Model save

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: llama3.2
+base_model: tanliboy/llama-3.2-3b
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: llama-3.2-3b-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. -->
+
+# llama-3.2-3b-sft
+
+This model is a fine-tuned version of [tanliboy/llama-3.2-3b](https://huggingface.co/tanliboy/llama-3.2-3b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7042
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6946        | 1.0   | 2230 | 0.7042          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 244955314192384.0,
+    "train_loss": 0.7376568270371099,
+    "train_runtime": 8720.6202,
+    "train_samples": 285435,
+    "train_samples_per_second": 32.731,
+    "train_steps_per_second": 0.256
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "tanliboy/llama-3.2-3b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bafbda1cf46dcdfa68fddb235d102da9d1885ae56e80b4e41840a35aba9df3e
+size 4965799096

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674efdeb16be82251aae01846f486cb86b0be050c9eba1232d0602a00bd5679b
+size 1459729952

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 6425499648
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Sep27_06-57-05_action-graph-trainer/events.out.tfevents.1727420433.action-graph-trainer.266925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff87f7a6c8c422dc66d5e77678cffaa2c5685b317eacaf5e0dd6c7406cedcd6
+size 5794

runs/Sep27_07-16-13_action-graph-trainer/events.out.tfevents.1727421904.action-graph-trainer.273912.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6001d951297692894fac86268847902a3d6d44ac9081e0f659a5118792fb512b
+size 5972

runs/Sep27_07-46-15_action-graph-trainer/events.out.tfevents.1727423653.action-graph-trainer.285220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5120d55938b523510f626e87c166373e358719a6d02f1871a5a015b17c73b9
+size 6213

runs/Sep27_08-01-14_action-graph-trainer/events.out.tfevents.1727424090.action-graph-trainer.292963.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c8c12f26a631b75673121ed48b902118dad02399e1a505da7d67058b82e471
+size 6008

runs/Sep27_08-03-07_action-graph-trainer/events.out.tfevents.1727424978.action-graph-trainer.294397.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6d5465a088bde094017fd0d438dae146ae650978737b410bce11e81d64352f
+size 53636

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_thinking|>",
+    "<|end_of_thinking|>",
+    "<|start_of_tools|>",
+    "<|end_of_tools|>",
+    "<|start_of_tool_calls|>",
+    "<|end_of_tool_calls|>",
+    "<|start_of_tool_results|>",
+    "<|end_of_tool_results|>"
+  ],
+  "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": "<|finetune_right_pad_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2073 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|start_of_thinking|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|end_of_thinking|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|start_of_tools|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|end_of_tools|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|start_of_tool_calls|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|end_of_tool_calls|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|start_of_tool_results|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|end_of_tool_results|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_thinking|>",
+    "<|end_of_thinking|>",
+    "<|start_of_tools|>",
+    "<|end_of_tools|>",
+    "<|start_of_tool_calls|>",
+    "<|end_of_tool_calls|>",
+    "<|start_of_tool_results|>",
+    "<|end_of_tool_results|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if tools is defined and tools is not none %}{{ '<|start_of_tools|>\n[' }}{% for tool in tools %}{{ '{\"type\": \"' + tool.type + '\", \"' + tool.type + '\": ' + ( tool[tool.type] if tool[tool.type] is string else tool[tool.type] | tojson ) + '}' }}{% if not loop.last %}{{ ', ' }}{% endif %}{% endfor %}{{ ']<|end_of_tools|>\n' }}{% endif %}{% for message in messages %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n' }}{% if message['content'] is defined and message['content'] is not none %}{{ message['content'] | trim }}{% endif %}{% if message.tool_calls is defined and message.tool_calls is not none and message.tool_calls | length > 0 %}{{ '<|start_of_tool_calls|>' + (message.tool_calls if message.tool_calls is string else message.tool_calls | tojson) + '<|end_of_tool_calls|>' }}{% elif message['role'] == 'tool' and message.tool_results | length > 0 %}{{ '<|start_of_tool_results|>' + (message.tool_results if message.tool_results is string else message.tool_results | tojson) + '<|end_of_tool_results|>' }}{% endif %}{{ '<|eot_id|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 244955314192384.0,
+    "train_loss": 0.7376568270371099,
+    "train_runtime": 8720.6202,
+    "train_samples": 285435,
+    "train_samples_per_second": 32.731,
+    "train_steps_per_second": 0.256
+}

trainer_state.json

@@ -0,0 +1,1618 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004484304932735426,
+      "grad_norm": 4.697020980518476,
+      "learning_rate": 4.4843049327354265e-08,
+      "loss": 0.9912,
+      "step": 1
+    },
+    {
+      "epoch": 0.004484304932735426,
+      "grad_norm": 5.023039914107906,
+      "learning_rate": 4.484304932735426e-07,
+      "loss": 1.0335,
+      "step": 10
+    },
+    {
+      "epoch": 0.008968609865470852,
+      "grad_norm": 4.618075407201601,
+      "learning_rate": 8.968609865470852e-07,
+      "loss": 1.0355,
+      "step": 20
+    },
+    {
+      "epoch": 0.013452914798206279,
+      "grad_norm": 2.181160774619855,
+      "learning_rate": 1.345291479820628e-06,
+      "loss": 0.9824,
+      "step": 30
+    },
+    {
+      "epoch": 0.017937219730941704,
+      "grad_norm": 2.008569343268214,
+      "learning_rate": 1.7937219730941704e-06,
+      "loss": 0.9383,
+      "step": 40
+    },
+    {
+      "epoch": 0.02242152466367713,
+      "grad_norm": 1.7133805307500916,
+      "learning_rate": 2.242152466367713e-06,
+      "loss": 0.87,
+      "step": 50
+    },
+    {
+      "epoch": 0.026905829596412557,
+      "grad_norm": 1.6402285214131669,
+      "learning_rate": 2.690582959641256e-06,
+      "loss": 0.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.03139013452914798,
+      "grad_norm": 1.548076900788033,
+      "learning_rate": 3.1390134529147986e-06,
+      "loss": 0.8675,
+      "step": 70
+    },
+    {
+      "epoch": 0.03587443946188341,
+      "grad_norm": 1.5686573872779637,
+      "learning_rate": 3.587443946188341e-06,
+      "loss": 0.8581,
+      "step": 80
+    },
+    {
+      "epoch": 0.04035874439461883,
+      "grad_norm": 1.8398749741247653,
+      "learning_rate": 4.0358744394618836e-06,
+      "loss": 0.8272,
+      "step": 90
+    },
+    {
+      "epoch": 0.04484304932735426,
+      "grad_norm": 1.431522929426351,
+      "learning_rate": 4.484304932735426e-06,
+      "loss": 0.837,
+      "step": 100
+    },
+    {
+      "epoch": 0.04932735426008968,
+      "grad_norm": 1.5183209831163855,
+      "learning_rate": 4.932735426008969e-06,
+      "loss": 0.7993,
+      "step": 110
+    },
+    {
+      "epoch": 0.053811659192825115,
+      "grad_norm": 1.440741479973038,
+      "learning_rate": 5.381165919282512e-06,
+      "loss": 0.7768,
+      "step": 120
+    },
+    {
+      "epoch": 0.05829596412556054,
+      "grad_norm": 1.6957957755628803,
+      "learning_rate": 5.8295964125560544e-06,
+      "loss": 0.793,
+      "step": 130
+    },
+    {
+      "epoch": 0.06278026905829596,
+      "grad_norm": 1.5847929433417824,
+      "learning_rate": 6.278026905829597e-06,
+      "loss": 0.8145,
+      "step": 140
+    },
+    {
+      "epoch": 0.06726457399103139,
+      "grad_norm": 1.721638040499256,
+      "learning_rate": 6.72645739910314e-06,
+      "loss": 0.7677,
+      "step": 150
+    },
+    {
+      "epoch": 0.07174887892376682,
+      "grad_norm": 1.8900581111883776,
+      "learning_rate": 7.174887892376682e-06,
+      "loss": 0.784,
+      "step": 160
+    },
+    {
+      "epoch": 0.07623318385650224,
+      "grad_norm": 1.554784427401762,
+      "learning_rate": 7.6233183856502244e-06,
+      "loss": 0.7595,
+      "step": 170
+    },
+    {
+      "epoch": 0.08071748878923767,
+      "grad_norm": 1.8326262271816938,
+      "learning_rate": 8.071748878923767e-06,
+      "loss": 0.7722,
+      "step": 180
+    },
+    {
+      "epoch": 0.08520179372197309,
+      "grad_norm": 1.4707798772479566,
+      "learning_rate": 8.52017937219731e-06,
+      "loss": 0.764,
+      "step": 190
+    },
+    {
+      "epoch": 0.08968609865470852,
+      "grad_norm": 1.449476026227771,
+      "learning_rate": 8.968609865470853e-06,
+      "loss": 0.773,
+      "step": 200
+    },
+    {
+      "epoch": 0.09417040358744394,
+      "grad_norm": 1.5945882538155545,
+      "learning_rate": 9.417040358744395e-06,
+      "loss": 0.7549,
+      "step": 210
+    },
+    {
+      "epoch": 0.09865470852017937,
+      "grad_norm": 1.4765341188830319,
+      "learning_rate": 9.865470852017938e-06,
+      "loss": 0.784,
+      "step": 220
+    },
+    {
+      "epoch": 0.1031390134529148,
+      "grad_norm": 1.452955640004767,
+      "learning_rate": 9.999699851108367e-06,
+      "loss": 0.7909,
+      "step": 230
+    },
+    {
+      "epoch": 0.10762331838565023,
+      "grad_norm": 1.5997501860541272,
+      "learning_rate": 9.9982298208374e-06,
+      "loss": 0.7651,
+      "step": 240
+    },
+    {
+      "epoch": 0.11210762331838565,
+      "grad_norm": 1.554511883278329,
+      "learning_rate": 9.995535139530904e-06,
+      "loss": 0.7621,
+      "step": 250
+    },
+    {
+      "epoch": 0.11659192825112108,
+      "grad_norm": 1.6319742757477633,
+      "learning_rate": 9.991616467431486e-06,
+      "loss": 0.7906,
+      "step": 260
+    },
+    {
+      "epoch": 0.1210762331838565,
+      "grad_norm": 1.6863475759473823,
+      "learning_rate": 9.986474764680236e-06,
+      "loss": 0.7684,
+      "step": 270
+    },
+    {
+      "epoch": 0.12556053811659193,
+      "grad_norm": 1.5563949560805244,
+      "learning_rate": 9.98011129108149e-06,
+      "loss": 0.793,
+      "step": 280
+    },
+    {
+      "epoch": 0.13004484304932734,
+      "grad_norm": 1.6203440473254576,
+      "learning_rate": 9.972527605794151e-06,
+      "loss": 0.771,
+      "step": 290
+    },
+    {
+      "epoch": 0.13452914798206278,
+      "grad_norm": 1.5211967329248808,
+      "learning_rate": 9.963725566949674e-06,
+      "loss": 0.7865,
+      "step": 300
+    },
+    {
+      "epoch": 0.13901345291479822,
+      "grad_norm": 1.3996609263865165,
+      "learning_rate": 9.953707331196787e-06,
+      "loss": 0.7397,
+      "step": 310
+    },
+    {
+      "epoch": 0.14349775784753363,
+      "grad_norm": 1.7467903395183983,
+      "learning_rate": 9.94247535317308e-06,
+      "loss": 0.802,
+      "step": 320
+    },
+    {
+      "epoch": 0.14798206278026907,
+      "grad_norm": 1.4561862746225176,
+      "learning_rate": 9.930032384903566e-06,
+      "loss": 0.78,
+      "step": 330
+    },
+    {
+      "epoch": 0.15246636771300448,
+      "grad_norm": 1.261592243705757,
+      "learning_rate": 9.916381475126406e-06,
+      "loss": 0.7678,
+      "step": 340
+    },
+    {
+      "epoch": 0.15695067264573992,
+      "grad_norm": 1.3845441861346746,
+      "learning_rate": 9.901525968545907e-06,
+      "loss": 0.7462,
+      "step": 350
+    },
+    {
+      "epoch": 0.16143497757847533,
+      "grad_norm": 1.330783975393604,
+      "learning_rate": 9.885469505013006e-06,
+      "loss": 0.7516,
+      "step": 360
+    },
+    {
+      "epoch": 0.16591928251121077,
+      "grad_norm": 1.5411411223309597,
+      "learning_rate": 9.868216018633456e-06,
+      "loss": 0.7617,
+      "step": 370
+    },
+    {
+      "epoch": 0.17040358744394618,
+      "grad_norm": 1.4997661320107978,
+      "learning_rate": 9.8497697368039e-06,
+      "loss": 0.7433,
+      "step": 380
+    },
+    {
+      "epoch": 0.17488789237668162,
+      "grad_norm": 1.4613487182945122,
+      "learning_rate": 9.830135179176086e-06,
+      "loss": 0.7977,
+      "step": 390
+    },
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 1.3823002584421413,
+      "learning_rate": 9.809317156549476e-06,
+      "loss": 0.7668,
+      "step": 400
+    },
+    {
+      "epoch": 0.18385650224215247,
+      "grad_norm": 1.3405610913825137,
+      "learning_rate": 9.787320769692517e-06,
+      "loss": 0.755,
+      "step": 410
+    },
+    {
+      "epoch": 0.18834080717488788,
+      "grad_norm": 1.321174566440371,
+      "learning_rate": 9.76415140809287e-06,
+      "loss": 0.7712,
+      "step": 420
+    },
+    {
+      "epoch": 0.19282511210762332,
+      "grad_norm": 1.5855307049280556,
+      "learning_rate": 9.739814748636892e-06,
+      "loss": 0.7876,
+      "step": 430
+    },
+    {
+      "epoch": 0.19730941704035873,
+      "grad_norm": 1.3277684374580685,
+      "learning_rate": 9.7143167542187e-06,
+      "loss": 0.7497,
+      "step": 440
+    },
+    {
+      "epoch": 0.20179372197309417,
+      "grad_norm": 1.3316052843966186,
+      "learning_rate": 9.687663672279167e-06,
+      "loss": 0.7742,
+      "step": 450
+    },
+    {
+      "epoch": 0.2062780269058296,
+      "grad_norm": 1.3422686862026139,
+      "learning_rate": 9.659862033275188e-06,
+      "loss": 0.7443,
+      "step": 460
+    },
+    {
+      "epoch": 0.21076233183856502,
+      "grad_norm": 1.3794382112115433,
+      "learning_rate": 9.630918649079606e-06,
+      "loss": 0.7423,
+      "step": 470
+    },
+    {
+      "epoch": 0.21524663677130046,
+      "grad_norm": 1.3473781761704757,
+      "learning_rate": 9.600840611312198e-06,
+      "loss": 0.756,
+      "step": 480
+    },
+    {
+      "epoch": 0.21973094170403587,
+      "grad_norm": 1.477159074283593,
+      "learning_rate": 9.569635289602098e-06,
+      "loss": 0.758,
+      "step": 490
+    },
+    {
+      "epoch": 0.2242152466367713,
+      "grad_norm": 1.4406496372056654,
+      "learning_rate": 9.537310329782109e-06,
+      "loss": 0.7373,
+      "step": 500
+    },
+    {
+      "epoch": 0.22869955156950672,
+      "grad_norm": 1.3236307975388621,
+      "learning_rate": 9.503873652015358e-06,
+      "loss": 0.7485,
+      "step": 510
+    },
+    {
+      "epoch": 0.23318385650224216,
+      "grad_norm": 1.2168213830447414,
+      "learning_rate": 9.469333448854713e-06,
+      "loss": 0.7518,
+      "step": 520
+    },
+    {
+      "epoch": 0.23766816143497757,
+      "grad_norm": 1.4695219464522695,
+      "learning_rate": 9.433698183235468e-06,
+      "loss": 0.7389,
+      "step": 530
+    },
+    {
+      "epoch": 0.242152466367713,
+      "grad_norm": 1.5460371795366352,
+      "learning_rate": 9.39697658640179e-06,
+      "loss": 0.7606,
+      "step": 540
+    },
+    {
+      "epoch": 0.24663677130044842,
+      "grad_norm": 1.36384817307445,
+      "learning_rate": 9.359177655767398e-06,
+      "loss": 0.7573,
+      "step": 550
+    },
+    {
+      "epoch": 0.25112107623318386,
+      "grad_norm": 1.2974873879986306,
+      "learning_rate": 9.320310652711062e-06,
+      "loss": 0.7447,
+      "step": 560
+    },
+    {
+      "epoch": 0.2556053811659193,
+      "grad_norm": 1.3924395179060305,
+      "learning_rate": 9.2803851003074e-06,
+      "loss": 0.7346,
+      "step": 570
+    },
+    {
+      "epoch": 0.2600896860986547,
+      "grad_norm": 1.3646463661968233,
+      "learning_rate": 9.239410780993565e-06,
+      "loss": 0.7637,
+      "step": 580
+    },
+    {
+      "epoch": 0.2645739910313901,
+      "grad_norm": 1.5500883315093192,
+      "learning_rate": 9.197397734172381e-06,
+      "loss": 0.7352,
+      "step": 590
+    },
+    {
+      "epoch": 0.26905829596412556,
+      "grad_norm": 1.2384578247121611,
+      "learning_rate": 9.154356253752519e-06,
+      "loss": 0.7467,
+      "step": 600
+    },
+    {
+      "epoch": 0.273542600896861,
+      "grad_norm": 1.4632407956897133,
+      "learning_rate": 9.110296885626315e-06,
+      "loss": 0.7592,
+      "step": 610
+    },
+    {
+      "epoch": 0.27802690582959644,
+      "grad_norm": 1.4743516068749583,
+      "learning_rate": 9.065230425085849e-06,
+      "loss": 0.7471,
+      "step": 620
+    },
+    {
+      "epoch": 0.2825112107623318,
+      "grad_norm": 1.609459180353317,
+      "learning_rate": 9.01916791417792e-06,
+      "loss": 0.7411,
+      "step": 630
+    },
+    {
+      "epoch": 0.28699551569506726,
+      "grad_norm": 1.4163468213726333,
+      "learning_rate": 8.97212063899854e-06,
+      "loss": 0.7583,
+      "step": 640
+    },
+    {
+      "epoch": 0.2914798206278027,
+      "grad_norm": 1.2789206960042645,
+      "learning_rate": 8.924100126927672e-06,
+      "loss": 0.7637,
+      "step": 650
+    },
+    {
+      "epoch": 0.29596412556053814,
+      "grad_norm": 1.4348891847742615,
+      "learning_rate": 8.87511814380481e-06,
+      "loss": 0.7376,
+      "step": 660
+    },
+    {
+      "epoch": 0.3004484304932735,
+      "grad_norm": 1.4055551714674843,
+      "learning_rate": 8.825186691046156e-06,
+      "loss": 0.7544,
+      "step": 670
+    },
+    {
+      "epoch": 0.30493273542600896,
+      "grad_norm": 1.3076750983715024,
+      "learning_rate": 8.774318002704072e-06,
+      "loss": 0.7388,
+      "step": 680
+    },
+    {
+      "epoch": 0.3094170403587444,
+      "grad_norm": 1.2832634236951583,
+      "learning_rate": 8.722524542469517e-06,
+      "loss": 0.7386,
+      "step": 690
+    },
+    {
+      "epoch": 0.31390134529147984,
+      "grad_norm": 1.3612825976793976,
+      "learning_rate": 8.669819000618248e-06,
+      "loss": 0.768,
+      "step": 700
+    },
+    {
+      "epoch": 0.3183856502242152,
+      "grad_norm": 1.3343477240590562,
+      "learning_rate": 8.616214290901474e-06,
+      "loss": 0.7244,
+      "step": 710
+    },
+    {
+      "epoch": 0.32286995515695066,
+      "grad_norm": 1.3061898085537815,
+      "learning_rate": 8.56172354738178e-06,
+      "loss": 0.7368,
+      "step": 720
+    },
+    {
+      "epoch": 0.3273542600896861,
+      "grad_norm": 1.423008056010291,
+      "learning_rate": 8.506360121215046e-06,
+      "loss": 0.7297,
+      "step": 730
+    },
+    {
+      "epoch": 0.33183856502242154,
+      "grad_norm": 1.258418518673196,
+      "learning_rate": 8.4501375773792e-06,
+      "loss": 0.7322,
+      "step": 740
+    },
+    {
+      "epoch": 0.336322869955157,
+      "grad_norm": 1.4805131801943718,
+      "learning_rate": 8.39306969135056e-06,
+      "loss": 0.7284,
+      "step": 750
+    },
+    {
+      "epoch": 0.34080717488789236,
+      "grad_norm": 1.3260411374117855,
+      "learning_rate": 8.335170445728609e-06,
+      "loss": 0.7618,
+      "step": 760
+    },
+    {
+      "epoch": 0.3452914798206278,
+      "grad_norm": 1.3351013471897553,
+      "learning_rate": 8.276454026810026e-06,
+      "loss": 0.7454,
+      "step": 770
+    },
+    {
+      "epoch": 0.34977578475336324,
+      "grad_norm": 1.267536863507402,
+      "learning_rate": 8.216934821112803e-06,
+      "loss": 0.742,
+      "step": 780
+    },
+    {
+      "epoch": 0.3542600896860987,
+      "grad_norm": 1.4791659570865663,
+      "learning_rate": 8.156627411851295e-06,
+      "loss": 0.7483,
+      "step": 790
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 1.4042375363677306,
+      "learning_rate": 8.095546575363098e-06,
+      "loss": 0.7134,
+      "step": 800
+    },
+    {
+      "epoch": 0.3632286995515695,
+      "grad_norm": 1.2552675050466975,
+      "learning_rate": 8.033707277488585e-06,
+      "loss": 0.7186,
+      "step": 810
+    },
+    {
+      "epoch": 0.36771300448430494,
+      "grad_norm": 1.281776208560821,
+      "learning_rate": 7.97112466990403e-06,
+      "loss": 0.7367,
+      "step": 820
+    },
+    {
+      "epoch": 0.3721973094170404,
+      "grad_norm": 1.417675486477273,
+      "learning_rate": 7.907814086409183e-06,
+      "loss": 0.7399,
+      "step": 830
+    },
+    {
+      "epoch": 0.37668161434977576,
+      "grad_norm": 1.4911782746859528,
+      "learning_rate": 7.843791039170232e-06,
+      "loss": 0.738,
+      "step": 840
+    },
+    {
+      "epoch": 0.3811659192825112,
+      "grad_norm": 1.3628167592658191,
+      "learning_rate": 7.779071214919068e-06,
+      "loss": 0.7404,
+      "step": 850
+    },
+    {
+      "epoch": 0.38565022421524664,
+      "grad_norm": 1.256534318600846,
+      "learning_rate": 7.713670471109749e-06,
+      "loss": 0.7364,
+      "step": 860
+    },
+    {
+      "epoch": 0.3901345291479821,
+      "grad_norm": 1.3061985247991272,
+      "learning_rate": 7.647604832033178e-06,
+      "loss": 0.7535,
+      "step": 870
+    },
+    {
+      "epoch": 0.39461883408071746,
+      "grad_norm": 1.3626743194809932,
+      "learning_rate": 7.580890484890864e-06,
+      "loss": 0.7212,
+      "step": 880
+    },
+    {
+      "epoch": 0.3991031390134529,
+      "grad_norm": 1.283405821881289,
+      "learning_rate": 7.513543775828791e-06,
+      "loss": 0.7336,
+      "step": 890
+    },
+    {
+      "epoch": 0.40358744394618834,
+      "grad_norm": 1.4217858183255085,
+      "learning_rate": 7.445581205932335e-06,
+      "loss": 0.7349,
+      "step": 900
+    },
+    {
+      "epoch": 0.4080717488789238,
+      "grad_norm": 1.3304359323377464,
+      "learning_rate": 7.377019427183213e-06,
+      "loss": 0.7265,
+      "step": 910
+    },
+    {
+      "epoch": 0.4125560538116592,
+      "grad_norm": 1.3324230635898773,
+      "learning_rate": 7.30787523837947e-06,
+      "loss": 0.7451,
+      "step": 920
+    },
+    {
+      "epoch": 0.4170403587443946,
+      "grad_norm": 1.2976336030674929,
+      "learning_rate": 7.238165581019488e-06,
+      "loss": 0.7415,
+      "step": 930
+    },
+    {
+      "epoch": 0.42152466367713004,
+      "grad_norm": 1.3082251443805497,
+      "learning_rate": 7.167907535151027e-06,
+      "loss": 0.7405,
+      "step": 940
+    },
+    {
+      "epoch": 0.4260089686098655,
+      "grad_norm": 1.368310990039969,
+      "learning_rate": 7.097118315186335e-06,
+      "loss": 0.7141,
+      "step": 950
+    },
+    {
+      "epoch": 0.4304932735426009,
+      "grad_norm": 1.3507885090012453,
+      "learning_rate": 7.025815265684315e-06,
+      "loss": 0.744,
+      "step": 960
+    },
+    {
+      "epoch": 0.4349775784753363,
+      "grad_norm": 1.3870418574466943,
+      "learning_rate": 6.9540158571008105e-06,
+      "loss": 0.7344,
+      "step": 970
+    },
+    {
+      "epoch": 0.43946188340807174,
+      "grad_norm": 1.2702369270052376,
+      "learning_rate": 6.881737681508065e-06,
+      "loss": 0.7131,
+      "step": 980
+    },
+    {
+      "epoch": 0.4439461883408072,
+      "grad_norm": 1.3694518474478212,
+      "learning_rate": 6.808998448284347e-06,
+      "loss": 0.7516,
+      "step": 990
+    },
+    {
+      "epoch": 0.4484304932735426,
+      "grad_norm": 1.3967080566658139,
+      "learning_rate": 6.735815979774865e-06,
+      "loss": 0.7208,
+      "step": 1000
+    },
+    {
+      "epoch": 0.452914798206278,
+      "grad_norm": 1.4517646369323314,
+      "learning_rate": 6.662208206924986e-06,
+      "loss": 0.7455,
+      "step": 1010
+    },
+    {
+      "epoch": 0.45739910313901344,
+      "grad_norm": 1.2752229454885209,
+      "learning_rate": 6.588193164886847e-06,
+      "loss": 0.7555,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4618834080717489,
+      "grad_norm": 1.3528261238688069,
+      "learning_rate": 6.513788988600441e-06,
+      "loss": 0.7428,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4663677130044843,
+      "grad_norm": 1.340831615562883,
+      "learning_rate": 6.439013908350249e-06,
+      "loss": 0.7446,
+      "step": 1040
+    },
+    {
+      "epoch": 0.47085201793721976,
+      "grad_norm": 1.3233981064583105,
+      "learning_rate": 6.363886245298514e-06,
+      "loss": 0.6945,
+      "step": 1050
+    },
+    {
+      "epoch": 0.47533632286995514,
+      "grad_norm": 1.29683857481815,
+      "learning_rate": 6.288424406996237e-06,
+      "loss": 0.7085,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4798206278026906,
+      "grad_norm": 1.3009424922765027,
+      "learning_rate": 6.2126468828730225e-06,
+      "loss": 0.7294,
+      "step": 1070
+    },
+    {
+      "epoch": 0.484304932735426,
+      "grad_norm": 1.244204104767217,
+      "learning_rate": 6.136572239706854e-06,
+      "loss": 0.7091,
+      "step": 1080
+    },
+    {
+      "epoch": 0.48878923766816146,
+      "grad_norm": 1.4080424781447183,
+      "learning_rate": 6.060219117074914e-06,
+      "loss": 0.724,
+      "step": 1090
+    },
+    {
+      "epoch": 0.49327354260089684,
+      "grad_norm": 1.4328593518662633,
+      "learning_rate": 5.983606222786577e-06,
+      "loss": 0.7106,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4977578475336323,
+      "grad_norm": 1.3515007322722326,
+      "learning_rate": 5.9067523282996775e-06,
+      "loss": 0.7111,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5022421524663677,
+      "grad_norm": 1.3343622572750706,
+      "learning_rate": 5.829676264121184e-06,
+      "loss": 0.7323,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5067264573991032,
+      "grad_norm": 1.3346769678858248,
+      "learning_rate": 5.752396915193403e-06,
+      "loss": 0.744,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5112107623318386,
+      "grad_norm": 1.4071259742434898,
+      "learning_rate": 5.6749332162668525e-06,
+      "loss": 0.7181,
+      "step": 1140
+    },
+    {
+      "epoch": 0.515695067264574,
+      "grad_norm": 1.314030857289351,
+      "learning_rate": 5.5973041472609265e-06,
+      "loss": 0.7278,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5201793721973094,
+      "grad_norm": 1.2893634754111014,
+      "learning_rate": 5.519528728613491e-06,
+      "loss": 0.722,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5246636771300448,
+      "grad_norm": 1.2894378069172643,
+      "learning_rate": 5.4416260166205525e-06,
+      "loss": 0.7282,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5291479820627802,
+      "grad_norm": 1.2691657277439665,
+      "learning_rate": 5.363615098767149e-06,
+      "loss": 0.7439,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5336322869955157,
+      "grad_norm": 1.3478124675299437,
+      "learning_rate": 5.285515089050587e-06,
+      "loss": 0.7164,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5381165919282511,
+      "grad_norm": 1.3052899854504807,
+      "learning_rate": 5.207345123297187e-06,
+      "loss": 0.7171,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5426008968609866,
+      "grad_norm": 1.27131464716386,
+      "learning_rate": 5.129124354473688e-06,
+      "loss": 0.7235,
+      "step": 1210
+    },
+    {
+      "epoch": 0.547085201793722,
+      "grad_norm": 1.257329353514232,
+      "learning_rate": 5.050871947994443e-06,
+      "loss": 0.6999,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5515695067264574,
+      "grad_norm": 1.3863466652299603,
+      "learning_rate": 4.972607077025563e-06,
+      "loss": 0.7251,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5560538116591929,
+      "grad_norm": 1.394706696869187,
+      "learning_rate": 4.894348917787174e-06,
+      "loss": 0.6963,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5605381165919282,
+      "grad_norm": 1.288516832053435,
+      "learning_rate": 4.816116644854912e-06,
+      "loss": 0.7207,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5650224215246636,
+      "grad_norm": 1.291568839795731,
+      "learning_rate": 4.73792942646183e-06,
+      "loss": 0.7168,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5695067264573991,
+      "grad_norm": 1.3692501176044114,
+      "learning_rate": 4.659806419801855e-06,
+      "loss": 0.7311,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5739910313901345,
+      "grad_norm": 1.2214111714932894,
+      "learning_rate": 4.581766766335953e-06,
+      "loss": 0.7175,
+      "step": 1280
+    },
+    {
+      "epoch": 0.57847533632287,
+      "grad_norm": 1.2261021201524966,
+      "learning_rate": 4.503829587102138e-06,
+      "loss": 0.722,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5829596412556054,
+      "grad_norm": 1.279552435182188,
+      "learning_rate": 4.426013978030508e-06,
+      "loss": 0.7407,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5874439461883408,
+      "grad_norm": 1.2639914975822624,
+      "learning_rate": 4.348339005264406e-06,
+      "loss": 0.7174,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5919282511210763,
+      "grad_norm": 1.2931987303236723,
+      "learning_rate": 4.270823700488896e-06,
+      "loss": 0.7236,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5964125560538116,
+      "grad_norm": 1.3083460389811294,
+      "learning_rate": 4.19348705626768e-06,
+      "loss": 0.7247,
+      "step": 1330
+    },
+    {
+      "epoch": 0.600896860986547,
+      "grad_norm": 1.359946232054244,
+      "learning_rate": 4.116348021389595e-06,
+      "loss": 0.7289,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6053811659192825,
+      "grad_norm": 1.3038409489179155,
+      "learning_rate": 4.039425496225834e-06,
+      "loss": 0.723,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6098654708520179,
+      "grad_norm": 1.337031671252276,
+      "learning_rate": 3.962738328099047e-06,
+      "loss": 0.718,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6143497757847534,
+      "grad_norm": 1.3006506595251124,
+      "learning_rate": 3.88630530666542e-06,
+      "loss": 0.7372,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6188340807174888,
+      "grad_norm": 1.3038120667886732,
+      "learning_rate": 3.8101451593108816e-06,
+      "loss": 0.732,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6233183856502242,
+      "grad_norm": 1.2544712968929104,
+      "learning_rate": 3.7342765465625953e-06,
+      "loss": 0.7347,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6278026905829597,
+      "grad_norm": 1.3352755014667614,
+      "learning_rate": 3.658718057516803e-06,
+      "loss": 0.7332,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6322869955156951,
+      "grad_norm": 1.3389617347187606,
+      "learning_rate": 3.5834882052841744e-06,
+      "loss": 0.7154,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6367713004484304,
+      "grad_norm": 1.2654799213890686,
+      "learning_rate": 3.508605422453799e-06,
+      "loss": 0.7002,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6412556053811659,
+      "grad_norm": 1.311398422880929,
+      "learning_rate": 3.4340880565768707e-06,
+      "loss": 0.7098,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6457399103139013,
+      "grad_norm": 1.3577211660369808,
+      "learning_rate": 3.359954365671241e-06,
+      "loss": 0.7024,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6502242152466368,
+      "grad_norm": 1.145375472595952,
+      "learning_rate": 3.2862225137478897e-06,
+      "loss": 0.7097,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6547085201793722,
+      "grad_norm": 1.3358950336855993,
+      "learning_rate": 3.2129105663604275e-06,
+      "loss": 0.7148,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6591928251121076,
+      "grad_norm": 1.2495395838860759,
+      "learning_rate": 3.1400364861787434e-06,
+      "loss": 0.7483,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6636771300448431,
+      "grad_norm": 1.2742823576583961,
+      "learning_rate": 3.0676181285878343e-06,
+      "loss": 0.7063,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6681614349775785,
+      "grad_norm": 1.2596513250823083,
+      "learning_rate": 2.9956732373129378e-06,
+      "loss": 0.7201,
+      "step": 1490
+    },
+    {
+      "epoch": 0.672645739910314,
+      "grad_norm": 1.4183600229677984,
+      "learning_rate": 2.9242194400720157e-06,
+      "loss": 0.7202,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6771300448430493,
+      "grad_norm": 1.224500332009707,
+      "learning_rate": 2.8532742442566735e-06,
+      "loss": 0.7228,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6816143497757847,
+      "grad_norm": 1.20210393613667,
+      "learning_rate": 2.782855032642535e-06,
+      "loss": 0.7386,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6860986547085202,
+      "grad_norm": 1.2835056973370584,
+      "learning_rate": 2.712979059130187e-06,
+      "loss": 0.7207,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6905829596412556,
+      "grad_norm": 1.180714987729606,
+      "learning_rate": 2.643663444517671e-06,
+      "loss": 0.6981,
+      "step": 1540
+    },
+    {
+      "epoch": 0.695067264573991,
+      "grad_norm": 1.2871858226590431,
+      "learning_rate": 2.5749251723055933e-06,
+      "loss": 0.6853,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6995515695067265,
+      "grad_norm": 1.3219720717807693,
+      "learning_rate": 2.5067810845358926e-06,
+      "loss": 0.7192,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7040358744394619,
+      "grad_norm": 1.391893981214182,
+      "learning_rate": 2.439247877665244e-06,
+      "loss": 0.7103,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7085201793721974,
+      "grad_norm": 1.2636799158865641,
+      "learning_rate": 2.3723420984741417e-06,
+      "loss": 0.684,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7130044843049327,
+      "grad_norm": 1.3557464635552046,
+      "learning_rate": 2.3060801400126693e-06,
+      "loss": 0.7207,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 1.3569256088684083,
+      "learning_rate": 2.240478237583915e-06,
+      "loss": 0.7077,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7219730941704036,
+      "grad_norm": 1.37192661939199,
+      "learning_rate": 2.1755524647660514e-06,
+      "loss": 0.693,
+      "step": 1610
+    },
+    {
+      "epoch": 0.726457399103139,
+      "grad_norm": 1.248391921620642,
+      "learning_rate": 2.1113187294740294e-06,
+      "loss": 0.6911,
+      "step": 1620
+    },
+    {
+      "epoch": 0.7309417040358744,
+      "grad_norm": 1.357856212054366,
+      "learning_rate": 2.047792770061881e-06,
+      "loss": 0.6838,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7354260089686099,
+      "grad_norm": 1.4147463764446673,
+      "learning_rate": 1.9849901514665458e-06,
+      "loss": 0.7122,
+      "step": 1640
+    },
+    {
+      "epoch": 0.7399103139013453,
+      "grad_norm": 1.3587967144630926,
+      "learning_rate": 1.922926261394206e-06,
+      "loss": 0.6927,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7443946188340808,
+      "grad_norm": 1.326112035320906,
+      "learning_rate": 1.8616163065500231e-06,
+      "loss": 0.6931,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7488789237668162,
+      "grad_norm": 1.2337199420172695,
+      "learning_rate": 1.8010753089122572e-06,
+      "loss": 0.6934,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7533632286995515,
+      "grad_norm": 1.2176765529306792,
+      "learning_rate": 1.7413181020516146e-06,
+      "loss": 0.7164,
+      "step": 1680
+    },
+    {
+      "epoch": 0.757847533632287,
+      "grad_norm": 1.2724919849788396,
+      "learning_rate": 1.6823593274967703e-06,
+      "loss": 0.7267,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7623318385650224,
+      "grad_norm": 1.3274428154634692,
+      "learning_rate": 1.6242134311469538e-06,
+      "loss": 0.6824,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7668161434977578,
+      "grad_norm": 1.3661211722387332,
+      "learning_rate": 1.5668946597324558e-06,
+      "loss": 0.7182,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7713004484304933,
+      "grad_norm": 1.2959174525555186,
+      "learning_rate": 1.51041705732393e-06,
+      "loss": 0.7118,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7757847533632287,
+      "grad_norm": 1.2773849053623296,
+      "learning_rate": 1.4547944618913706e-06,
+      "loss": 0.6929,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7802690582959642,
+      "grad_norm": 1.297150269984566,
+      "learning_rate": 1.4000405019135676e-06,
+      "loss": 0.6883,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7847533632286996,
+      "grad_norm": 1.400539444832659,
+      "learning_rate": 1.3461685930388958e-06,
+      "loss": 0.6911,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 1.2337657683341194,
+      "learning_rate": 1.2931919347982607e-06,
+      "loss": 0.6921,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7937219730941704,
+      "grad_norm": 1.2072415924732212,
+      "learning_rate": 1.2411235073709883e-06,
+      "loss": 0.7102,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7982062780269058,
+      "grad_norm": 1.381367292756694,
+      "learning_rate": 1.1899760684044515e-06,
+      "loss": 0.6838,
+      "step": 1780
+    },
+    {
+      "epoch": 0.8026905829596412,
+      "grad_norm": 1.3102643665842388,
+      "learning_rate": 1.1397621498882471e-06,
+      "loss": 0.6945,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8071748878923767,
+      "grad_norm": 1.3214717866253802,
+      "learning_rate": 1.0904940550836285e-06,
+      "loss": 0.7016,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8116591928251121,
+      "grad_norm": 1.1240219719921938,
+      "learning_rate": 1.0421838555090119e-06,
+      "loss": 0.7018,
+      "step": 1810
+    },
+    {
+      "epoch": 0.8161434977578476,
+      "grad_norm": 1.2844428659053804,
+      "learning_rate": 9.948433879822428e-07,
+      "loss": 0.7361,
+      "step": 1820
+    },
+    {
+      "epoch": 0.820627802690583,
+      "grad_norm": 1.249492840397432,
+      "learning_rate": 9.484842517203735e-07,
+      "loss": 0.707,
+      "step": 1830
+    },
+    {
+      "epoch": 0.8251121076233184,
+      "grad_norm": 1.2793612843154911,
+      "learning_rate": 9.031178054976636e-07,
+      "loss": 0.7226,
+      "step": 1840
+    },
+    {
+      "epoch": 0.8295964125560538,
+      "grad_norm": 1.3447642426455195,
+      "learning_rate": 8.587551648624859e-07,
+      "loss": 0.6906,
+      "step": 1850
+    },
+    {
+      "epoch": 0.8340807174887892,
+      "grad_norm": 1.282168137173779,
+      "learning_rate": 8.154071994138241e-07,
+      "loss": 0.698,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8385650224215246,
+      "grad_norm": 1.4629920435128856,
+      "learning_rate": 7.730845301380441e-07,
+      "loss": 0.7212,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8430493273542601,
+      "grad_norm": 1.3143459341111923,
+      "learning_rate": 7.317975268065685e-07,
+      "loss": 0.6942,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8475336322869955,
+      "grad_norm": 1.3274198546425116,
+      "learning_rate": 6.915563054351037e-07,
+      "loss": 0.6944,
+      "step": 1890
+    },
+    {
+      "epoch": 0.852017937219731,
+      "grad_norm": 1.2958298618538142,
+      "learning_rate": 6.523707258050516e-07,
+      "loss": 0.6692,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8565022421524664,
+      "grad_norm": 1.3403229426415875,
+      "learning_rate": 6.14250389047692e-07,
+      "loss": 0.7034,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8609865470852018,
+      "grad_norm": 1.258601487476543,
+      "learning_rate": 5.772046352917399e-07,
+      "loss": 0.7144,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8654708520179372,
+      "grad_norm": 1.1222145256140716,
+      "learning_rate": 5.412425413748623e-07,
+      "loss": 0.6988,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8699551569506726,
+      "grad_norm": 1.2674996138499859,
+      "learning_rate": 5.063729186196948e-07,
+      "loss": 0.7089,
+      "step": 1940
+    },
+    {
+      "epoch": 0.874439461883408,
+      "grad_norm": 1.3633828734617575,
+      "learning_rate": 4.7260431067491617e-07,
+      "loss": 0.733,
+      "step": 1950
+    },
+    {
+      "epoch": 0.8789237668161435,
+      "grad_norm": 1.2652212276863493,
+      "learning_rate": 4.399449914219167e-07,
+      "loss": 0.7209,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8834080717488789,
+      "grad_norm": 1.2975811004623845,
+      "learning_rate": 4.084029629475478e-07,
+      "loss": 0.7252,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8878923766816144,
+      "grad_norm": 1.2744740809644324,
+      "learning_rate": 3.7798595358348457e-07,
+      "loss": 0.7083,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8923766816143498,
+      "grad_norm": 1.2924446335095698,
+      "learning_rate": 3.487014160126467e-07,
+      "loss": 0.7077,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8968609865470852,
+      "grad_norm": 1.283938673421291,
+      "learning_rate": 3.2055652544316695e-07,
+      "loss": 0.7038,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9013452914798207,
+      "grad_norm": 1.3428158271865258,
+      "learning_rate": 2.9355817785034325e-07,
+      "loss": 0.7177,
+      "step": 2010
+    },
+    {
+      "epoch": 0.905829596412556,
+      "grad_norm": 1.3237588390932393,
+      "learning_rate": 2.6771298828700885e-07,
+      "loss": 0.7079,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9103139013452914,
+      "grad_norm": 1.379188659318735,
+      "learning_rate": 2.4302728926273224e-07,
+      "loss": 0.7159,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9147982062780269,
+      "grad_norm": 1.2853687562313414,
+      "learning_rate": 2.195071291922435e-07,
+      "loss": 0.6842,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9192825112107623,
+      "grad_norm": 1.3212853096546313,
+      "learning_rate": 1.9715827091347005e-07,
+      "loss": 0.6994,
+      "step": 2050
+    },
+    {
+      "epoch": 0.9237668161434978,
+      "grad_norm": 1.4231610496002076,
+      "learning_rate": 1.7598619027554553e-07,
+      "loss": 0.7032,
+      "step": 2060
+    },
+    {
+      "epoch": 0.9282511210762332,
+      "grad_norm": 1.288660209861224,
+      "learning_rate": 1.5599607479713396e-07,
+      "loss": 0.6856,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9327354260089686,
+      "grad_norm": 1.291080758227027,
+      "learning_rate": 1.3719282239539722e-07,
+      "loss": 0.7183,
+      "step": 2080
+    },
+    {
+      "epoch": 0.9372197309417041,
+      "grad_norm": 1.3527938026636528,
+      "learning_rate": 1.1958104018592376e-07,
+      "loss": 0.7022,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9417040358744395,
+      "grad_norm": 1.306930563286188,
+      "learning_rate": 1.0316504335390775e-07,
+      "loss": 0.7202,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9461883408071748,
+      "grad_norm": 1.34728936572921,
+      "learning_rate": 8.79488540968565e-08,
+      "loss": 0.7128,
+      "step": 2110
+    },
+    {
+      "epoch": 0.9506726457399103,
+      "grad_norm": 1.5138997567977701,
+      "learning_rate": 7.39362006390798e-08,
+      "loss": 0.6841,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9551569506726457,
+      "grad_norm": 1.2518587224976194,
+      "learning_rate": 6.113051631821631e-08,
+      "loss": 0.71,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9596412556053812,
+      "grad_norm": 1.4419766059722212,
+      "learning_rate": 4.9534938744004723e-08,
+      "loss": 0.6944,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9641255605381166,
+      "grad_norm": 1.3591089992663685,
+      "learning_rate": 3.915230902951761e-08,
+      "loss": 0.717,
+      "step": 2150
+    },
+    {
+      "epoch": 0.968609865470852,
+      "grad_norm": 1.281084457332566,
+      "learning_rate": 2.9985171095041066e-08,
+      "loss": 0.703,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9730941704035875,
+      "grad_norm": 1.1922556783094496,
+      "learning_rate": 2.203577104476773e-08,
+      "loss": 0.7085,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9775784753363229,
+      "grad_norm": 1.3917918614257676,
+      "learning_rate": 1.5306056616468666e-08,
+      "loss": 0.709,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9820627802690582,
+      "grad_norm": 1.178733370314234,
+      "learning_rate": 9.797676704259574e-09,
+      "loss": 0.7009,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9865470852017937,
+      "grad_norm": 1.2352452900540438,
+      "learning_rate": 5.511980954596152e-09,
+      "loss": 0.7085,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9910313901345291,
+      "grad_norm": 1.519249312059187,
+      "learning_rate": 2.4500194355880913e-09,
+      "loss": 0.6865,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9955156950672646,
+      "grad_norm": 1.2975150315542752,
+      "learning_rate": 6.125423797137541e-10,
+      "loss": 0.6935,
+      "step": 2220
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2570272992562246,
+      "learning_rate": 0.0,
+      "loss": 0.6946,
+      "step": 2230
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7042345404624939,
+      "eval_runtime": 381.2635,
+      "eval_samples_per_second": 131.345,
+      "eval_steps_per_second": 2.054,
+      "step": 2230
+    },
+    {
+      "epoch": 1.0,
+      "step": 2230,
+      "total_flos": 244955314192384.0,
+      "train_loss": 0.7376568270371099,
+      "train_runtime": 8720.6202,
+      "train_samples_per_second": 32.731,
+      "train_steps_per_second": 0.256
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 244955314192384.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb25fa7c42df808b4748bec88dee1a8e16e0082e24daff6298a752d2dca4e443
+size 6968