Upload folder using huggingface_hub

README.md

@@ -0,0 +1,102 @@
+---
+license: other
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: C015_llama3-8b-base_instruct_20240504_123713
+  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. -->
+
+# C015_llama3-8b-base_instruct_20240504_123713
+
+This model is a fine-tuned version of [/mnt/fl/projects/pro-align/progressalign/shared_storage/our_models/C015_llama3-8b-base_pretrain_20240428_005832](https://huggingface.co//mnt/fl/projects/pro-align/progressalign/shared_storage/our_models/C015_llama3-8b-base_pretrain_20240428_005832) on the instructions_curated dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8063
+
+## 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: 1.5e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: polynomial
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 4.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8675        | 0.1042 | 5    | 0.8585          |
+| 0.8415        | 0.2083 | 10   | 0.8063          |
+| 0.8225        | 0.3125 | 15   | 0.8210          |
+| 0.806         | 0.4167 | 20   | 0.8412          |
+| 0.8139        | 0.5208 | 25   | 0.8702          |
+| 0.8978        | 0.625  | 30   | 0.8631          |
+| 0.814         | 0.7292 | 35   | 0.8550          |
+| 0.7989        | 0.8333 | 40   | 0.8473          |
+| 0.8769        | 0.9375 | 45   | 0.8383          |
+| 0.7244        | 1.0417 | 50   | 0.8278          |
+| 0.4644        | 1.1458 | 55   | 0.8387          |
+| 0.4488        | 1.25   | 60   | 0.8680          |
+| 0.3973        | 1.3542 | 65   | 0.8718          |
+| 0.443         | 1.4583 | 70   | 0.8596          |
+| 0.4346        | 1.5625 | 75   | 0.8514          |
+| 0.4701        | 1.6667 | 80   | 0.8461          |
+| 0.4344        | 1.7708 | 85   | 0.8437          |
+| 0.4274        | 1.875  | 90   | 0.8434          |
+| 0.4771        | 1.9792 | 95   | 0.8434          |
+| 0.3876        | 2.0833 | 100  | 0.8439          |
+| 0.3698        | 2.1875 | 105  | 0.8451          |
+| 0.407         | 2.2917 | 110  | 0.8465          |
+| 0.374         | 2.3958 | 115  | 0.8482          |
+| 0.3945        | 2.5    | 120  | 0.8498          |
+| 0.3753        | 2.6042 | 125  | 0.8513          |
+| 0.3721        | 2.7083 | 130  | 0.8528          |
+| 0.3718        | 2.8125 | 135  | 0.8542          |
+| 0.3773        | 2.9167 | 140  | 0.8555          |
+| 0.3723        | 3.0208 | 145  | 0.8565          |
+| 0.374         | 3.125  | 150  | 0.8576          |
+| 0.3728        | 3.2292 | 155  | 0.8588          |
+| 0.3686        | 3.3333 | 160  | 0.8598          |
+| 0.3617        | 3.4375 | 165  | 0.8607          |
+| 0.3546        | 3.5417 | 170  | 0.8613          |
+| 0.3707        | 3.6458 | 175  | 0.8619          |
+| 0.3739        | 3.75   | 180  | 0.8625          |
+| 0.3617        | 3.8542 | 185  | 0.8632          |
+| 0.3591        | 3.9583 | 190  | 0.8637          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.8062803149223328,
+    "eval_runtime": 1.9823,
+    "eval_samples_per_second": 171.522,
+    "eval_steps_per_second": 1.513,
+    "total_flos": 5334785064960.0,
+    "train_loss": 0.508326952966551,
+    "train_runtime": 4164.2152,
+    "train_samples_per_second": 2.934,
+    "train_steps_per_second": 0.046
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/fl/projects/pro-align/progressalign/shared_storage/our_models/C015_llama3-8b-base_pretrain_20240428_005832",
+  "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,
+  "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": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.8062803149223328,
+    "eval_runtime": 1.9823,
+    "eval_samples_per_second": 171.522,
+    "eval_steps_per_second": 1.513
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef6764666375baa6c70755ee998e513f62060f5b46913ae34e67abe0e31a72d
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f657d1353892b5d5fe5ed93998f2aa6e88c5a78fc81fb51cb9573ee86d0c8583
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb906e7483301863b75ce9e879e61afb9cf662fee8c8167b7e3221807d8eda6
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adff485e0f3ece17e8f1673a10767ec1fe1aea949fad8118fe8a1e26c16d979
+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 +1,23 @@
+{
+  "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": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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.' %}{% 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": 4.0,
+    "total_flos": 5334785064960.0,
+    "train_loss": 0.508326952966551,
+    "train_runtime": 4164.2152,
+    "train_samples_per_second": 2.934,
+    "train_steps_per_second": 0.046
+}

trainer_log.jsonl

@@ -0,0 +1,79 @@
+{"current_steps": 1, "total_steps": 192, "loss": 0.8766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 0.52, "elapsed_time": "0:00:03", "remaining_time": "0:09:41"}
+{"current_steps": 5, "total_steps": 192, "loss": 0.8675, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.10416666666666667, "percentage": 2.6, "elapsed_time": "0:00:08", "remaining_time": "0:05:18"}
+{"current_steps": 5, "total_steps": 192, "loss": null, "eval_loss": 0.8584801554679871, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.10416666666666667, "percentage": 2.6, "elapsed_time": "0:00:08", "remaining_time": "0:05:18"}
+{"current_steps": 10, "total_steps": 192, "loss": 0.8415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.25e-06, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:59", "remaining_time": "0:18:00"}
+{"current_steps": 10, "total_steps": 192, "loss": null, "eval_loss": 0.8062803149223328, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:59", "remaining_time": "0:18:00"}
+{"current_steps": 15, "total_steps": 192, "loss": 0.8225, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.25e-06, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:01:52", "remaining_time": "0:22:11"}
+{"current_steps": 15, "total_steps": 192, "loss": null, "eval_loss": 0.820951521396637, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:01:52", "remaining_time": "0:22:11"}
+{"current_steps": 20, "total_steps": 192, "loss": 0.806, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2e-05, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:03:49", "remaining_time": "0:32:56"}
+{"current_steps": 20, "total_steps": 192, "loss": null, "eval_loss": 0.8412486910820007, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:03:49", "remaining_time": "0:32:56"}
+{"current_steps": 25, "total_steps": 192, "loss": 0.8139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4071209905461127e-05, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:05:44", "remaining_time": "0:38:20"}
+{"current_steps": 25, "total_steps": 192, "loss": null, "eval_loss": 0.8701534867286682, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:05:44", "remaining_time": "0:38:20"}
+{"current_steps": 30, "total_steps": 192, "loss": 0.8978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0166196232101288e-05, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:07:41", "remaining_time": "0:41:30"}
+{"current_steps": 30, "total_steps": 192, "loss": null, "eval_loss": 0.8630704879760742, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:07:41", "remaining_time": "0:41:30"}
+{"current_steps": 35, "total_steps": 192, "loss": 0.814, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.276248845991498e-06, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:09:38", "remaining_time": "0:43:14"}
+{"current_steps": 35, "total_steps": 192, "loss": null, "eval_loss": 0.8549697995185852, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:09:38", "remaining_time": "0:43:14"}
+{"current_steps": 40, "total_steps": 192, "loss": 0.7989, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.157388080190487e-06, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:11:33", "remaining_time": "0:43:56"}
+{"current_steps": 40, "total_steps": 192, "loss": null, "eval_loss": 0.8472943902015686, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:11:33", "remaining_time": "0:43:56"}
+{"current_steps": 45, "total_steps": 192, "loss": 0.8769, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6192313334626905e-06, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:13:28", "remaining_time": "0:44:01"}
+{"current_steps": 45, "total_steps": 192, "loss": null, "eval_loss": 0.8382811546325684, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:13:28", "remaining_time": "0:44:01"}
+{"current_steps": 50, "total_steps": 192, "loss": 0.7244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.514391432582838e-06, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:15:23", "remaining_time": "0:43:43"}
+{"current_steps": 50, "total_steps": 192, "loss": null, "eval_loss": 0.8277742266654968, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:15:23", "remaining_time": "0:43:43"}
+{"current_steps": 55, "total_steps": 192, "loss": 0.4644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7297262757656213e-06, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:17:17", "remaining_time": "0:43:05"}
+{"current_steps": 55, "total_steps": 192, "loss": null, "eval_loss": 0.8387134671211243, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:17:17", "remaining_time": "0:43:05"}
+{"current_steps": 60, "total_steps": 192, "loss": 0.4488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1791620375982074e-06, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:19:12", "remaining_time": "0:42:16"}
+{"current_steps": 60, "total_steps": 192, "loss": null, "eval_loss": 0.8680305480957031, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:19:12", "remaining_time": "0:42:16"}
+{"current_steps": 65, "total_steps": 192, "loss": 0.3973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.978466092394693e-07, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:21:07", "remaining_time": "0:41:15"}
+{"current_steps": 65, "total_steps": 192, "loss": null, "eval_loss": 0.8717625737190247, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:21:07", "remaining_time": "0:41:15"}
+{"current_steps": 70, "total_steps": 192, "loss": 0.443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.374210410959207e-07, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:22:59", "remaining_time": "0:40:03"}
+{"current_steps": 70, "total_steps": 192, "loss": null, "eval_loss": 0.8596016764640808, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:22:59", "remaining_time": "0:40:03"}
+{"current_steps": 75, "total_steps": 192, "loss": 0.4346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6222476698215175e-07, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:24:51", "remaining_time": "0:38:46"}
+{"current_steps": 75, "total_steps": 192, "loss": null, "eval_loss": 0.8514222502708435, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:24:51", "remaining_time": "0:38:46"}
+{"current_steps": 80, "total_steps": 192, "loss": 0.4701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.462755297384099e-07, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:26:44", "remaining_time": "0:37:25"}
+{"current_steps": 80, "total_steps": 192, "loss": null, "eval_loss": 0.8461114764213562, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:26:44", "remaining_time": "0:37:25"}
+{"current_steps": 85, "total_steps": 192, "loss": 0.4344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7088740175034947e-07, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:28:36", "remaining_time": "0:36:00"}
+{"current_steps": 85, "total_steps": 192, "loss": null, "eval_loss": 0.8437052369117737, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:28:36", "remaining_time": "0:36:00"}
+{"current_steps": 90, "total_steps": 192, "loss": 0.4274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.228102956599465e-07, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:30:27", "remaining_time": "0:34:31"}
+{"current_steps": 90, "total_steps": 192, "loss": null, "eval_loss": 0.8434357643127441, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:30:27", "remaining_time": "0:34:31"}
+{"current_steps": 95, "total_steps": 192, "loss": 0.4771, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.279207916081227e-08, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:32:20", "remaining_time": "0:33:01"}
+{"current_steps": 95, "total_steps": 192, "loss": null, "eval_loss": 0.8434197902679443, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:32:20", "remaining_time": "0:33:01"}
+{"current_steps": 100, "total_steps": 192, "loss": 0.3876, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.448002404850094e-08, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:34:12", "remaining_time": "0:31:28"}
+{"current_steps": 100, "total_steps": 192, "loss": null, "eval_loss": 0.8438728451728821, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:34:12", "remaining_time": "0:31:28"}
+{"current_steps": 105, "total_steps": 192, "loss": 0.3698, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.35920070839697e-08, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:36:01", "remaining_time": "0:29:51"}
+{"current_steps": 105, "total_steps": 192, "loss": null, "eval_loss": 0.845079243183136, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:36:01", "remaining_time": "0:29:51"}
+{"current_steps": 110, "total_steps": 192, "loss": 0.407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.7299804687499997e-08, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:37:49", "remaining_time": "0:28:12"}
+{"current_steps": 110, "total_steps": 192, "loss": null, "eval_loss": 0.8465444445610046, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:37:49", "remaining_time": "0:28:12"}
+{"current_steps": 115, "total_steps": 192, "loss": 0.374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.37771434967624e-08, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:39:40", "remaining_time": "0:26:33"}
+{"current_steps": 115, "total_steps": 192, "loss": null, "eval_loss": 0.8481599688529968, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:39:40", "remaining_time": "0:26:33"}
+{"current_steps": 120, "total_steps": 192, "loss": 0.3945, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.187403540619925e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:41:28", "remaining_time": "0:24:53"}
+{"current_steps": 120, "total_steps": 192, "loss": null, "eval_loss": 0.8498236536979675, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:41:28", "remaining_time": "0:24:53"}
+{"current_steps": 125, "total_steps": 192, "loss": 0.3753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.088648238966908e-08, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:43:19", "remaining_time": "0:23:13"}
+{"current_steps": 125, "total_steps": 192, "loss": null, "eval_loss": 0.8512565493583679, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:43:19", "remaining_time": "0:23:13"}
+{"current_steps": 130, "total_steps": 192, "loss": 0.3721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.039701925276604e-08, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:45:11", "remaining_time": "0:21:32"}
+{"current_steps": 130, "total_steps": 192, "loss": null, "eval_loss": 0.8527700304985046, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:45:11", "remaining_time": "0:21:32"}
+{"current_steps": 135, "total_steps": 192, "loss": 0.3718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0166900048082497e-08, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:47:01", "remaining_time": "0:19:51"}
+{"current_steps": 135, "total_steps": 192, "loss": null, "eval_loss": 0.8541720509529114, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:47:01", "remaining_time": "0:19:51"}
+{"current_steps": 140, "total_steps": 192, "loss": 0.3773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0065147322870076e-08, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:48:51", "remaining_time": "0:18:09"}
+{"current_steps": 140, "total_steps": 192, "loss": null, "eval_loss": 0.8555252552032471, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:48:51", "remaining_time": "0:18:09"}
+{"current_steps": 145, "total_steps": 192, "loss": 0.3723, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.002328628528332e-08, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:50:40", "remaining_time": "0:16:25"}
+{"current_steps": 145, "total_steps": 192, "loss": null, "eval_loss": 0.8565484881401062, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:50:40", "remaining_time": "0:16:25"}
+{"current_steps": 150, "total_steps": 192, "loss": 0.374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0007484528133236e-08, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:52:32", "remaining_time": "0:14:42"}
+{"current_steps": 150, "total_steps": 192, "loss": null, "eval_loss": 0.8576194643974304, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:52:32", "remaining_time": "0:14:42"}
+{"current_steps": 155, "total_steps": 192, "loss": 0.3728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0002110817570477e-08, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:54:21", "remaining_time": "0:12:58"}
+{"current_steps": 155, "total_steps": 192, "loss": null, "eval_loss": 0.8588044047355652, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:54:21", "remaining_time": "0:12:58"}
+{"current_steps": 160, "total_steps": 192, "loss": 0.3686, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000504842356326e-08, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:56:13", "remaining_time": "0:11:14"}
+{"current_steps": 160, "total_steps": 192, "loss": null, "eval_loss": 0.859791100025177, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:56:13", "remaining_time": "0:11:14"}
+{"current_steps": 165, "total_steps": 192, "loss": 0.3617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000009745562451e-08, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:58:03", "remaining_time": "0:09:29"}
+{"current_steps": 165, "total_steps": 192, "loss": null, "eval_loss": 0.8607122302055359, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:58:03", "remaining_time": "0:09:29"}
+{"current_steps": 170, "total_steps": 192, "loss": 0.3546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000014077810156e-08, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:59:52", "remaining_time": "0:07:44"}
+{"current_steps": 170, "total_steps": 192, "loss": null, "eval_loss": 0.8613293170928955, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:59:52", "remaining_time": "0:07:44"}
+{"current_steps": 175, "total_steps": 192, "loss": 0.3707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000001343508807e-08, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "1:01:40", "remaining_time": "0:05:59"}
+{"current_steps": 175, "total_steps": 192, "loss": null, "eval_loss": 0.8619220852851868, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "1:01:40", "remaining_time": "0:05:59"}
+{"current_steps": 180, "total_steps": 192, "loss": 0.3739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000006747581e-08, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "1:03:31", "remaining_time": "0:04:14"}
+{"current_steps": 180, "total_steps": 192, "loss": null, "eval_loss": 0.862490177154541, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "1:03:31", "remaining_time": "0:04:14"}
+{"current_steps": 185, "total_steps": 192, "loss": 0.3617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000001094325e-08, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "1:05:21", "remaining_time": "0:02:28"}
+{"current_steps": 185, "total_steps": 192, "loss": null, "eval_loss": 0.8631939888000488, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "1:05:21", "remaining_time": "0:02:28"}
+{"current_steps": 190, "total_steps": 192, "loss": 0.3591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000000139e-08, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "1:07:12", "remaining_time": "0:00:42"}
+{"current_steps": 190, "total_steps": 192, "loss": null, "eval_loss": 0.8637197613716125, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "1:07:12", "remaining_time": "0:00:42"}
+{"current_steps": 192, "total_steps": 192, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:08:56", "remaining_time": "0:00:00"}
+{"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.8062803149223328, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:09:34", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,607 @@
+{
+  "best_metric": 0.8062803149223328,
+  "best_model_checkpoint": "./output/training_results/C015_llama3-8b-base_instruct_20240504_123713/checkpoint-10",
+  "epoch": 4.0,
+  "eval_steps": 5,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020833333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8766,
+      "step": 1
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": 10.34330229700748,
+      "learning_rate": 2.25e-06,
+      "loss": 0.8675,
+      "step": 5
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "eval_loss": 0.8584801554679871,
+      "eval_runtime": 1.9951,
+      "eval_samples_per_second": 170.414,
+      "eval_steps_per_second": 1.504,
+      "step": 5
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 4.512014612667122,
+      "learning_rate": 5.25e-06,
+      "loss": 0.8415,
+      "step": 10
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "eval_loss": 0.8062803149223328,
+      "eval_runtime": 1.9589,
+      "eval_samples_per_second": 173.564,
+      "eval_steps_per_second": 1.531,
+      "step": 10
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 5.466223920700161,
+      "learning_rate": 8.25e-06,
+      "loss": 0.8225,
+      "step": 15
+    },
+    {
+      "epoch": 0.3125,
+      "eval_loss": 0.820951521396637,
+      "eval_runtime": 1.9583,
+      "eval_samples_per_second": 173.62,
+      "eval_steps_per_second": 1.532,
+      "step": 15
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 5.091985939472258,
+      "learning_rate": 1.2e-05,
+      "loss": 0.806,
+      "step": 20
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "eval_loss": 0.8412486910820007,
+      "eval_runtime": 1.9516,
+      "eval_samples_per_second": 174.217,
+      "eval_steps_per_second": 1.537,
+      "step": 20
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "grad_norm": 4.323182492427286,
+      "learning_rate": 1.4071209905461127e-05,
+      "loss": 0.8139,
+      "step": 25
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "eval_loss": 0.8701534867286682,
+      "eval_runtime": 1.956,
+      "eval_samples_per_second": 173.828,
+      "eval_steps_per_second": 1.534,
+      "step": 25
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 4.430828029367158,
+      "learning_rate": 1.0166196232101288e-05,
+      "loss": 0.8978,
+      "step": 30
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 0.8630704879760742,
+      "eval_runtime": 1.9545,
+      "eval_samples_per_second": 173.954,
+      "eval_steps_per_second": 1.535,
+      "step": 30
+    },
+    {
+      "epoch": 0.7291666666666666,
+      "grad_norm": 3.8459262571296122,
+      "learning_rate": 7.276248845991498e-06,
+      "loss": 0.814,
+      "step": 35
+    },
+    {
+      "epoch": 0.7291666666666666,
+      "eval_loss": 0.8549697995185852,
+      "eval_runtime": 1.9539,
+      "eval_samples_per_second": 174.008,
+      "eval_steps_per_second": 1.535,
+      "step": 35
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 4.312137758874538,
+      "learning_rate": 5.157388080190487e-06,
+      "loss": 0.7989,
+      "step": 40
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "eval_loss": 0.8472943902015686,
+      "eval_runtime": 1.9515,
+      "eval_samples_per_second": 174.222,
+      "eval_steps_per_second": 1.537,
+      "step": 40
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.013634591695819,
+      "learning_rate": 3.6192313334626905e-06,
+      "loss": 0.8769,
+      "step": 45
+    },
+    {
+      "epoch": 0.9375,
+      "eval_loss": 0.8382811546325684,
+      "eval_runtime": 1.9527,
+      "eval_samples_per_second": 174.116,
+      "eval_steps_per_second": 1.536,
+      "step": 45
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 3.825805552811641,
+      "learning_rate": 2.514391432582838e-06,
+      "loss": 0.7244,
+      "step": 50
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "eval_loss": 0.8277742266654968,
+      "eval_runtime": 1.9549,
+      "eval_samples_per_second": 173.925,
+      "eval_steps_per_second": 1.535,
+      "step": 50
+    },
+    {
+      "epoch": 1.1458333333333333,
+      "grad_norm": 3.0670883145044487,
+      "learning_rate": 1.7297262757656213e-06,
+      "loss": 0.4644,
+      "step": 55
+    },
+    {
+      "epoch": 1.1458333333333333,
+      "eval_loss": 0.8387134671211243,
+      "eval_runtime": 1.959,
+      "eval_samples_per_second": 173.561,
+      "eval_steps_per_second": 1.531,
+      "step": 55
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 3.904758197983173,
+      "learning_rate": 1.1791620375982074e-06,
+      "loss": 0.4488,
+      "step": 60
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.8680305480957031,
+      "eval_runtime": 1.953,
+      "eval_samples_per_second": 174.087,
+      "eval_steps_per_second": 1.536,
+      "step": 60
+    },
+    {
+      "epoch": 1.3541666666666667,
+      "grad_norm": 4.037522952699986,
+      "learning_rate": 7.978466092394693e-07,
+      "loss": 0.3973,
+      "step": 65
+    },
+    {
+      "epoch": 1.3541666666666667,
+      "eval_loss": 0.8717625737190247,
+      "eval_runtime": 1.9541,
+      "eval_samples_per_second": 173.996,
+      "eval_steps_per_second": 1.535,
+      "step": 65
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 4.006395162021574,
+      "learning_rate": 5.374210410959207e-07,
+      "loss": 0.443,
+      "step": 70
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "eval_loss": 0.8596016764640808,
+      "eval_runtime": 1.9513,
+      "eval_samples_per_second": 174.244,
+      "eval_steps_per_second": 1.537,
+      "step": 70
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 4.477860740274337,
+      "learning_rate": 3.6222476698215175e-07,
+      "loss": 0.4346,
+      "step": 75
+    },
+    {
+      "epoch": 1.5625,
+      "eval_loss": 0.8514222502708435,
+      "eval_runtime": 1.9616,
+      "eval_samples_per_second": 173.329,
+      "eval_steps_per_second": 1.529,
+      "step": 75
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 3.79003494996975,
+      "learning_rate": 2.462755297384099e-07,
+      "loss": 0.4701,
+      "step": 80
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.8461114764213562,
+      "eval_runtime": 1.9519,
+      "eval_samples_per_second": 174.192,
+      "eval_steps_per_second": 1.537,
+      "step": 80
+    },
+    {
+      "epoch": 1.7708333333333335,
+      "grad_norm": 3.431009868136907,
+      "learning_rate": 1.7088740175034947e-07,
+      "loss": 0.4344,
+      "step": 85
+    },
+    {
+      "epoch": 1.7708333333333335,
+      "eval_loss": 0.8437052369117737,
+      "eval_runtime": 1.9548,
+      "eval_samples_per_second": 173.928,
+      "eval_steps_per_second": 1.535,
+      "step": 85
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 3.4612975522103846,
+      "learning_rate": 1.228102956599465e-07,
+      "loss": 0.4274,
+      "step": 90
+    },
+    {
+      "epoch": 1.875,
+      "eval_loss": 0.8434357643127441,
+      "eval_runtime": 1.9551,
+      "eval_samples_per_second": 173.905,
+      "eval_steps_per_second": 1.534,
+      "step": 90
+    },
+    {
+      "epoch": 1.9791666666666665,
+      "grad_norm": 4.089060356958601,
+      "learning_rate": 9.279207916081227e-08,
+      "loss": 0.4771,
+      "step": 95
+    },
+    {
+      "epoch": 1.9791666666666665,
+      "eval_loss": 0.8434197902679443,
+      "eval_runtime": 1.9533,
+      "eval_samples_per_second": 174.06,
+      "eval_steps_per_second": 1.536,
+      "step": 95
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 3.5663107359521624,
+      "learning_rate": 7.448002404850094e-08,
+      "loss": 0.3876,
+      "step": 100
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "eval_loss": 0.8438728451728821,
+      "eval_runtime": 1.957,
+      "eval_samples_per_second": 173.739,
+      "eval_steps_per_second": 1.533,
+      "step": 100
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 3.3025378175144806,
+      "learning_rate": 6.35920070839697e-08,
+      "loss": 0.3698,
+      "step": 105
+    },
+    {
+      "epoch": 2.1875,
+      "eval_loss": 0.845079243183136,
+      "eval_runtime": 1.9562,
+      "eval_samples_per_second": 173.803,
+      "eval_steps_per_second": 1.534,
+      "step": 105
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 3.4985300165216615,
+      "learning_rate": 5.7299804687499997e-08,
+      "loss": 0.407,
+      "step": 110
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "eval_loss": 0.8465444445610046,
+      "eval_runtime": 1.9573,
+      "eval_samples_per_second": 173.708,
+      "eval_steps_per_second": 1.533,
+      "step": 110
+    },
+    {
+      "epoch": 2.3958333333333335,
+      "grad_norm": 3.394752587183079,
+      "learning_rate": 5.37771434967624e-08,
+      "loss": 0.374,
+      "step": 115
+    },
+    {
+      "epoch": 2.3958333333333335,
+      "eval_loss": 0.8481599688529968,
+      "eval_runtime": 1.9556,
+      "eval_samples_per_second": 173.861,
+      "eval_steps_per_second": 1.534,
+      "step": 115
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.399721414998381,
+      "learning_rate": 5.187403540619925e-08,
+      "loss": 0.3945,
+      "step": 120
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.8498236536979675,
+      "eval_runtime": 1.9552,
+      "eval_samples_per_second": 173.893,
+      "eval_steps_per_second": 1.534,
+      "step": 120
+    },
+    {
+      "epoch": 2.6041666666666665,
+      "grad_norm": 3.2768849901156845,
+      "learning_rate": 5.088648238966908e-08,
+      "loss": 0.3753,
+      "step": 125
+    },
+    {
+      "epoch": 2.6041666666666665,
+      "eval_loss": 0.8512565493583679,
+      "eval_runtime": 1.9594,
+      "eval_samples_per_second": 173.526,
+      "eval_steps_per_second": 1.531,
+      "step": 125
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 3.666595330730063,
+      "learning_rate": 5.039701925276604e-08,
+      "loss": 0.3721,
+      "step": 130
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "eval_loss": 0.8527700304985046,
+      "eval_runtime": 1.9575,
+      "eval_samples_per_second": 173.689,
+      "eval_steps_per_second": 1.533,
+      "step": 130
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 3.4733320032072537,
+      "learning_rate": 5.0166900048082497e-08,
+      "loss": 0.3718,
+      "step": 135
+    },
+    {
+      "epoch": 2.8125,
+      "eval_loss": 0.8541720509529114,
+      "eval_runtime": 1.9599,
+      "eval_samples_per_second": 173.479,
+      "eval_steps_per_second": 1.531,
+      "step": 135
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 3.447696757476531,
+      "learning_rate": 5.0065147322870076e-08,
+      "loss": 0.3773,
+      "step": 140
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "eval_loss": 0.8555252552032471,
+      "eval_runtime": 1.9586,
+      "eval_samples_per_second": 173.592,
+      "eval_steps_per_second": 1.532,
+      "step": 140
+    },
+    {
+      "epoch": 3.0208333333333335,
+      "grad_norm": 3.0052210603196237,
+      "learning_rate": 5.002328628528332e-08,
+      "loss": 0.3723,
+      "step": 145
+    },
+    {
+      "epoch": 3.0208333333333335,
+      "eval_loss": 0.8565484881401062,
+      "eval_runtime": 1.9586,
+      "eval_samples_per_second": 173.589,
+      "eval_steps_per_second": 1.532,
+      "step": 145
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 3.368197941438436,
+      "learning_rate": 5.0007484528133236e-08,
+      "loss": 0.374,
+      "step": 150
+    },
+    {
+      "epoch": 3.125,
+      "eval_loss": 0.8576194643974304,
+      "eval_runtime": 1.9541,
+      "eval_samples_per_second": 173.993,
+      "eval_steps_per_second": 1.535,
+      "step": 150
+    },
+    {
+      "epoch": 3.2291666666666665,
+      "grad_norm": 3.3290743731904304,
+      "learning_rate": 5.0002110817570477e-08,
+      "loss": 0.3728,
+      "step": 155
+    },
+    {
+      "epoch": 3.2291666666666665,
+      "eval_loss": 0.8588044047355652,
+      "eval_runtime": 1.951,
+      "eval_samples_per_second": 174.273,
+      "eval_steps_per_second": 1.538,
+      "step": 155
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.793937739567796,
+      "learning_rate": 5.0000504842356326e-08,
+      "loss": 0.3686,
+      "step": 160
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 0.859791100025177,
+      "eval_runtime": 1.9522,
+      "eval_samples_per_second": 174.159,
+      "eval_steps_per_second": 1.537,
+      "step": 160
+    },
+    {
+      "epoch": 3.4375,
+      "grad_norm": 3.326342529192208,
+      "learning_rate": 5.000009745562451e-08,
+      "loss": 0.3617,
+      "step": 165
+    },
+    {
+      "epoch": 3.4375,
+      "eval_loss": 0.8607122302055359,
+      "eval_runtime": 1.958,
+      "eval_samples_per_second": 173.647,
+      "eval_steps_per_second": 1.532,
+      "step": 165
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "grad_norm": 3.6505713497705736,
+      "learning_rate": 5.0000014077810156e-08,
+      "loss": 0.3546,
+      "step": 170
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "eval_loss": 0.8613293170928955,
+      "eval_runtime": 1.9527,
+      "eval_samples_per_second": 174.122,
+      "eval_steps_per_second": 1.536,
+      "step": 170
+    },
+    {
+      "epoch": 3.6458333333333335,
+      "grad_norm": 3.496080458530573,
+      "learning_rate": 5.0000001343508807e-08,
+      "loss": 0.3707,
+      "step": 175
+    },
+    {
+      "epoch": 3.6458333333333335,
+      "eval_loss": 0.8619220852851868,
+      "eval_runtime": 1.9552,
+      "eval_samples_per_second": 173.893,
+      "eval_steps_per_second": 1.534,
+      "step": 175
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 3.50316414527161,
+      "learning_rate": 5.000000006747581e-08,
+      "loss": 0.3739,
+      "step": 180
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 0.862490177154541,
+      "eval_runtime": 1.9547,
+      "eval_samples_per_second": 173.936,
+      "eval_steps_per_second": 1.535,
+      "step": 180
+    },
+    {
+      "epoch": 3.8541666666666665,
+      "grad_norm": 3.7278057893863874,
+      "learning_rate": 5.0000000001094325e-08,
+      "loss": 0.3617,
+      "step": 185
+    },
+    {
+      "epoch": 3.8541666666666665,
+      "eval_loss": 0.8631939888000488,
+      "eval_runtime": 1.9574,
+      "eval_samples_per_second": 173.703,
+      "eval_steps_per_second": 1.533,
+      "step": 185
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "grad_norm": 3.160928200357982,
+      "learning_rate": 5.000000000000139e-08,
+      "loss": 0.3591,
+      "step": 190
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "eval_loss": 0.8637197613716125,
+      "eval_runtime": 1.9552,
+      "eval_samples_per_second": 173.893,
+      "eval_steps_per_second": 1.534,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "step": 192,
+      "total_flos": 5334785064960.0,
+      "train_loss": 0.508326952966551,
+      "train_runtime": 4164.2152,
+      "train_samples_per_second": 2.934,
+      "train_steps_per_second": 0.046
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 5,
+  "total_flos": 5334785064960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6847c094292a8b40cbd23c921c6bcb9cbc8346d03045e21561f149c7aa6e6569
+size 6776