61761104486314e-07,
+      "loss": 0.0271,
+      "step": 1560
+    },
+    {
+      "epoch": 10.735042735042736,
+      "grad_norm": 0.70703125,
+      "learning_rate": 3.2546275109475554e-07,
+      "loss": 0.0179,
+      "step": 1570
+    },
+    {
+      "epoch": 10.803418803418804,
+      "grad_norm": 0.796875,
+      "learning_rate": 2.9102182388425106e-07,
+      "loss": 0.0228,
+      "step": 1580
+    },
+    {
+      "epoch": 10.871794871794872,
+      "grad_norm": 0.451171875,
+      "learning_rate": 2.5845200794842154e-07,
+      "loss": 0.0217,
+      "step": 1590
+    },
+    {
+      "epoch": 10.94017094017094,
+      "grad_norm": 0.95703125,
+      "learning_rate": 2.2776624489530664e-07,
+      "loss": 0.0212,
+      "step": 1600
+    },
+    {
+      "epoch": 11.008547008547009,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.9897672770501198e-07,
+      "loss": 0.0492,
+      "step": 1610
+    },
+    {
+      "epoch": 11.076923076923077,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.7209489588483396e-07,
+      "loss": 0.0265,
+      "step": 1620
+    },
+    {
+      "epoch": 11.145299145299145,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.4713143092377534e-07,
+      "loss": 0.0188,
+      "step": 1630
+    },
+    {
+      "epoch": 11.213675213675213,
+      "grad_norm": 2.625,
+      "learning_rate": 1.2409625204825802e-07,
+      "loss": 0.025,
+      "step": 1640
+    },
+    {
+      "epoch": 11.282051282051283,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.0299851228072089e-07,
+      "loss": 0.0186,
+      "step": 1650
+    },
+    {
+      "epoch": 11.350427350427351,
+      "grad_norm": 5.40625,
+      "learning_rate": 8.384659480266733e-08,
+      "loss": 0.0257,
+      "step": 1660
+    },
+    {
+      "epoch": 11.418803418803419,
+      "grad_norm": 4.09375,
+      "learning_rate": 6.664810962361268e-08,
+      "loss": 0.0213,
+      "step": 1670
+    },
+    {
+      "epoch": 11.487179487179487,
+      "grad_norm": 3.125,
+      "learning_rate": 5.1409890557246876e-08,
+      "loss": 0.0137,
+      "step": 1680
+    },
+    {
+      "epoch": 11.555555555555555,
+      "grad_norm": 5.21875,
+      "learning_rate": 3.813799250602046e-08,
+      "loss": 0.0164,
+      "step": 1690
+    },
+    {
+      "epoch": 11.623931623931623,
+      "grad_norm": 0.328125,
+      "learning_rate": 2.683768905523243e-08,
+      "loss": 0.0197,
+      "step": 1700
+    },
+    {
+      "epoch": 11.692307692307692,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.7513470377570896e-08,
+      "loss": 0.0246,
+      "step": 1710
+    },
+    {
+      "epoch": 11.760683760683762,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.016904144894304e-08,
+      "loss": 0.0295,
+      "step": 1720
+    },
+    {
+      "epoch": 11.82905982905983,
+      "grad_norm": 1.3671875,
+      "learning_rate": 4.807320576307728e-09,
+      "loss": 0.029,
+      "step": 1730
+    },
+    {
+      "epoch": 11.897435897435898,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.4304382380819771e-09,
+      "loss": 0.0177,
+      "step": 1740
+    },
+    {
+      "epoch": 11.965811965811966,
+      "grad_norm": 1.0234375,
+      "learning_rate": 3.9736237600895846e-11,
+      "loss": 0.0261,
+      "step": 1750
+    },
+    {
+      "epoch": 11.97948717948718,
+      "step": 1752,
+      "total_flos": 9.576163802677248e+16,
+      "train_loss": 0.4554890414942311,
+      "train_runtime": 1838.2954,
+      "train_samples_per_second": 7.638,
+      "train_steps_per_second": 0.953
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1752,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.576163802677248e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab620514947fb9d397c617b77e3f66b34339ff4de9840ac3d96ae1f32ebae0a
+size 5304