First commit

README.md

@@ -0,0 +1,66 @@
+---
+license: other
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: llama3-8b-energy
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zihao-lee/huggingface/runs/i2zqx10g)
+# llama3-8b-energy
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the IEA_Energy_Dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7752
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.75          | 1.8868 | 1000 | 2.2884          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.7752132415771484,
+    "eval_runtime": 177.8773,
+    "eval_samples_per_second": 10.592,
+    "eval_steps_per_second": 2.648,
+    "perplexity": 16.042047462451425,
+    "total_flos": 83202240675840.0,
+    "train_loss": 1.594443890733539,
+    "train_runtime": 15602.0514,
+    "train_samples_per_second": 3.26,
+    "train_steps_per_second": 0.102
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.7752132415771484,
+    "eval_runtime": 177.8773,
+    "eval_samples_per_second": 10.592,
+    "eval_steps_per_second": 2.648,
+    "perplexity": 16.042047462451425
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ccdfc78dc855275f232974880b9041565e6087994e66b4a5194efc94bd29cc
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642a1795426b8276ea03b3c1b79cdd983602e7db18bae8f8d164695d792c1ca1
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59dfd58947a15fa5b8de31d92b1a90ba0657b01a5ac5fd94317eb81304f16edb
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a72b1feb0fef63d650e7a0e1b8f733c268640281e6c1fc83280a8856c80c5d2
+size 1168138808

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 83202240675840.0,
+    "train_loss": 1.594443890733539,
+    "train_runtime": 15602.0514,
+    "train_samples_per_second": 3.26,
+    "train_steps_per_second": 0.102
+}

trainer_log.jsonl

@@ -0,0 +1,161 @@
+{"current_steps": 10, "total_steps": 1590, "loss": 2.3241, "learning_rate": 6.289308176100629e-06, "epoch": 0.018867924528301886, "percentage": 0.63, "elapsed_time": "0:01:36", "remaining_time": "4:13:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 1590, "loss": 2.2496, "learning_rate": 1.2578616352201259e-05, "epoch": 0.03773584905660377, "percentage": 1.26, "elapsed_time": "0:03:02", "remaining_time": "3:59:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 1590, "loss": 2.2836, "learning_rate": 1.8867924528301888e-05, "epoch": 0.05660377358490566, "percentage": 1.89, "elapsed_time": "0:04:28", "remaining_time": "3:52:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 1590, "loss": 2.2567, "learning_rate": 2.5157232704402517e-05, "epoch": 0.07547169811320754, "percentage": 2.52, "elapsed_time": "0:05:53", "remaining_time": "3:48:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 1590, "loss": 2.2749, "learning_rate": 3.144654088050314e-05, "epoch": 0.09433962264150944, "percentage": 3.14, "elapsed_time": "0:07:18", "remaining_time": "3:45:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 1590, "loss": 2.3334, "learning_rate": 3.7735849056603776e-05, "epoch": 0.11320754716981132, "percentage": 3.77, "elapsed_time": "0:08:43", "remaining_time": "3:42:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 1590, "loss": 2.3378, "learning_rate": 4.402515723270441e-05, "epoch": 0.1320754716981132, "percentage": 4.4, "elapsed_time": "0:10:08", "remaining_time": "3:40:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 1590, "loss": 2.3462, "learning_rate": 5.0314465408805034e-05, "epoch": 0.1509433962264151, "percentage": 5.03, "elapsed_time": "0:11:32", "remaining_time": "3:37:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 1590, "loss": 2.3832, "learning_rate": 5.660377358490566e-05, "epoch": 0.16981132075471697, "percentage": 5.66, "elapsed_time": "0:12:57", "remaining_time": "3:36:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 1590, "loss": 2.3658, "learning_rate": 6.289308176100629e-05, "epoch": 0.18867924528301888, "percentage": 6.29, "elapsed_time": "0:14:22", "remaining_time": "3:34:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 1590, "loss": 2.3894, "learning_rate": 6.918238993710691e-05, "epoch": 0.20754716981132076, "percentage": 6.92, "elapsed_time": "0:15:47", "remaining_time": "3:32:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 120, "total_steps": 1590, "loss": 2.4635, "learning_rate": 7.547169811320755e-05, "epoch": 0.22641509433962265, "percentage": 7.55, "elapsed_time": "0:17:13", "remaining_time": "3:31:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 130, "total_steps": 1590, "loss": 2.4099, "learning_rate": 8.176100628930818e-05, "epoch": 0.24528301886792453, "percentage": 8.18, "elapsed_time": "0:18:40", "remaining_time": "3:29:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 140, "total_steps": 1590, "loss": 2.4141, "learning_rate": 8.805031446540882e-05, "epoch": 0.2641509433962264, "percentage": 8.81, "elapsed_time": "0:20:07", "remaining_time": "3:28:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 150, "total_steps": 1590, "loss": 2.4505, "learning_rate": 9.433962264150944e-05, "epoch": 0.2830188679245283, "percentage": 9.43, "elapsed_time": "0:21:34", "remaining_time": "3:27:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1590, "loss": 2.4853, "learning_rate": 9.999987950741765e-05, "epoch": 0.3018867924528302, "percentage": 10.06, "elapsed_time": "0:23:00", "remaining_time": "3:25:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1590, "loss": 2.529, "learning_rate": 9.9985421100216e-05, "epoch": 0.32075471698113206, "percentage": 10.69, "elapsed_time": "0:24:27", "remaining_time": "3:24:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1590, "loss": 2.5123, "learning_rate": 9.99468721610658e-05, "epoch": 0.33962264150943394, "percentage": 11.32, "elapsed_time": "0:25:54", "remaining_time": "3:22:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1590, "loss": 2.5137, "learning_rate": 9.988425126867315e-05, "epoch": 0.3584905660377358, "percentage": 11.95, "elapsed_time": "0:27:20", "remaining_time": "3:21:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1590, "loss": 2.4818, "learning_rate": 9.979758860325019e-05, "epoch": 0.37735849056603776, "percentage": 12.58, "elapsed_time": "0:28:47", "remaining_time": "3:20:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1590, "loss": 2.5084, "learning_rate": 9.968692593196944e-05, "epoch": 0.39622641509433965, "percentage": 13.21, "elapsed_time": "0:30:13", "remaining_time": "3:18:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1590, "loss": 2.4667, "learning_rate": 9.955231658883432e-05, "epoch": 0.41509433962264153, "percentage": 13.84, "elapsed_time": "0:31:40", "remaining_time": "3:17:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1590, "loss": 2.4815, "learning_rate": 9.93938254489746e-05, "epoch": 0.4339622641509434, "percentage": 14.47, "elapsed_time": "0:33:07", "remaining_time": "3:15:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1590, "loss": 2.465, "learning_rate": 9.921152889737984e-05, "epoch": 0.4528301886792453, "percentage": 15.09, "elapsed_time": "0:34:33", "remaining_time": "3:14:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1590, "loss": 2.4827, "learning_rate": 9.900551479208552e-05, "epoch": 0.4716981132075472, "percentage": 15.72, "elapsed_time": "0:35:59", "remaining_time": "3:12:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 260, "total_steps": 1590, "loss": 2.5077, "learning_rate": 9.877588242182975e-05, "epoch": 0.49056603773584906, "percentage": 16.35, "elapsed_time": "0:37:26", "remaining_time": "3:11:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 270, "total_steps": 1590, "loss": 2.5812, "learning_rate": 9.852274245820096e-05, "epoch": 0.5094339622641509, "percentage": 16.98, "elapsed_time": "0:38:52", "remaining_time": "3:10:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 280, "total_steps": 1590, "loss": 2.5047, "learning_rate": 9.824621690229965e-05, "epoch": 0.5283018867924528, "percentage": 17.61, "elapsed_time": "0:40:19", "remaining_time": "3:08:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 290, "total_steps": 1590, "loss": 2.4985, "learning_rate": 9.79464390259397e-05, "epoch": 0.5471698113207547, "percentage": 18.24, "elapsed_time": "0:41:46", "remaining_time": "3:07:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 300, "total_steps": 1590, "loss": 2.4943, "learning_rate": 9.762355330741796e-05, "epoch": 0.5660377358490566, "percentage": 18.87, "elapsed_time": "0:43:12", "remaining_time": "3:05:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 310, "total_steps": 1590, "loss": 2.4536, "learning_rate": 9.727771536188275e-05, "epoch": 0.5849056603773585, "percentage": 19.5, "elapsed_time": "0:44:39", "remaining_time": "3:04:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 320, "total_steps": 1590, "loss": 2.4837, "learning_rate": 9.690909186633492e-05, "epoch": 0.6037735849056604, "percentage": 20.13, "elapsed_time": "0:46:06", "remaining_time": "3:02:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 330, "total_steps": 1590, "loss": 2.5074, "learning_rate": 9.651786047929773e-05, "epoch": 0.6226415094339622, "percentage": 20.75, "elapsed_time": "0:47:32", "remaining_time": "3:01:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 340, "total_steps": 1590, "loss": 2.441, "learning_rate": 9.610420975519408e-05, "epoch": 0.6415094339622641, "percentage": 21.38, "elapsed_time": "0:48:59", "remaining_time": "3:00:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 350, "total_steps": 1590, "loss": 2.4885, "learning_rate": 9.566833905347245e-05, "epoch": 0.660377358490566, "percentage": 22.01, "elapsed_time": "0:50:26", "remaining_time": "2:58:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 360, "total_steps": 1590, "loss": 2.4342, "learning_rate": 9.521045844252552e-05, "epoch": 0.6792452830188679, "percentage": 22.64, "elapsed_time": "0:51:52", "remaining_time": "2:57:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 370, "total_steps": 1590, "loss": 2.4425, "learning_rate": 9.473078859844728e-05, "epoch": 0.6981132075471698, "percentage": 23.27, "elapsed_time": "0:53:19", "remaining_time": "2:55:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 380, "total_steps": 1590, "loss": 2.4567, "learning_rate": 9.422956069867807e-05, "epoch": 0.7169811320754716, "percentage": 23.9, "elapsed_time": "0:54:45", "remaining_time": "2:54:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 390, "total_steps": 1590, "loss": 2.4636, "learning_rate": 9.370701631058829e-05, "epoch": 0.7358490566037735, "percentage": 24.53, "elapsed_time": "0:56:12", "remaining_time": "2:52:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 400, "total_steps": 1590, "loss": 2.4707, "learning_rate": 9.316340727505468e-05, "epoch": 0.7547169811320755, "percentage": 25.16, "elapsed_time": "0:57:38", "remaining_time": "2:51:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 1590, "loss": 2.4242, "learning_rate": 9.259899558508543e-05, "epoch": 0.7735849056603774, "percentage": 25.79, "elapsed_time": "0:59:05", "remaining_time": "2:50:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 1590, "loss": 2.4754, "learning_rate": 9.201405325955221e-05, "epoch": 0.7924528301886793, "percentage": 26.42, "elapsed_time": "1:00:31", "remaining_time": "2:48:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 1590, "loss": 2.4735, "learning_rate": 9.14088622120905e-05, "epoch": 0.8113207547169812, "percentage": 27.04, "elapsed_time": "1:01:58", "remaining_time": "2:47:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 1590, "loss": 2.4511, "learning_rate": 9.078371411523084e-05, "epoch": 0.8301886792452831, "percentage": 27.67, "elapsed_time": "1:03:24", "remaining_time": "2:45:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1590, "loss": 2.4627, "learning_rate": 9.013891025982704e-05, "epoch": 0.8490566037735849, "percentage": 28.3, "elapsed_time": "1:04:58", "remaining_time": "2:44:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1590, "loss": 2.4804, "learning_rate": 8.947476140984856e-05, "epoch": 0.8679245283018868, "percentage": 28.93, "elapsed_time": "1:06:45", "remaining_time": "2:43:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1590, "loss": 2.4872, "learning_rate": 8.879158765260767e-05, "epoch": 0.8867924528301887, "percentage": 29.56, "elapsed_time": "1:08:28", "remaining_time": "2:43:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1590, "loss": 2.4847, "learning_rate": 8.808971824449275e-05, "epoch": 0.9056603773584906, "percentage": 30.19, "elapsed_time": "1:10:09", "remaining_time": "2:42:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 490, "total_steps": 1590, "loss": 2.4873, "learning_rate": 8.736949145228295e-05, "epoch": 0.9245283018867925, "percentage": 30.82, "elapsed_time": "1:11:51", "remaining_time": "2:41:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1590, "loss": 2.4738, "learning_rate": 8.66312543901201e-05, "epoch": 0.9433962264150944, "percentage": 31.45, "elapsed_time": "1:13:32", "remaining_time": "2:40:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1590, "loss": 2.4211, "learning_rate": 8.587536285221656e-05, "epoch": 0.9622641509433962, "percentage": 32.08, "elapsed_time": "1:15:13", "remaining_time": "2:39:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1590, "loss": 2.4183, "learning_rate": 8.510218114137992e-05, "epoch": 0.9811320754716981, "percentage": 32.7, "elapsed_time": "1:16:54", "remaining_time": "2:38:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1590, "loss": 2.459, "learning_rate": 8.43120818934367e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:18:35", "remaining_time": "2:37:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1590, "loss": 1.8838, "learning_rate": 8.350544589764016e-05, "epoch": 1.0188679245283019, "percentage": 33.96, "elapsed_time": "1:20:16", "remaining_time": "2:36:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1590, "loss": 1.8624, "learning_rate": 8.268266191314848e-05, "epoch": 1.0377358490566038, "percentage": 34.59, "elapsed_time": "1:21:57", "remaining_time": "2:34:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1590, "loss": 1.8182, "learning_rate": 8.184412648166183e-05, "epoch": 1.0566037735849056, "percentage": 35.22, "elapsed_time": "1:23:38", "remaining_time": "2:33:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1590, "loss": 1.8391, "learning_rate": 8.099024373630854e-05, "epoch": 1.0754716981132075, "percentage": 35.85, "elapsed_time": "1:25:19", "remaining_time": "2:32:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1590, "loss": 1.8545, "learning_rate": 8.01214252068728e-05, "epoch": 1.0943396226415094, "percentage": 36.48, "elapsed_time": "1:27:00", "remaining_time": "2:31:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1590, "loss": 1.8367, "learning_rate": 7.923808962145734e-05, "epoch": 1.1132075471698113, "percentage": 37.11, "elapsed_time": "1:28:41", "remaining_time": "2:30:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1590, "loss": 1.8149, "learning_rate": 7.83406627046769e-05, "epoch": 1.1320754716981132, "percentage": 37.74, "elapsed_time": "1:30:22", "remaining_time": "2:29:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1590, "loss": 1.8061, "learning_rate": 7.742957697247984e-05, "epoch": 1.150943396226415, "percentage": 38.36, "elapsed_time": "1:32:03", "remaining_time": "2:27:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1590, "loss": 1.8411, "learning_rate": 7.650527152369647e-05, "epoch": 1.169811320754717, "percentage": 38.99, "elapsed_time": "1:33:44", "remaining_time": "2:26:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1590, "loss": 1.8264, "learning_rate": 7.556819182841497e-05, "epoch": 1.1886792452830188, "percentage": 39.62, "elapsed_time": "1:35:24", "remaining_time": "2:25:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1590, "loss": 1.8954, "learning_rate": 7.461878951328653e-05, "epoch": 1.2075471698113207, "percentage": 40.25, "elapsed_time": "1:37:05", "remaining_time": "2:24:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1590, "loss": 1.8346, "learning_rate": 7.365752214386321e-05, "epoch": 1.2264150943396226, "percentage": 40.88, "elapsed_time": "1:38:46", "remaining_time": "2:22:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 660, "total_steps": 1590, "loss": 1.8805, "learning_rate": 7.268485300407393e-05, "epoch": 1.2452830188679245, "percentage": 41.51, "elapsed_time": "1:40:27", "remaining_time": "2:21:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 1590, "loss": 1.7728, "learning_rate": 7.17012508729441e-05, "epoch": 1.2641509433962264, "percentage": 42.14, "elapsed_time": "1:42:08", "remaining_time": "2:20:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 1590, "loss": 1.8718, "learning_rate": 7.070718979866702e-05, "epoch": 1.2830188679245282, "percentage": 42.77, "elapsed_time": "1:43:48", "remaining_time": "2:18:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 1590, "loss": 1.8535, "learning_rate": 6.970314887013584e-05, "epoch": 1.3018867924528301, "percentage": 43.4, "elapsed_time": "1:45:29", "remaining_time": "2:17:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1590, "loss": 1.8344, "learning_rate": 6.868961198604611e-05, "epoch": 1.320754716981132, "percentage": 44.03, "elapsed_time": "1:47:08", "remaining_time": "2:16:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 710, "total_steps": 1590, "loss": 1.8759, "learning_rate": 6.766706762168022e-05, "epoch": 1.3396226415094339, "percentage": 44.65, "elapsed_time": "1:48:46", "remaining_time": "2:14:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 720, "total_steps": 1590, "loss": 1.7973, "learning_rate": 6.663600859348616e-05, "epoch": 1.3584905660377358, "percentage": 45.28, "elapsed_time": "1:50:24", "remaining_time": "2:13:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 730, "total_steps": 1590, "loss": 1.8101, "learning_rate": 6.55969318215641e-05, "epoch": 1.3773584905660377, "percentage": 45.91, "elapsed_time": "1:52:02", "remaining_time": "2:11:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 740, "total_steps": 1590, "loss": 1.8574, "learning_rate": 6.455033809017512e-05, "epoch": 1.3962264150943398, "percentage": 46.54, "elapsed_time": "1:53:39", "remaining_time": "2:10:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 750, "total_steps": 1590, "loss": 1.8194, "learning_rate": 6.34967318063877e-05, "epoch": 1.4150943396226414, "percentage": 47.17, "elapsed_time": "1:55:17", "remaining_time": "2:09:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 760, "total_steps": 1590, "loss": 1.8557, "learning_rate": 6.24366207569781e-05, "epoch": 1.4339622641509435, "percentage": 47.8, "elapsed_time": "1:56:55", "remaining_time": "2:07:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 770, "total_steps": 1590, "loss": 1.8403, "learning_rate": 6.137051586370194e-05, "epoch": 1.4528301886792452, "percentage": 48.43, "elapsed_time": "1:58:32", "remaining_time": "2:06:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 780, "total_steps": 1590, "loss": 1.86, "learning_rate": 6.029893093705492e-05, "epoch": 1.4716981132075473, "percentage": 49.06, "elapsed_time": "2:00:10", "remaining_time": "2:04:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 790, "total_steps": 1590, "loss": 1.8223, "learning_rate": 5.9222382428641174e-05, "epoch": 1.490566037735849, "percentage": 49.69, "elapsed_time": "2:01:48", "remaining_time": "2:03:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1590, "loss": 1.7957, "learning_rate": 5.814138918226887e-05, "epoch": 1.509433962264151, "percentage": 50.31, "elapsed_time": "2:03:25", "remaining_time": "2:01:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1590, "loss": 1.8542, "learning_rate": 5.7056472183892806e-05, "epoch": 1.5283018867924527, "percentage": 50.94, "elapsed_time": "2:05:03", "remaining_time": "2:00:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1590, "loss": 1.8043, "learning_rate": 5.5968154310524614e-05, "epoch": 1.5471698113207548, "percentage": 51.57, "elapsed_time": "2:06:41", "remaining_time": "1:58:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1590, "loss": 1.7981, "learning_rate": 5.487696007823161e-05, "epoch": 1.5660377358490565, "percentage": 52.2, "elapsed_time": "2:08:19", "remaining_time": "1:57:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1590, "loss": 1.8313, "learning_rate": 5.378341538934566e-05, "epoch": 1.5849056603773586, "percentage": 52.83, "elapsed_time": "2:10:02", "remaining_time": "1:56:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1590, "loss": 1.8476, "learning_rate": 5.268804727900391e-05, "epoch": 1.6037735849056602, "percentage": 53.46, "elapsed_time": "2:11:42", "remaining_time": "1:54:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 1590, "loss": 1.7863, "learning_rate": 5.159138366114358e-05, "epoch": 1.6226415094339623, "percentage": 54.09, "elapsed_time": "2:13:21", "remaining_time": "1:53:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1590, "loss": 1.8363, "learning_rate": 5.049395307407329e-05, "epoch": 1.641509433962264, "percentage": 54.72, "elapsed_time": "2:14:59", "remaining_time": "1:51:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1590, "loss": 1.8004, "learning_rate": 4.9396284425743326e-05, "epoch": 1.6603773584905661, "percentage": 55.35, "elapsed_time": "2:16:38", "remaining_time": "1:50:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1590, "loss": 1.818, "learning_rate": 4.829890673883792e-05, "epoch": 1.6792452830188678, "percentage": 55.97, "elapsed_time": "2:18:16", "remaining_time": "1:48:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1590, "loss": 1.7885, "learning_rate": 4.7202348895812035e-05, "epoch": 1.6981132075471699, "percentage": 56.6, "elapsed_time": "2:19:54", "remaining_time": "1:47:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 910, "total_steps": 1590, "loss": 1.7906, "learning_rate": 4.610713938399601e-05, "epoch": 1.7169811320754715, "percentage": 57.23, "elapsed_time": "2:21:33", "remaining_time": "1:45:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 1590, "loss": 1.7858, "learning_rate": 4.5013806040890294e-05, "epoch": 1.7358490566037736, "percentage": 57.86, "elapsed_time": "2:23:12", "remaining_time": "1:44:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 1590, "loss": 1.7796, "learning_rate": 4.392287579977374e-05, "epoch": 1.7547169811320755, "percentage": 58.49, "elapsed_time": "2:24:50", "remaining_time": "1:42:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 1590, "loss": 1.7666, "learning_rate": 4.2834874435747305e-05, "epoch": 1.7735849056603774, "percentage": 59.12, "elapsed_time": "2:26:29", "remaining_time": "1:41:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1590, "loss": 1.7516, "learning_rate": 4.1750326312336254e-05, "epoch": 1.7924528301886793, "percentage": 59.75, "elapsed_time": "2:28:07", "remaining_time": "1:39:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 960, "total_steps": 1590, "loss": 1.7904, "learning_rate": 4.066975412877255e-05, "epoch": 1.8113207547169812, "percentage": 60.38, "elapsed_time": "2:29:45", "remaining_time": "1:38:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 970, "total_steps": 1590, "loss": 1.7605, "learning_rate": 3.959367866807926e-05, "epoch": 1.830188679245283, "percentage": 61.01, "elapsed_time": "2:31:24", "remaining_time": "1:36:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 980, "total_steps": 1590, "loss": 1.8169, "learning_rate": 3.852261854607866e-05, "epoch": 1.849056603773585, "percentage": 61.64, "elapsed_time": "2:33:02", "remaining_time": "1:35:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 990, "total_steps": 1590, "loss": 1.7652, "learning_rate": 3.7457089961444636e-05, "epoch": 1.8679245283018868, "percentage": 62.26, "elapsed_time": "2:34:40", "remaining_time": "1:33:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1000, "total_steps": 1590, "loss": 1.75, "learning_rate": 3.6397606446920294e-05, "epoch": 1.8867924528301887, "percentage": 62.89, "elapsed_time": "2:36:19", "remaining_time": "1:32:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1000, "total_steps": 1590, "eval_loss": 2.2884254455566406, "epoch": 1.8867924528301887, "percentage": 62.89, "elapsed_time": "2:39:04", "remaining_time": "1:33:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1010, "total_steps": 1590, "loss": 1.7847, "learning_rate": 3.534467862182008e-05, "epoch": 1.9056603773584906, "percentage": 63.52, "elapsed_time": "2:41:45", "remaining_time": "1:32:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1020, "total_steps": 1590, "loss": 1.7737, "learning_rate": 3.4298813945936295e-05, "epoch": 1.9245283018867925, "percentage": 64.15, "elapsed_time": "2:43:27", "remaining_time": "1:31:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1030, "total_steps": 1590, "loss": 1.7281, "learning_rate": 3.3260516474968285e-05, "epoch": 1.9433962264150944, "percentage": 64.78, "elapsed_time": "2:45:08", "remaining_time": "1:29:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1040, "total_steps": 1590, "loss": 1.7924, "learning_rate": 3.223028661759211e-05, "epoch": 1.9622641509433962, "percentage": 65.41, "elapsed_time": "2:46:48", "remaining_time": "1:28:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1590, "loss": 1.7397, "learning_rate": 3.12086208942881e-05, "epoch": 1.9811320754716981, "percentage": 66.04, "elapsed_time": "2:48:28", "remaining_time": "1:26:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1060, "total_steps": 1590, "loss": 1.6932, "learning_rate": 3.019601169804216e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:50:09", "remaining_time": "1:25:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1070, "total_steps": 1590, "loss": 0.6881, "learning_rate": 2.919294705703647e-05, "epoch": 2.018867924528302, "percentage": 67.3, "elapsed_time": "2:51:49", "remaining_time": "1:23:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1080, "total_steps": 1590, "loss": 0.6078, "learning_rate": 2.819991039944363e-05, "epoch": 2.0377358490566038, "percentage": 67.92, "elapsed_time": "2:53:29", "remaining_time": "1:21:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1090, "total_steps": 1590, "loss": 0.6092, "learning_rate": 2.7217380320437978e-05, "epoch": 2.056603773584906, "percentage": 68.55, "elapsed_time": "2:55:09", "remaining_time": "1:20:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1590, "loss": 0.585, "learning_rate": 2.624583035153609e-05, "epoch": 2.0754716981132075, "percentage": 69.18, "elapsed_time": "2:56:49", "remaining_time": "1:18:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1110, "total_steps": 1590, "loss": 0.577, "learning_rate": 2.5285728732377613e-05, "epoch": 2.0943396226415096, "percentage": 69.81, "elapsed_time": "2:58:29", "remaining_time": "1:17:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1120, "total_steps": 1590, "loss": 0.551, "learning_rate": 2.4337538185056762e-05, "epoch": 2.1132075471698113, "percentage": 70.44, "elapsed_time": "3:00:08", "remaining_time": "1:15:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1130, "total_steps": 1590, "loss": 0.556, "learning_rate": 2.3401715691112746e-05, "epoch": 2.1320754716981134, "percentage": 71.07, "elapsed_time": "3:01:48", "remaining_time": "1:14:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1140, "total_steps": 1590, "loss": 0.5711, "learning_rate": 2.247871227128709e-05, "epoch": 2.150943396226415, "percentage": 71.7, "elapsed_time": "3:03:28", "remaining_time": "1:12:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1150, "total_steps": 1590, "loss": 0.5601, "learning_rate": 2.1568972768153556e-05, "epoch": 2.169811320754717, "percentage": 72.33, "elapsed_time": "3:05:07", "remaining_time": "1:10:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1160, "total_steps": 1590, "loss": 0.5609, "learning_rate": 2.067293563172581e-05, "epoch": 2.188679245283019, "percentage": 72.96, "elapsed_time": "3:06:47", "remaining_time": "1:09:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1170, "total_steps": 1590, "loss": 0.5417, "learning_rate": 1.9791032708145963e-05, "epoch": 2.207547169811321, "percentage": 73.58, "elapsed_time": "3:08:27", "remaining_time": "1:07:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1180, "total_steps": 1590, "loss": 0.5635, "learning_rate": 1.8923689031555697e-05, "epoch": 2.2264150943396226, "percentage": 74.21, "elapsed_time": "3:10:07", "remaining_time": "1:06:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1190, "total_steps": 1590, "loss": 0.5371, "learning_rate": 1.807132261925073e-05, "epoch": 2.2452830188679247, "percentage": 74.84, "elapsed_time": "3:11:47", "remaining_time": "1:04:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1200, "total_steps": 1590, "loss": 0.5459, "learning_rate": 1.7234344270216713e-05, "epoch": 2.2641509433962264, "percentage": 75.47, "elapsed_time": "3:13:27", "remaining_time": "1:02:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1210, "total_steps": 1590, "loss": 0.5608, "learning_rate": 1.6413157367144354e-05, "epoch": 2.2830188679245285, "percentage": 76.1, "elapsed_time": "3:15:12", "remaining_time": "1:01:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1220, "total_steps": 1590, "loss": 0.5613, "learning_rate": 1.5608157682018505e-05, "epoch": 2.30188679245283, "percentage": 76.73, "elapsed_time": "3:16:53", "remaining_time": "0:59:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1230, "total_steps": 1590, "loss": 0.537, "learning_rate": 1.4819733185375534e-05, "epoch": 2.3207547169811322, "percentage": 77.36, "elapsed_time": "3:18:33", "remaining_time": "0:58:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1240, "total_steps": 1590, "loss": 0.5425, "learning_rate": 1.4048263859320344e-05, "epoch": 2.339622641509434, "percentage": 77.99, "elapsed_time": "3:20:13", "remaining_time": "0:56:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1250, "total_steps": 1590, "loss": 0.5289, "learning_rate": 1.3294121514393637e-05, "epoch": 2.358490566037736, "percentage": 78.62, "elapsed_time": "3:21:53", "remaining_time": "0:54:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1260, "total_steps": 1590, "loss": 0.5155, "learning_rate": 1.2557669610377399e-05, "epoch": 2.3773584905660377, "percentage": 79.25, "elapsed_time": "3:23:34", "remaining_time": "0:53:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1270, "total_steps": 1590, "loss": 0.5214, "learning_rate": 1.1839263081124946e-05, "epoch": 2.3962264150943398, "percentage": 79.87, "elapsed_time": "3:25:14", "remaining_time": "0:51:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1280, "total_steps": 1590, "loss": 0.5326, "learning_rate": 1.113924816350026e-05, "epoch": 2.4150943396226414, "percentage": 80.5, "elapsed_time": "3:26:54", "remaining_time": "0:50:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1290, "total_steps": 1590, "loss": 0.5218, "learning_rate": 1.04579622305086e-05, "epoch": 2.4339622641509435, "percentage": 81.13, "elapsed_time": "3:28:34", "remaining_time": "0:48:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1300, "total_steps": 1590, "loss": 0.5341, "learning_rate": 9.795733628699333e-06, "epoch": 2.452830188679245, "percentage": 81.76, "elapsed_time": "3:30:14", "remaining_time": "0:46:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1310, "total_steps": 1590, "loss": 0.5102, "learning_rate": 9.152881519918787e-06, "epoch": 2.4716981132075473, "percentage": 82.39, "elapsed_time": "3:31:54", "remaining_time": "0:45:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1320, "total_steps": 1590, "loss": 0.5113, "learning_rate": 8.529715727489912e-06, "epoch": 2.490566037735849, "percentage": 83.02, "elapsed_time": "3:33:34", "remaining_time": "0:43:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1330, "total_steps": 1590, "loss": 0.51, "learning_rate": 7.926536586892591e-06, "epoch": 2.509433962264151, "percentage": 83.65, "elapsed_time": "3:35:14", "remaining_time": "0:42:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1340, "total_steps": 1590, "loss": 0.5075, "learning_rate": 7.3436348010165025e-06, "epoch": 2.5283018867924527, "percentage": 84.28, "elapsed_time": "3:36:54", "remaining_time": "0:40:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1350, "total_steps": 1590, "loss": 0.5111, "learning_rate": 6.781291300056647e-06, "epoch": 2.547169811320755, "percentage": 84.91, "elapsed_time": "3:38:34", "remaining_time": "0:38:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1360, "total_steps": 1590, "loss": 0.501, "learning_rate": 6.239777106118605e-06, "epoch": 2.5660377358490565, "percentage": 85.53, "elapsed_time": "3:40:14", "remaining_time": "0:37:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1370, "total_steps": 1590, "loss": 0.5065, "learning_rate": 5.719353202599209e-06, "epoch": 2.5849056603773586, "percentage": 86.16, "elapsed_time": "3:41:54", "remaining_time": "0:35:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1380, "total_steps": 1590, "loss": 0.5268, "learning_rate": 5.220270408405198e-06, "epoch": 2.6037735849056602, "percentage": 86.79, "elapsed_time": "3:43:35", "remaining_time": "0:34:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1390, "total_steps": 1590, "loss": 0.5225, "learning_rate": 4.7427692570708445e-06, "epoch": 2.6226415094339623, "percentage": 87.42, "elapsed_time": "3:45:16", "remaining_time": "0:32:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1400, "total_steps": 1590, "loss": 0.5094, "learning_rate": 4.287079880832478e-06, "epoch": 2.641509433962264, "percentage": 88.05, "elapsed_time": "3:47:02", "remaining_time": "0:30:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1410, "total_steps": 1590, "loss": 0.4991, "learning_rate": 3.853421899715992e-06, "epoch": 2.660377358490566, "percentage": 88.68, "elapsed_time": "3:48:43", "remaining_time": "0:29:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1420, "total_steps": 1590, "loss": 0.5011, "learning_rate": 3.44200431569075e-06, "epoch": 2.6792452830188678, "percentage": 89.31, "elapsed_time": "3:50:24", "remaining_time": "0:27:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1430, "total_steps": 1590, "loss": 0.4954, "learning_rate": 3.053025411940802e-06, "epoch": 2.69811320754717, "percentage": 89.94, "elapsed_time": "3:52:05", "remaining_time": "0:25:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1440, "total_steps": 1590, "loss": 0.5054, "learning_rate": 2.6866726573021026e-06, "epoch": 2.7169811320754715, "percentage": 90.57, "elapsed_time": "3:53:46", "remaining_time": "0:24:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1450, "total_steps": 1590, "loss": 0.5154, "learning_rate": 2.3431226159116637e-06, "epoch": 2.7358490566037736, "percentage": 91.19, "elapsed_time": "3:55:27", "remaining_time": "0:22:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1460, "total_steps": 1590, "loss": 0.5029, "learning_rate": 2.022540862112282e-06, "epoch": 2.7547169811320753, "percentage": 91.82, "elapsed_time": "3:57:07", "remaining_time": "0:21:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1470, "total_steps": 1590, "loss": 0.5147, "learning_rate": 1.725081900653791e-06, "epoch": 2.7735849056603774, "percentage": 92.45, "elapsed_time": "3:58:48", "remaining_time": "0:19:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1480, "total_steps": 1590, "loss": 0.4882, "learning_rate": 1.4508890922293018e-06, "epoch": 2.7924528301886795, "percentage": 93.08, "elapsed_time": "4:00:29", "remaining_time": "0:17:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1490, "total_steps": 1590, "loss": 0.4909, "learning_rate": 1.2000945843823551e-06, "epoch": 2.811320754716981, "percentage": 93.71, "elapsed_time": "4:02:09", "remaining_time": "0:16:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1590, "loss": 0.485, "learning_rate": 9.728192478182574e-07, "epoch": 2.830188679245283, "percentage": 94.34, "elapsed_time": "4:03:50", "remaining_time": "0:14:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1510, "total_steps": 1590, "loss": 0.4985, "learning_rate": 7.691726181503267e-07, "epoch": 2.849056603773585, "percentage": 94.97, "elapsed_time": "4:05:30", "remaining_time": "0:13:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1520, "total_steps": 1590, "loss": 0.4816, "learning_rate": 5.892528431090393e-07, "epoch": 2.867924528301887, "percentage": 95.6, "elapsed_time": "4:07:11", "remaining_time": "0:11:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1530, "total_steps": 1590, "loss": 0.4955, "learning_rate": 4.331466352396396e-07, "epoch": 2.8867924528301887, "percentage": 96.23, "elapsed_time": "4:08:52", "remaining_time": "0:09:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1540, "total_steps": 1590, "loss": 0.5018, "learning_rate": 3.009292301109412e-07, "epoch": 2.9056603773584904, "percentage": 96.86, "elapsed_time": "4:10:32", "remaining_time": "0:08:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1550, "total_steps": 1590, "loss": 0.5011, "learning_rate": 1.9266435005540483e-07, "epoch": 2.9245283018867925, "percentage": 97.48, "elapsed_time": "4:12:13", "remaining_time": "0:06:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1560, "total_steps": 1590, "loss": 0.5141, "learning_rate": 1.0840417345814313e-07, "epoch": 2.9433962264150946, "percentage": 98.11, "elapsed_time": "4:13:53", "remaining_time": "0:04:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1570, "total_steps": 1590, "loss": 0.4904, "learning_rate": 4.818930960945878e-08, "epoch": 2.9622641509433962, "percentage": 98.74, "elapsed_time": "4:15:34", "remaining_time": "0:03:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1580, "total_steps": 1590, "loss": 0.4746, "learning_rate": 1.2048779133150279e-08, "epoch": 2.981132075471698, "percentage": 99.37, "elapsed_time": "4:17:14", "remaining_time": "0:01:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1590, "total_steps": 1590, "loss": 0.5039, "learning_rate": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:18:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1590, "total_steps": 1590, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:19:44", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,1163 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 1000,
+  "global_step": 1590,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018867924528301886,
+      "grad_norm": 2.9446594971470272,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 2.3241,
+      "step": 10
+    },
+    {
+      "epoch": 0.03773584905660377,
+      "grad_norm": 3.2052443029455557,
+      "learning_rate": 1.2578616352201259e-05,
+      "loss": 2.2496,
+      "step": 20
+    },
+    {
+      "epoch": 0.05660377358490566,
+      "grad_norm": 2.593311686421377,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 2.2836,
+      "step": 30
+    },
+    {
+      "epoch": 0.07547169811320754,
+      "grad_norm": 2.8033026461409043,
+      "learning_rate": 2.5157232704402517e-05,
+      "loss": 2.2567,
+      "step": 40
+    },
+    {
+      "epoch": 0.09433962264150944,
+      "grad_norm": 3.0647958985618127,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 2.2749,
+      "step": 50
+    },
+    {
+      "epoch": 0.11320754716981132,
+      "grad_norm": 2.7224942436893023,
+      "learning_rate": 3.7735849056603776e-05,
+      "loss": 2.3334,
+      "step": 60
+    },
+    {
+      "epoch": 0.1320754716981132,
+      "grad_norm": 2.507797193629058,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 2.3378,
+      "step": 70
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 2.791876220429587,
+      "learning_rate": 5.0314465408805034e-05,
+      "loss": 2.3462,
+      "step": 80
+    },
+    {
+      "epoch": 0.16981132075471697,
+      "grad_norm": 2.8934882752144877,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 2.3832,
+      "step": 90
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 2.74130339104755,
+      "learning_rate": 6.289308176100629e-05,
+      "loss": 2.3658,
+      "step": 100
+    },
+    {
+      "epoch": 0.20754716981132076,
+      "grad_norm": 2.464301918797891,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 2.3894,
+      "step": 110
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 3.5787748721128176,
+      "learning_rate": 7.547169811320755e-05,
+      "loss": 2.4635,
+      "step": 120
+    },
+    {
+      "epoch": 0.24528301886792453,
+      "grad_norm": 3.8614586522023586,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 2.4099,
+      "step": 130
+    },
+    {
+      "epoch": 0.2641509433962264,
+      "grad_norm": 2.624798812422503,
+      "learning_rate": 8.805031446540882e-05,
+      "loss": 2.4141,
+      "step": 140
+    },
+    {
+      "epoch": 0.2830188679245283,
+      "grad_norm": 3.4083833226002174,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 2.4505,
+      "step": 150
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 2.4164498878680254,
+      "learning_rate": 9.999987950741765e-05,
+      "loss": 2.4853,
+      "step": 160
+    },
+    {
+      "epoch": 0.32075471698113206,
+      "grad_norm": 4.2037868049637,
+      "learning_rate": 9.9985421100216e-05,
+      "loss": 2.529,
+      "step": 170
+    },
+    {
+      "epoch": 0.33962264150943394,
+      "grad_norm": 10.425711730519438,
+      "learning_rate": 9.99468721610658e-05,
+      "loss": 2.5123,
+      "step": 180
+    },
+    {
+      "epoch": 0.3584905660377358,
+      "grad_norm": 6.075608387062913,
+      "learning_rate": 9.988425126867315e-05,
+      "loss": 2.5137,
+      "step": 190
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 5.979582059920921,
+      "learning_rate": 9.979758860325019e-05,
+      "loss": 2.4818,
+      "step": 200
+    },
+    {
+      "epoch": 0.39622641509433965,
+      "grad_norm": 300.5526680134449,
+      "learning_rate": 9.968692593196944e-05,
+      "loss": 2.5084,
+      "step": 210
+    },
+    {
+      "epoch": 0.41509433962264153,
+      "grad_norm": 2.3641585810185437,
+      "learning_rate": 9.955231658883432e-05,
+      "loss": 2.4667,
+      "step": 220
+    },
+    {
+      "epoch": 0.4339622641509434,
+      "grad_norm": 2.399558237267707,
+      "learning_rate": 9.93938254489746e-05,
+      "loss": 2.4815,
+      "step": 230
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 2.291187744959764,
+      "learning_rate": 9.921152889737984e-05,
+      "loss": 2.465,
+      "step": 240
+    },
+    {
+      "epoch": 0.4716981132075472,
+      "grad_norm": 2.2425372020480685,
+      "learning_rate": 9.900551479208552e-05,
+      "loss": 2.4827,
+      "step": 250
+    },
+    {
+      "epoch": 0.49056603773584906,
+      "grad_norm": 2.106996905280666,
+      "learning_rate": 9.877588242182975e-05,
+      "loss": 2.5077,
+      "step": 260
+    },
+    {
+      "epoch": 0.5094339622641509,
+      "grad_norm": 2.56597906125238,
+      "learning_rate": 9.852274245820096e-05,
+      "loss": 2.5812,
+      "step": 270
+    },
+    {
+      "epoch": 0.5283018867924528,
+      "grad_norm": 2.1161401839810323,
+      "learning_rate": 9.824621690229965e-05,
+      "loss": 2.5047,
+      "step": 280
+    },
+    {
+      "epoch": 0.5471698113207547,
+      "grad_norm": 2.9746454428316467,
+      "learning_rate": 9.79464390259397e-05,
+      "loss": 2.4985,
+      "step": 290
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 2.1237673830934156,
+      "learning_rate": 9.762355330741796e-05,
+      "loss": 2.4943,
+      "step": 300
+    },
+    {
+      "epoch": 0.5849056603773585,
+      "grad_norm": 1.8440846284987655,
+      "learning_rate": 9.727771536188275e-05,
+      "loss": 2.4536,
+      "step": 310
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 3.3815527986620526,
+      "learning_rate": 9.690909186633492e-05,
+      "loss": 2.4837,
+      "step": 320
+    },
+    {
+      "epoch": 0.6226415094339622,
+      "grad_norm": 2.7797010587604953,
+      "learning_rate": 9.651786047929773e-05,
+      "loss": 2.5074,
+      "step": 330
+    },
+    {
+      "epoch": 0.6415094339622641,
+      "grad_norm": 2.0947283835947794,
+      "learning_rate": 9.610420975519408e-05,
+      "loss": 2.441,
+      "step": 340
+    },
+    {
+      "epoch": 0.660377358490566,
+      "grad_norm": 1.9288902952601223,
+      "learning_rate": 9.566833905347245e-05,
+      "loss": 2.4885,
+      "step": 350
+    },
+    {
+      "epoch": 0.6792452830188679,
+      "grad_norm": 2.004635564736395,
+      "learning_rate": 9.521045844252552e-05,
+      "loss": 2.4342,
+      "step": 360
+    },
+    {
+      "epoch": 0.6981132075471698,
+      "grad_norm": 1.6511867070394874,
+      "learning_rate": 9.473078859844728e-05,
+      "loss": 2.4425,
+      "step": 370
+    },
+    {
+      "epoch": 0.7169811320754716,
+      "grad_norm": 1.4598720970043289,
+      "learning_rate": 9.422956069867807e-05,
+      "loss": 2.4567,
+      "step": 380
+    },
+    {
+      "epoch": 0.7358490566037735,
+      "grad_norm": 1.5295808219144331,
+      "learning_rate": 9.370701631058829e-05,
+      "loss": 2.4636,
+      "step": 390
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 1.606602994374719,
+      "learning_rate": 9.316340727505468e-05,
+      "loss": 2.4707,
+      "step": 400
+    },
+    {
+      "epoch": 0.7735849056603774,
+      "grad_norm": 1.5773231811089237,
+      "learning_rate": 9.259899558508543e-05,
+      "loss": 2.4242,
+      "step": 410
+    },
+    {
+      "epoch": 0.7924528301886793,
+      "grad_norm": 1.5694593702673683,
+      "learning_rate": 9.201405325955221e-05,
+      "loss": 2.4754,
+      "step": 420
+    },
+    {
+      "epoch": 0.8113207547169812,
+      "grad_norm": 1.4513304920200845,
+      "learning_rate": 9.14088622120905e-05,
+      "loss": 2.4735,
+      "step": 430
+    },
+    {
+      "epoch": 0.8301886792452831,
+      "grad_norm": 2.2119679560211436,
+      "learning_rate": 9.078371411523084e-05,
+      "loss": 2.4511,
+      "step": 440
+    },
+    {
+      "epoch": 0.8490566037735849,
+      "grad_norm": 1.4837853314532448,
+      "learning_rate": 9.013891025982704e-05,
+      "loss": 2.4627,
+      "step": 450
+    },
+    {
+      "epoch": 0.8679245283018868,
+      "grad_norm": 1.548323059472257,
+      "learning_rate": 8.947476140984856e-05,
+      "loss": 2.4804,
+      "step": 460
+    },
+    {
+      "epoch": 0.8867924528301887,
+      "grad_norm": 1.7369189464037587,
+      "learning_rate": 8.879158765260767e-05,
+      "loss": 2.4872,
+      "step": 470
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 1.4222000085980089,
+      "learning_rate": 8.808971824449275e-05,
+      "loss": 2.4847,
+      "step": 480
+    },
+    {
+      "epoch": 0.9245283018867925,
+      "grad_norm": 1.39169720237414,
+      "learning_rate": 8.736949145228295e-05,
+      "loss": 2.4873,
+      "step": 490
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 1.5495461414725966,
+      "learning_rate": 8.66312543901201e-05,
+      "loss": 2.4738,
+      "step": 500
+    },
+    {
+      "epoch": 0.9622641509433962,
+      "grad_norm": 1.5689856394055257,
+      "learning_rate": 8.587536285221656e-05,
+      "loss": 2.4211,
+      "step": 510
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "grad_norm": 1.559462761559426,
+      "learning_rate": 8.510218114137992e-05,
+      "loss": 2.4183,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.38445361325361,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 2.459,
+      "step": 530
+    },
+    {
+      "epoch": 1.0188679245283019,
+      "grad_norm": 1.8042327175721304,
+      "learning_rate": 8.350544589764016e-05,
+      "loss": 1.8838,
+      "step": 540
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "grad_norm": 1.8176496290402602,
+      "learning_rate": 8.268266191314848e-05,
+      "loss": 1.8624,
+      "step": 550
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "grad_norm": 1.8868344352432986,
+      "learning_rate": 8.184412648166183e-05,
+      "loss": 1.8182,
+      "step": 560
+    },
+    {
+      "epoch": 1.0754716981132075,
+      "grad_norm": 1.7299260995769612,
+      "learning_rate": 8.099024373630854e-05,
+      "loss": 1.8391,
+      "step": 570
+    },
+    {
+      "epoch": 1.0943396226415094,
+      "grad_norm": 1.9113984544679725,
+      "learning_rate": 8.01214252068728e-05,
+      "loss": 1.8545,
+      "step": 580
+    },
+    {
+      "epoch": 1.1132075471698113,
+      "grad_norm": 1.794174287705714,
+      "learning_rate": 7.923808962145734e-05,
+      "loss": 1.8367,
+      "step": 590
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 1.5751797225379325,
+      "learning_rate": 7.83406627046769e-05,
+      "loss": 1.8149,
+      "step": 600
+    },
+    {
+      "epoch": 1.150943396226415,
+      "grad_norm": 1.9105350922209694,
+      "learning_rate": 7.742957697247984e-05,
+      "loss": 1.8061,
+      "step": 610
+    },
+    {
+      "epoch": 1.169811320754717,
+      "grad_norm": 1.7630498555967447,
+      "learning_rate": 7.650527152369647e-05,
+      "loss": 1.8411,
+      "step": 620
+    },
+    {
+      "epoch": 1.1886792452830188,
+      "grad_norm": 1.5261816105997068,
+      "learning_rate": 7.556819182841497e-05,
+      "loss": 1.8264,
+      "step": 630
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 1.9369411893196908,
+      "learning_rate": 7.461878951328653e-05,
+      "loss": 1.8954,
+      "step": 640
+    },
+    {
+      "epoch": 1.2264150943396226,
+      "grad_norm": 1.7688000917923798,
+      "learning_rate": 7.365752214386321e-05,
+      "loss": 1.8346,
+      "step": 650
+    },
+    {
+      "epoch": 1.2452830188679245,
+      "grad_norm": 1.6569058541238642,
+      "learning_rate": 7.268485300407393e-05,
+      "loss": 1.8805,
+      "step": 660
+    },
+    {
+      "epoch": 1.2641509433962264,
+      "grad_norm": 1.6708545601020437,
+      "learning_rate": 7.17012508729441e-05,
+      "loss": 1.7728,
+      "step": 670
+    },
+    {
+      "epoch": 1.2830188679245282,
+      "grad_norm": 1.652310201967167,
+      "learning_rate": 7.070718979866702e-05,
+      "loss": 1.8718,
+      "step": 680
+    },
+    {
+      "epoch": 1.3018867924528301,
+      "grad_norm": 1.9899020380799617,
+      "learning_rate": 6.970314887013584e-05,
+      "loss": 1.8535,
+      "step": 690
+    },
+    {
+      "epoch": 1.320754716981132,
+      "grad_norm": 1.643783798160392,
+      "learning_rate": 6.868961198604611e-05,
+      "loss": 1.8344,
+      "step": 700
+    },
+    {
+      "epoch": 1.3396226415094339,
+      "grad_norm": 1.8435538882684133,
+      "learning_rate": 6.766706762168022e-05,
+      "loss": 1.8759,
+      "step": 710
+    },
+    {
+      "epoch": 1.3584905660377358,
+      "grad_norm": 1.6989197917459231,
+      "learning_rate": 6.663600859348616e-05,
+      "loss": 1.7973,
+      "step": 720
+    },
+    {
+      "epoch": 1.3773584905660377,
+      "grad_norm": 1.6640164364452317,
+      "learning_rate": 6.55969318215641e-05,
+      "loss": 1.8101,
+      "step": 730
+    },
+    {
+      "epoch": 1.3962264150943398,
+      "grad_norm": 1.663705205393152,
+      "learning_rate": 6.455033809017512e-05,
+      "loss": 1.8574,
+      "step": 740
+    },
+    {
+      "epoch": 1.4150943396226414,
+      "grad_norm": 1.524574911562225,
+      "learning_rate": 6.34967318063877e-05,
+      "loss": 1.8194,
+      "step": 750
+    },
+    {
+      "epoch": 1.4339622641509435,
+      "grad_norm": 1.638744038935454,
+      "learning_rate": 6.24366207569781e-05,
+      "loss": 1.8557,
+      "step": 760
+    },
+    {
+      "epoch": 1.4528301886792452,
+      "grad_norm": 1.5905792259719815,
+      "learning_rate": 6.137051586370194e-05,
+      "loss": 1.8403,
+      "step": 770
+    },
+    {
+      "epoch": 1.4716981132075473,
+      "grad_norm": 1.4115389229640394,
+      "learning_rate": 6.029893093705492e-05,
+      "loss": 1.86,
+      "step": 780
+    },
+    {
+      "epoch": 1.490566037735849,
+      "grad_norm": 1.5664716217022607,
+      "learning_rate": 5.9222382428641174e-05,
+      "loss": 1.8223,
+      "step": 790
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 1.3426007079954652,
+      "learning_rate": 5.814138918226887e-05,
+      "loss": 1.7957,
+      "step": 800
+    },
+    {
+      "epoch": 1.5283018867924527,
+      "grad_norm": 1.4496928054044773,
+      "learning_rate": 5.7056472183892806e-05,
+      "loss": 1.8542,
+      "step": 810
+    },
+    {
+      "epoch": 1.5471698113207548,
+      "grad_norm": 1.7249530177698127,
+      "learning_rate": 5.5968154310524614e-05,
+      "loss": 1.8043,
+      "step": 820
+    },
+    {
+      "epoch": 1.5660377358490565,
+      "grad_norm": 1.4451712049547103,
+      "learning_rate": 5.487696007823161e-05,
+      "loss": 1.7981,
+      "step": 830
+    },
+    {
+      "epoch": 1.5849056603773586,
+      "grad_norm": 1.5035729769726907,
+      "learning_rate": 5.378341538934566e-05,
+      "loss": 1.8313,
+      "step": 840
+    },
+    {
+      "epoch": 1.6037735849056602,
+      "grad_norm": 1.3823097737594126,
+      "learning_rate": 5.268804727900391e-05,
+      "loss": 1.8476,
+      "step": 850
+    },
+    {
+      "epoch": 1.6226415094339623,
+      "grad_norm": 1.41439773210909,
+      "learning_rate": 5.159138366114358e-05,
+      "loss": 1.7863,
+      "step": 860
+    },
+    {
+      "epoch": 1.641509433962264,
+      "grad_norm": 1.513162165314957,
+      "learning_rate": 5.049395307407329e-05,
+      "loss": 1.8363,
+      "step": 870
+    },
+    {
+      "epoch": 1.6603773584905661,
+      "grad_norm": 1.5375457880909025,
+      "learning_rate": 4.9396284425743326e-05,
+      "loss": 1.8004,
+      "step": 880
+    },
+    {
+      "epoch": 1.6792452830188678,
+      "grad_norm": 1.5695919072614308,
+      "learning_rate": 4.829890673883792e-05,
+      "loss": 1.818,
+      "step": 890
+    },
+    {
+      "epoch": 1.6981132075471699,
+      "grad_norm": 1.3666688643802247,
+      "learning_rate": 4.7202348895812035e-05,
+      "loss": 1.7885,
+      "step": 900
+    },
+    {
+      "epoch": 1.7169811320754715,
+      "grad_norm": 1.6027481528500458,
+      "learning_rate": 4.610713938399601e-05,
+      "loss": 1.7906,
+      "step": 910
+    },
+    {
+      "epoch": 1.7358490566037736,
+      "grad_norm": 1.3930291385793376,
+      "learning_rate": 4.5013806040890294e-05,
+      "loss": 1.7858,
+      "step": 920
+    },
+    {
+      "epoch": 1.7547169811320755,
+      "grad_norm": 1.4293209085375194,
+      "learning_rate": 4.392287579977374e-05,
+      "loss": 1.7796,
+      "step": 930
+    },
+    {
+      "epoch": 1.7735849056603774,
+      "grad_norm": 1.5151788900532224,
+      "learning_rate": 4.2834874435747305e-05,
+      "loss": 1.7666,
+      "step": 940
+    },
+    {
+      "epoch": 1.7924528301886793,
+      "grad_norm": 1.5253274784864974,
+      "learning_rate": 4.1750326312336254e-05,
+      "loss": 1.7516,
+      "step": 950
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 1.3957421524480444,
+      "learning_rate": 4.066975412877255e-05,
+      "loss": 1.7904,
+      "step": 960
+    },
+    {
+      "epoch": 1.830188679245283,
+      "grad_norm": 1.399046653332325,
+      "learning_rate": 3.959367866807926e-05,
+      "loss": 1.7605,
+      "step": 970
+    },
+    {
+      "epoch": 1.849056603773585,
+      "grad_norm": 1.48580398039922,
+      "learning_rate": 3.852261854607866e-05,
+      "loss": 1.8169,
+      "step": 980
+    },
+    {
+      "epoch": 1.8679245283018868,
+      "grad_norm": 1.4703556780094864,
+      "learning_rate": 3.7457089961444636e-05,
+      "loss": 1.7652,
+      "step": 990
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 1.4196287584590106,
+      "learning_rate": 3.6397606446920294e-05,
+      "loss": 1.75,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "eval_loss": 2.2884254455566406,
+      "eval_runtime": 165.0682,
+      "eval_samples_per_second": 11.413,
+      "eval_steps_per_second": 2.853,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9056603773584906,
+      "grad_norm": 1.442346199206303,
+      "learning_rate": 3.534467862182008e-05,
+      "loss": 1.7847,
+      "step": 1010
+    },
+    {
+      "epoch": 1.9245283018867925,
+      "grad_norm": 1.3835916856247392,
+      "learning_rate": 3.4298813945936295e-05,
+      "loss": 1.7737,
+      "step": 1020
+    },
+    {
+      "epoch": 1.9433962264150944,
+      "grad_norm": 1.3821884730018883,
+      "learning_rate": 3.3260516474968285e-05,
+      "loss": 1.7281,
+      "step": 1030
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 1.3924722724907153,
+      "learning_rate": 3.223028661759211e-05,
+      "loss": 1.7924,
+      "step": 1040
+    },
+    {
+      "epoch": 1.9811320754716981,
+      "grad_norm": 1.3388702147690976,
+      "learning_rate": 3.12086208942881e-05,
+      "loss": 1.7397,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4015243388990968,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 1.6932,
+      "step": 1060
+    },
+    {
+      "epoch": 2.018867924528302,
+      "grad_norm": 1.7480746986263314,
+      "learning_rate": 2.919294705703647e-05,
+      "loss": 0.6881,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0377358490566038,
+      "grad_norm": 1.7026666847000977,
+      "learning_rate": 2.819991039944363e-05,
+      "loss": 0.6078,
+      "step": 1080
+    },
+    {
+      "epoch": 2.056603773584906,
+      "grad_norm": 1.7917514233908862,
+      "learning_rate": 2.7217380320437978e-05,
+      "loss": 0.6092,
+      "step": 1090
+    },
+    {
+      "epoch": 2.0754716981132075,
+      "grad_norm": 1.6723597171494868,
+      "learning_rate": 2.624583035153609e-05,
+      "loss": 0.585,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0943396226415096,
+      "grad_norm": 1.63904815463906,
+      "learning_rate": 2.5285728732377613e-05,
+      "loss": 0.577,
+      "step": 1110
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "grad_norm": 1.6791437732786112,
+      "learning_rate": 2.4337538185056762e-05,
+      "loss": 0.551,
+      "step": 1120
+    },
+    {
+      "epoch": 2.1320754716981134,
+      "grad_norm": 1.6076545037137666,
+      "learning_rate": 2.3401715691112746e-05,
+      "loss": 0.556,
+      "step": 1130
+    },
+    {
+      "epoch": 2.150943396226415,
+      "grad_norm": 1.726665027733004,
+      "learning_rate": 2.247871227128709e-05,
+      "loss": 0.5711,
+      "step": 1140
+    },
+    {
+      "epoch": 2.169811320754717,
+      "grad_norm": 1.6490156416373818,
+      "learning_rate": 2.1568972768153556e-05,
+      "loss": 0.5601,
+      "step": 1150
+    },
+    {
+      "epoch": 2.188679245283019,
+      "grad_norm": 1.7210537816210676,
+      "learning_rate": 2.067293563172581e-05,
+      "loss": 0.5609,
+      "step": 1160
+    },
+    {
+      "epoch": 2.207547169811321,
+      "grad_norm": 1.6521402147978896,
+      "learning_rate": 1.9791032708145963e-05,
+      "loss": 0.5417,
+      "step": 1170
+    },
+    {
+      "epoch": 2.2264150943396226,
+      "grad_norm": 1.7020323862071838,
+      "learning_rate": 1.8923689031555697e-05,
+      "loss": 0.5635,
+      "step": 1180
+    },
+    {
+      "epoch": 2.2452830188679247,
+      "grad_norm": 1.5791599921066155,
+      "learning_rate": 1.807132261925073e-05,
+      "loss": 0.5371,
+      "step": 1190
+    },
+    {
+      "epoch": 2.2641509433962264,
+      "grad_norm": 1.6370275383685373,
+      "learning_rate": 1.7234344270216713e-05,
+      "loss": 0.5459,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2830188679245285,
+      "grad_norm": 1.649807184686461,
+      "learning_rate": 1.6413157367144354e-05,
+      "loss": 0.5608,
+      "step": 1210
+    },
+    {
+      "epoch": 2.30188679245283,
+      "grad_norm": 1.7662002841569535,
+      "learning_rate": 1.5608157682018505e-05,
+      "loss": 0.5613,
+      "step": 1220
+    },
+    {
+      "epoch": 2.3207547169811322,
+      "grad_norm": 1.641520954901167,
+      "learning_rate": 1.4819733185375534e-05,
+      "loss": 0.537,
+      "step": 1230
+    },
+    {
+      "epoch": 2.339622641509434,
+      "grad_norm": 1.6680780951150302,
+      "learning_rate": 1.4048263859320344e-05,
+      "loss": 0.5425,
+      "step": 1240
+    },
+    {
+      "epoch": 2.358490566037736,
+      "grad_norm": 1.5858289559337815,
+      "learning_rate": 1.3294121514393637e-05,
+      "loss": 0.5289,
+      "step": 1250
+    },
+    {
+      "epoch": 2.3773584905660377,
+      "grad_norm": 1.609281814988441,
+      "learning_rate": 1.2557669610377399e-05,
+      "loss": 0.5155,
+      "step": 1260
+    },
+    {
+      "epoch": 2.3962264150943398,
+      "grad_norm": 1.6108061713809745,
+      "learning_rate": 1.1839263081124946e-05,
+      "loss": 0.5214,
+      "step": 1270
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "grad_norm": 1.5364583247125485,
+      "learning_rate": 1.113924816350026e-05,
+      "loss": 0.5326,
+      "step": 1280
+    },
+    {
+      "epoch": 2.4339622641509435,
+      "grad_norm": 1.523827370861251,
+      "learning_rate": 1.04579622305086e-05,
+      "loss": 0.5218,
+      "step": 1290
+    },
+    {
+      "epoch": 2.452830188679245,
+      "grad_norm": 1.6969638639614046,
+      "learning_rate": 9.795733628699333e-06,
+      "loss": 0.5341,
+      "step": 1300
+    },
+    {
+      "epoch": 2.4716981132075473,
+      "grad_norm": 1.502222163556516,
+      "learning_rate": 9.152881519918787e-06,
+      "loss": 0.5102,
+      "step": 1310
+    },
+    {
+      "epoch": 2.490566037735849,
+      "grad_norm": 1.6251186914379474,
+      "learning_rate": 8.529715727489912e-06,
+      "loss": 0.5113,
+      "step": 1320
+    },
+    {
+      "epoch": 2.509433962264151,
+      "grad_norm": 1.641634385361185,
+      "learning_rate": 7.926536586892591e-06,
+      "loss": 0.51,
+      "step": 1330
+    },
+    {
+      "epoch": 2.5283018867924527,
+      "grad_norm": 1.564996479749529,
+      "learning_rate": 7.3436348010165025e-06,
+      "loss": 0.5075,
+      "step": 1340
+    },
+    {
+      "epoch": 2.547169811320755,
+      "grad_norm": 1.5204914266086813,
+      "learning_rate": 6.781291300056647e-06,
+      "loss": 0.5111,
+      "step": 1350
+    },
+    {
+      "epoch": 2.5660377358490565,
+      "grad_norm": 1.5204438359613908,
+      "learning_rate": 6.239777106118605e-06,
+      "loss": 0.501,
+      "step": 1360
+    },
+    {
+      "epoch": 2.5849056603773586,
+      "grad_norm": 1.6153170323469739,
+      "learning_rate": 5.719353202599209e-06,
+      "loss": 0.5065,
+      "step": 1370
+    },
+    {
+      "epoch": 2.6037735849056602,
+      "grad_norm": 1.532440501266883,
+      "learning_rate": 5.220270408405198e-06,
+      "loss": 0.5268,
+      "step": 1380
+    },
+    {
+      "epoch": 2.6226415094339623,
+      "grad_norm": 1.5295028060682831,
+      "learning_rate": 4.7427692570708445e-06,
+      "loss": 0.5225,
+      "step": 1390
+    },
+    {
+      "epoch": 2.641509433962264,
+      "grad_norm": 1.5576876729006885,
+      "learning_rate": 4.287079880832478e-06,
+      "loss": 0.5094,
+      "step": 1400
+    },
+    {
+      "epoch": 2.660377358490566,
+      "grad_norm": 1.535240889295645,
+      "learning_rate": 3.853421899715992e-06,
+      "loss": 0.4991,
+      "step": 1410
+    },
+    {
+      "epoch": 2.6792452830188678,
+      "grad_norm": 1.5668838039374533,
+      "learning_rate": 3.44200431569075e-06,
+      "loss": 0.5011,
+      "step": 1420
+    },
+    {
+      "epoch": 2.69811320754717,
+      "grad_norm": 1.6597779325377704,
+      "learning_rate": 3.053025411940802e-06,
+      "loss": 0.4954,
+      "step": 1430
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "grad_norm": 1.5562079580978392,
+      "learning_rate": 2.6866726573021026e-06,
+      "loss": 0.5054,
+      "step": 1440
+    },
+    {
+      "epoch": 2.7358490566037736,
+      "grad_norm": 1.5996686204830912,
+      "learning_rate": 2.3431226159116637e-06,
+      "loss": 0.5154,
+      "step": 1450
+    },
+    {
+      "epoch": 2.7547169811320753,
+      "grad_norm": 1.6603987931741782,
+      "learning_rate": 2.022540862112282e-06,
+      "loss": 0.5029,
+      "step": 1460
+    },
+    {
+      "epoch": 2.7735849056603774,
+      "grad_norm": 1.4442160081367916,
+      "learning_rate": 1.725081900653791e-06,
+      "loss": 0.5147,
+      "step": 1470
+    },
+    {
+      "epoch": 2.7924528301886795,
+      "grad_norm": 1.5601472307077258,
+      "learning_rate": 1.4508890922293018e-06,
+      "loss": 0.4882,
+      "step": 1480
+    },
+    {
+      "epoch": 2.811320754716981,
+      "grad_norm": 1.6882814081660615,
+      "learning_rate": 1.2000945843823551e-06,
+      "loss": 0.4909,
+      "step": 1490
+    },
+    {
+      "epoch": 2.830188679245283,
+      "grad_norm": 1.5897926116142052,
+      "learning_rate": 9.728192478182574e-07,
+      "loss": 0.485,
+      "step": 1500
+    },
+    {
+      "epoch": 2.849056603773585,
+      "grad_norm": 1.480162495765326,
+      "learning_rate": 7.691726181503267e-07,
+      "loss": 0.4985,
+      "step": 1510
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 1.5161543246256077,
+      "learning_rate": 5.892528431090393e-07,
+      "loss": 0.4816,
+      "step": 1520
+    },
+    {
+      "epoch": 2.8867924528301887,
+      "grad_norm": 1.5434464499844907,
+      "learning_rate": 4.331466352396396e-07,
+      "loss": 0.4955,
+      "step": 1530
+    },
+    {
+      "epoch": 2.9056603773584904,
+      "grad_norm": 1.5292680330833108,
+      "learning_rate": 3.009292301109412e-07,
+      "loss": 0.5018,
+      "step": 1540
+    },
+    {
+      "epoch": 2.9245283018867925,
+      "grad_norm": 1.501995031518757,
+      "learning_rate": 1.9266435005540483e-07,
+      "loss": 0.5011,
+      "step": 1550
+    },
+    {
+      "epoch": 2.9433962264150946,
+      "grad_norm": 1.5344813758662075,
+      "learning_rate": 1.0840417345814313e-07,
+      "loss": 0.5141,
+      "step": 1560
+    },
+    {
+      "epoch": 2.9622641509433962,
+      "grad_norm": 1.5204098865333115,
+      "learning_rate": 4.818930960945878e-08,
+      "loss": 0.4904,
+      "step": 1570
+    },
+    {
+      "epoch": 2.981132075471698,
+      "grad_norm": 1.5256874098586901,
+      "learning_rate": 1.2048779133150279e-08,
+      "loss": 0.4746,
+      "step": 1580
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4804382321073322,
+      "learning_rate": 0.0,
+      "loss": 0.5039,
+      "step": 1590
+    },
+    {
+      "epoch": 3.0,
+      "step": 1590,
+      "total_flos": 83202240675840.0,
+      "train_loss": 1.594443890733539,
+      "train_runtime": 15602.0514,
+      "train_samples_per_second": 3.26,
+      "train_steps_per_second": 0.102
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 83202240675840.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff70f0597be33b8911125cec7a6eadce68e450c3dd9992879e8d80fc43a1575b
+size 7288