Add fine-tuned model

README.md

@@ -0,0 +1,78 @@
+---
+license: other
+base_model: rinna/llama-3-youko-8b
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [rinna/llama-3-youko-8b](https://huggingface.co/rinna/llama-3-youko-8b) on the data_bricks, the kunishou, the ichikara-004-multi, the ichikara-004-single, the apto_instruct, the apto_dialogue, the oasst_ja and the megagon datasets.
+It achieves the following results on the evaluation set:
+- Loss: 1.0135
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.9155        | 0.1433 | 100  | 1.8934          |
+| 1.7826        | 0.2865 | 200  | 1.7808          |
+| 1.6897        | 0.4298 | 300  | 1.6719          |
+| 1.5887        | 0.5731 | 400  | 1.5738          |
+| 1.4628        | 0.7163 | 500  | 1.4660          |
+| 1.3751        | 0.8596 | 600  | 1.3671          |
+| 1.1263        | 1.0029 | 700  | 1.2831          |
+| 0.688         | 1.1461 | 800  | 1.2492          |
+| 0.6544        | 1.2894 | 900  | 1.1818          |
+| 0.6017        | 1.4327 | 1000 | 1.1207          |
+| 0.5763        | 1.5759 | 1100 | 1.0708          |
+| 0.5599        | 1.7192 | 1200 | 1.0365          |
+| 0.5101        | 1.8625 | 1300 | 1.0170          |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.013519048690796,
+    "eval_runtime": 53.2963,
+    "eval_samples_per_second": 186.204,
+    "eval_steps_per_second": 1.464,
+    "total_flos": 192624989306880.0,
+    "train_loss": 1.1565231682577926,
+    "train_runtime": 4692.4705,
+    "train_samples_per_second": 38.067,
+    "train_steps_per_second": 0.297
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "rinna/llama-3-youko-8b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.013519048690796,
+    "eval_runtime": 53.2963,
+    "eval_samples_per_second": 186.204,
+    "eval_steps_per_second": 1.464
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf294170684d80266dcc8fb31a809ec009c5c6e8517a7ab6cea5f0ad096fd280
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93f53e6354a8dfce33313c73595b8973e8e235310c11ae4e9909aa4c28ee688
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7943cb63a984df937a3a256809e5168f23c959bfd1b5bbc06a3ad166ac4999b1
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4044c8da6e2e3d9183d2667c014b739a693e2b1eb8350686f9f48de0119eab
+size 1168138808

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|end_of_text|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|end_of_text|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' }}{% 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": 2.0,
+    "total_flos": 192624989306880.0,
+    "train_loss": 1.1565231682577926,
+    "train_runtime": 4692.4705,
+    "train_samples_per_second": 38.067,
+    "train_steps_per_second": 0.297
+}

trainer_log.jsonl

@@ -0,0 +1,153 @@
+{"current_steps": 10, "total_steps": 1396, "loss": 3.6922, "learning_rate": 9.9998935058887e-05, "epoch": 0.014326647564469915, "percentage": 0.72, "elapsed_time": "0:00:37", "remaining_time": "1:26:23"}
+{"current_steps": 20, "total_steps": 1396, "loss": 5.6597, "learning_rate": 9.99820692232566e-05, "epoch": 0.02865329512893983, "percentage": 1.43, "elapsed_time": "0:01:04", "remaining_time": "1:14:14"}
+{"current_steps": 30, "total_steps": 1396, "loss": 2.5057, "learning_rate": 9.993928004395286e-05, "epoch": 0.04297994269340974, "percentage": 2.15, "elapsed_time": "0:01:33", "remaining_time": "1:10:38"}
+{"current_steps": 40, "total_steps": 1396, "loss": 1.984, "learning_rate": 9.987119700662767e-05, "epoch": 0.05730659025787966, "percentage": 2.87, "elapsed_time": "0:02:01", "remaining_time": "1:08:26"}
+{"current_steps": 50, "total_steps": 1396, "loss": 1.9796, "learning_rate": 9.977785459481133e-05, "epoch": 0.07163323782234957, "percentage": 3.58, "elapsed_time": "0:02:28", "remaining_time": "1:06:50"}
+{"current_steps": 60, "total_steps": 1396, "loss": 1.9357, "learning_rate": 9.965930008571152e-05, "epoch": 0.08595988538681948, "percentage": 4.3, "elapsed_time": "0:02:57", "remaining_time": "1:05:41"}
+{"current_steps": 70, "total_steps": 1396, "loss": 1.9499, "learning_rate": 9.951559352626757e-05, "epoch": 0.10028653295128939, "percentage": 5.01, "elapsed_time": "0:03:25", "remaining_time": "1:04:57"}
+{"current_steps": 80, "total_steps": 1396, "loss": 1.9316, "learning_rate": 9.934680770273733e-05, "epoch": 0.11461318051575932, "percentage": 5.73, "elapsed_time": "0:03:54", "remaining_time": "1:04:13"}
+{"current_steps": 90, "total_steps": 1396, "loss": 1.9162, "learning_rate": 9.915302810383132e-05, "epoch": 0.12893982808022922, "percentage": 6.45, "elapsed_time": "0:04:22", "remaining_time": "1:03:28"}
+{"current_steps": 100, "total_steps": 1396, "loss": 1.9155, "learning_rate": 9.893435287741343e-05, "epoch": 0.14326647564469913, "percentage": 7.16, "elapsed_time": "0:04:50", "remaining_time": "1:02:42"}
+{"current_steps": 100, "total_steps": 1396, "eval_loss": 1.8934402465820312, "epoch": 0.14326647564469913, "percentage": 7.16, "elapsed_time": "0:05:44", "remaining_time": "1:14:21"}
+{"current_steps": 110, "total_steps": 1396, "loss": 1.8955, "learning_rate": 9.869089278078987e-05, "epoch": 0.15759312320916904, "percentage": 7.88, "elapsed_time": "0:06:12", "remaining_time": "1:12:30"}
+{"current_steps": 120, "total_steps": 1396, "loss": 1.8796, "learning_rate": 9.842277112461131e-05, "epoch": 0.17191977077363896, "percentage": 8.6, "elapsed_time": "0:06:40", "remaining_time": "1:10:55"}
+{"current_steps": 130, "total_steps": 1396, "loss": 1.8806, "learning_rate": 9.813012371041714e-05, "epoch": 0.18624641833810887, "percentage": 9.31, "elapsed_time": "0:07:07", "remaining_time": "1:09:27"}
+{"current_steps": 140, "total_steps": 1396, "loss": 1.8566, "learning_rate": 9.781309876185291e-05, "epoch": 0.20057306590257878, "percentage": 10.03, "elapsed_time": "0:07:36", "remaining_time": "1:08:11"}
+{"current_steps": 150, "total_steps": 1396, "loss": 1.8784, "learning_rate": 9.747185684959626e-05, "epoch": 0.2148997134670487, "percentage": 10.74, "elapsed_time": "0:08:04", "remaining_time": "1:07:02"}
+{"current_steps": 160, "total_steps": 1396, "loss": 1.8404, "learning_rate": 9.710657081002914e-05, "epoch": 0.22922636103151864, "percentage": 11.46, "elapsed_time": "0:08:32", "remaining_time": "1:05:58"}
+{"current_steps": 170, "total_steps": 1396, "loss": 1.8486, "learning_rate": 9.671742565769749e-05, "epoch": 0.24355300859598855, "percentage": 12.18, "elapsed_time": "0:08:59", "remaining_time": "1:04:51"}
+{"current_steps": 180, "total_steps": 1396, "loss": 1.8228, "learning_rate": 9.630461849160281e-05, "epoch": 0.25787965616045844, "percentage": 12.89, "elapsed_time": "0:09:27", "remaining_time": "1:03:54"}
+{"current_steps": 190, "total_steps": 1396, "loss": 1.8419, "learning_rate": 9.586835839537311e-05, "epoch": 0.2722063037249284, "percentage": 13.61, "elapsed_time": "0:09:54", "remaining_time": "1:02:56"}
+{"current_steps": 200, "total_steps": 1396, "loss": 1.7826, "learning_rate": 9.540886633136352e-05, "epoch": 0.28653295128939826, "percentage": 14.33, "elapsed_time": "0:10:22", "remaining_time": "1:02:03"}
+{"current_steps": 200, "total_steps": 1396, "eval_loss": 1.7807523012161255, "epoch": 0.28653295128939826, "percentage": 14.33, "elapsed_time": "0:11:16", "remaining_time": "1:07:24"}
+{"current_steps": 210, "total_steps": 1396, "loss": 1.7436, "learning_rate": 9.492637502874073e-05, "epoch": 0.3008595988538682, "percentage": 15.04, "elapsed_time": "0:11:43", "remaining_time": "1:06:14"}
+{"current_steps": 220, "total_steps": 1396, "loss": 1.7747, "learning_rate": 9.44211288656074e-05, "epoch": 0.3151862464183381, "percentage": 15.76, "elapsed_time": "0:12:10", "remaining_time": "1:05:06"}
+{"current_steps": 230, "total_steps": 1396, "loss": 1.8156, "learning_rate": 9.389338374522656e-05, "epoch": 0.32951289398280803, "percentage": 16.48, "elapsed_time": "0:12:38", "remaining_time": "1:04:04"}
+{"current_steps": 240, "total_steps": 1396, "loss": 1.767, "learning_rate": 9.334340696640855e-05, "epoch": 0.3438395415472779, "percentage": 17.19, "elapsed_time": "0:13:06", "remaining_time": "1:03:10"}
+{"current_steps": 250, "total_steps": 1396, "loss": 1.7629, "learning_rate": 9.277147708812635e-05, "epoch": 0.35816618911174786, "percentage": 17.91, "elapsed_time": "0:13:34", "remaining_time": "1:02:13"}
+{"current_steps": 260, "total_steps": 1396, "loss": 1.7388, "learning_rate": 9.217788378842749e-05, "epoch": 0.37249283667621774, "percentage": 18.62, "elapsed_time": "0:14:02", "remaining_time": "1:01:21"}
+{"current_steps": 270, "total_steps": 1396, "loss": 1.7428, "learning_rate": 9.156292771771447e-05, "epoch": 0.3868194842406877, "percentage": 19.34, "elapsed_time": "0:14:30", "remaining_time": "1:00:31"}
+{"current_steps": 280, "total_steps": 1396, "loss": 1.7206, "learning_rate": 9.09269203464676e-05, "epoch": 0.40114613180515757, "percentage": 20.06, "elapsed_time": "0:14:57", "remaining_time": "0:59:38"}
+{"current_steps": 290, "total_steps": 1396, "loss": 1.6931, "learning_rate": 9.027018380748766e-05, "epoch": 0.4154727793696275, "percentage": 20.77, "elapsed_time": "0:15:25", "remaining_time": "0:58:50"}
+{"current_steps": 300, "total_steps": 1396, "loss": 1.6897, "learning_rate": 8.959305073273809e-05, "epoch": 0.4297994269340974, "percentage": 21.49, "elapsed_time": "0:15:53", "remaining_time": "0:58:04"}
+{"current_steps": 300, "total_steps": 1396, "eval_loss": 1.6719396114349365, "epoch": 0.4297994269340974, "percentage": 21.49, "elapsed_time": "0:16:47", "remaining_time": "1:01:19"}
+{"current_steps": 310, "total_steps": 1396, "loss": 1.6554, "learning_rate": 8.889586408486953e-05, "epoch": 0.44412607449856734, "percentage": 22.21, "elapsed_time": "0:17:15", "remaining_time": "1:00:26"}
+{"current_steps": 320, "total_steps": 1396, "loss": 1.6655, "learning_rate": 8.817897698351185e-05, "epoch": 0.4584527220630373, "percentage": 22.92, "elapsed_time": "0:17:43", "remaining_time": "0:59:36"}
+{"current_steps": 330, "total_steps": 1396, "loss": 1.638, "learning_rate": 8.744275252642184e-05, "epoch": 0.47277936962750716, "percentage": 23.64, "elapsed_time": "0:18:11", "remaining_time": "0:58:46"}
+{"current_steps": 340, "total_steps": 1396, "loss": 1.6386, "learning_rate": 8.668756360557697e-05, "epoch": 0.4871060171919771, "percentage": 24.36, "elapsed_time": "0:18:39", "remaining_time": "0:57:58"}
+{"current_steps": 350, "total_steps": 1396, "loss": 1.6365, "learning_rate": 8.591379271830855e-05, "epoch": 0.501432664756447, "percentage": 25.07, "elapsed_time": "0:19:07", "remaining_time": "0:57:10"}
+{"current_steps": 360, "total_steps": 1396, "loss": 1.6135, "learning_rate": 8.512183177356973e-05, "epoch": 0.5157593123209169, "percentage": 25.79, "elapsed_time": "0:19:36", "remaining_time": "0:56:25"}
+{"current_steps": 370, "total_steps": 1396, "loss": 1.6001, "learning_rate": 8.43120818934367e-05, "epoch": 0.5300859598853869, "percentage": 26.5, "elapsed_time": "0:20:04", "remaining_time": "0:55:39"}
+{"current_steps": 380, "total_steps": 1396, "loss": 1.6161, "learning_rate": 8.348495320994345e-05, "epoch": 0.5444126074498568, "percentage": 27.22, "elapsed_time": "0:20:31", "remaining_time": "0:54:53"}
+{"current_steps": 390, "total_steps": 1396, "loss": 1.5873, "learning_rate": 8.264086465735312e-05, "epoch": 0.5587392550143266, "percentage": 27.94, "elapsed_time": "0:21:00", "remaining_time": "0:54:10"}
+{"current_steps": 400, "total_steps": 1396, "loss": 1.5887, "learning_rate": 8.178024375997097e-05, "epoch": 0.5730659025787965, "percentage": 28.65, "elapsed_time": "0:21:28", "remaining_time": "0:53:28"}
+{"current_steps": 400, "total_steps": 1396, "eval_loss": 1.5738122463226318, "epoch": 0.5730659025787965, "percentage": 28.65, "elapsed_time": "0:22:22", "remaining_time": "0:55:41"}
+{"current_steps": 410, "total_steps": 1396, "loss": 1.6297, "learning_rate": 8.090352641560668e-05, "epoch": 0.5873925501432665, "percentage": 29.37, "elapsed_time": "0:22:50", "remaining_time": "0:54:54"}
+{"current_steps": 420, "total_steps": 1396, "loss": 1.5987, "learning_rate": 8.001115667479552e-05, "epoch": 0.6017191977077364, "percentage": 30.09, "elapsed_time": "0:23:18", "remaining_time": "0:54:09"}
+{"current_steps": 430, "total_steps": 1396, "loss": 1.5509, "learning_rate": 7.910358651589015e-05, "epoch": 0.6160458452722063, "percentage": 30.8, "elapsed_time": "0:23:45", "remaining_time": "0:53:23"}
+{"current_steps": 440, "total_steps": 1396, "loss": 1.5429, "learning_rate": 7.818127561613707e-05, "epoch": 0.6303724928366762, "percentage": 31.52, "elapsed_time": "0:24:13", "remaining_time": "0:52:38"}
+{"current_steps": 450, "total_steps": 1396, "loss": 1.5396, "learning_rate": 7.724469111885371e-05, "epoch": 0.6446991404011462, "percentage": 32.23, "elapsed_time": "0:24:41", "remaining_time": "0:51:54"}
+{"current_steps": 460, "total_steps": 1396, "loss": 1.5266, "learning_rate": 7.629430739682398e-05, "epoch": 0.6590257879656161, "percentage": 32.95, "elapsed_time": "0:25:09", "remaining_time": "0:51:10"}
+{"current_steps": 470, "total_steps": 1396, "loss": 1.5824, "learning_rate": 7.533060581203201e-05, "epoch": 0.673352435530086, "percentage": 33.67, "elapsed_time": "0:25:37", "remaining_time": "0:50:29"}
+{"current_steps": 480, "total_steps": 1396, "loss": 1.4828, "learning_rate": 7.435407447185623e-05, "epoch": 0.6876790830945558, "percentage": 34.38, "elapsed_time": "0:26:05", "remaining_time": "0:49:47"}
+{"current_steps": 490, "total_steps": 1396, "loss": 1.4991, "learning_rate": 7.336520798184664e-05, "epoch": 0.7020057306590258, "percentage": 35.1, "elapsed_time": "0:26:32", "remaining_time": "0:49:04"}
+{"current_steps": 500, "total_steps": 1396, "loss": 1.4628, "learning_rate": 7.236450719521092e-05, "epoch": 0.7163323782234957, "percentage": 35.82, "elapsed_time": "0:26:59", "remaining_time": "0:48:22"}
+{"current_steps": 500, "total_steps": 1396, "eval_loss": 1.4659688472747803, "epoch": 0.7163323782234957, "percentage": 35.82, "elapsed_time": "0:27:53", "remaining_time": "0:49:59"}
+{"current_steps": 510, "total_steps": 1396, "loss": 1.485, "learning_rate": 7.135247895913623e-05, "epoch": 0.7306590257879656, "percentage": 36.53, "elapsed_time": "0:29:06", "remaining_time": "0:50:34"}
+{"current_steps": 520, "total_steps": 1396, "loss": 1.454, "learning_rate": 7.032963585807501e-05, "epoch": 0.7449856733524355, "percentage": 37.25, "elapsed_time": "0:29:34", "remaining_time": "0:49:49"}
+{"current_steps": 530, "total_steps": 1396, "loss": 1.4675, "learning_rate": 6.929649595412497e-05, "epoch": 0.7593123209169055, "percentage": 37.97, "elapsed_time": "0:30:02", "remaining_time": "0:49:05"}
+{"current_steps": 540, "total_steps": 1396, "loss": 1.4232, "learning_rate": 6.825358252463461e-05, "epoch": 0.7736389684813754, "percentage": 38.68, "elapsed_time": "0:30:30", "remaining_time": "0:48:22"}
+{"current_steps": 550, "total_steps": 1396, "loss": 1.4084, "learning_rate": 6.720142379716728e-05, "epoch": 0.7879656160458453, "percentage": 39.4, "elapsed_time": "0:30:58", "remaining_time": "0:47:38"}
+{"current_steps": 560, "total_steps": 1396, "loss": 1.4034, "learning_rate": 6.614055268195805e-05, "epoch": 0.8022922636103151, "percentage": 40.11, "elapsed_time": "0:31:26", "remaining_time": "0:46:56"}
+{"current_steps": 570, "total_steps": 1396, "loss": 1.439, "learning_rate": 6.507150650199886e-05, "epoch": 0.8166189111747851, "percentage": 40.83, "elapsed_time": "0:31:54", "remaining_time": "0:46:14"}
+{"current_steps": 580, "total_steps": 1396, "loss": 1.3767, "learning_rate": 6.399482672088852e-05, "epoch": 0.830945558739255, "percentage": 41.55, "elapsed_time": "0:32:22", "remaining_time": "0:45:33"}
+{"current_steps": 590, "total_steps": 1396, "loss": 1.4084, "learning_rate": 6.291105866858562e-05, "epoch": 0.8452722063037249, "percentage": 42.26, "elapsed_time": "0:32:51", "remaining_time": "0:44:52"}
+{"current_steps": 600, "total_steps": 1396, "loss": 1.3751, "learning_rate": 6.18207512652031e-05, "epoch": 0.8595988538681948, "percentage": 42.98, "elapsed_time": "0:33:19", "remaining_time": "0:44:12"}
+{"current_steps": 600, "total_steps": 1396, "eval_loss": 1.3670978546142578, "epoch": 0.8595988538681948, "percentage": 42.98, "elapsed_time": "0:34:12", "remaining_time": "0:45:23"}
+{"current_steps": 610, "total_steps": 1396, "loss": 1.3799, "learning_rate": 6.0724456742984535e-05, "epoch": 0.8739255014326648, "percentage": 43.7, "elapsed_time": "0:34:41", "remaining_time": "0:44:41"}
+{"current_steps": 620, "total_steps": 1396, "loss": 1.372, "learning_rate": 5.962273036660276e-05, "epoch": 0.8882521489971347, "percentage": 44.41, "elapsed_time": "0:35:08", "remaining_time": "0:43:59"}
+{"current_steps": 630, "total_steps": 1396, "loss": 1.3514, "learning_rate": 5.851613015192261e-05, "epoch": 0.9025787965616046, "percentage": 45.13, "elapsed_time": "0:35:36", "remaining_time": "0:43:18"}
+{"current_steps": 640, "total_steps": 1396, "loss": 1.3283, "learning_rate": 5.74052165833702e-05, "epoch": 0.9169054441260746, "percentage": 45.85, "elapsed_time": "0:36:04", "remaining_time": "0:42:37"}
+{"current_steps": 650, "total_steps": 1396, "loss": 1.3257, "learning_rate": 5.6290552330051946e-05, "epoch": 0.9312320916905444, "percentage": 46.56, "elapsed_time": "0:36:32", "remaining_time": "0:41:56"}
+{"current_steps": 660, "total_steps": 1396, "loss": 1.3279, "learning_rate": 5.5172701960767006e-05, "epoch": 0.9455587392550143, "percentage": 47.28, "elapsed_time": "0:37:00", "remaining_time": "0:41:16"}
+{"current_steps": 670, "total_steps": 1396, "loss": 1.2695, "learning_rate": 5.405223165805755e-05, "epoch": 0.9598853868194842, "percentage": 47.99, "elapsed_time": "0:37:28", "remaining_time": "0:40:36"}
+{"current_steps": 680, "total_steps": 1396, "loss": 1.2958, "learning_rate": 5.292970893144172e-05, "epoch": 0.9742120343839542, "percentage": 48.71, "elapsed_time": "0:37:56", "remaining_time": "0:39:56"}
+{"current_steps": 690, "total_steps": 1396, "loss": 1.2763, "learning_rate": 5.180570232997446e-05, "epoch": 0.9885386819484241, "percentage": 49.43, "elapsed_time": "0:38:24", "remaining_time": "0:39:17"}
+{"current_steps": 700, "total_steps": 1396, "loss": 1.1263, "learning_rate": 5.06807811542818e-05, "epoch": 1.002865329512894, "percentage": 50.14, "elapsed_time": "0:38:52", "remaining_time": "0:38:39"}
+{"current_steps": 700, "total_steps": 1396, "eval_loss": 1.2830663919448853, "epoch": 1.002865329512894, "percentage": 50.14, "elapsed_time": "0:39:45", "remaining_time": "0:39:32"}
+{"current_steps": 710, "total_steps": 1396, "loss": 0.7167, "learning_rate": 4.9555515168214514e-05, "epoch": 1.0171919770773639, "percentage": 50.86, "elapsed_time": "0:40:13", "remaining_time": "0:38:51"}
+{"current_steps": 720, "total_steps": 1396, "loss": 0.6893, "learning_rate": 4.8430474310267185e-05, "epoch": 1.0315186246418337, "percentage": 51.58, "elapsed_time": "0:40:40", "remaining_time": "0:38:11"}
+{"current_steps": 730, "total_steps": 1396, "loss": 0.6935, "learning_rate": 4.7306228404908706e-05, "epoch": 1.0458452722063036, "percentage": 52.29, "elapsed_time": "0:41:08", "remaining_time": "0:37:31"}
+{"current_steps": 740, "total_steps": 1396, "loss": 0.7053, "learning_rate": 4.6183346873970704e-05, "epoch": 1.0601719197707737, "percentage": 53.01, "elapsed_time": "0:41:36", "remaining_time": "0:36:52"}
+{"current_steps": 750, "total_steps": 1396, "loss": 0.6848, "learning_rate": 4.506239844823972e-05, "epoch": 1.0744985673352436, "percentage": 53.72, "elapsed_time": "0:42:03", "remaining_time": "0:36:13"}
+{"current_steps": 760, "total_steps": 1396, "loss": 0.6677, "learning_rate": 4.394395087939947e-05, "epoch": 1.0888252148997135, "percentage": 54.44, "elapsed_time": "0:42:31", "remaining_time": "0:35:35"}
+{"current_steps": 770, "total_steps": 1396, "loss": 0.6844, "learning_rate": 4.282857065246908e-05, "epoch": 1.1031518624641834, "percentage": 55.16, "elapsed_time": "0:42:58", "remaining_time": "0:34:56"}
+{"current_steps": 780, "total_steps": 1396, "loss": 0.6735, "learning_rate": 4.1716822698882826e-05, "epoch": 1.1174785100286533, "percentage": 55.87, "elapsed_time": "0:43:26", "remaining_time": "0:34:18"}
+{"current_steps": 790, "total_steps": 1396, "loss": 0.6405, "learning_rate": 4.0609270110356625e-05, "epoch": 1.1318051575931232, "percentage": 56.59, "elapsed_time": "0:43:55", "remaining_time": "0:33:41"}
+{"current_steps": 800, "total_steps": 1396, "loss": 0.688, "learning_rate": 3.9506473853686586e-05, "epoch": 1.146131805157593, "percentage": 57.31, "elapsed_time": "0:44:23", "remaining_time": "0:33:04"}
+{"current_steps": 800, "total_steps": 1396, "eval_loss": 1.2491989135742188, "epoch": 1.146131805157593, "percentage": 57.31, "elapsed_time": "0:45:16", "remaining_time": "0:33:44"}
+{"current_steps": 810, "total_steps": 1396, "loss": 0.662, "learning_rate": 3.8408992486623595e-05, "epoch": 1.1604584527220632, "percentage": 58.02, "elapsed_time": "0:45:44", "remaining_time": "0:33:05"}
+{"current_steps": 820, "total_steps": 1396, "loss": 0.6901, "learning_rate": 3.7317381874968207e-05, "epoch": 1.174785100286533, "percentage": 58.74, "elapsed_time": "0:46:13", "remaining_time": "0:32:27"}
+{"current_steps": 830, "total_steps": 1396, "loss": 0.6705, "learning_rate": 3.6232194911028874e-05, "epoch": 1.189111747851003, "percentage": 59.46, "elapsed_time": "0:46:41", "remaining_time": "0:31:50"}
+{"current_steps": 840, "total_steps": 1396, "loss": 0.6764, "learning_rate": 3.515398123358627e-05, "epoch": 1.2034383954154728, "percentage": 60.17, "elapsed_time": "0:47:09", "remaining_time": "0:31:12"}
+{"current_steps": 850, "total_steps": 1396, "loss": 0.6761, "learning_rate": 3.40832869495056e-05, "epoch": 1.2177650429799427, "percentage": 60.89, "elapsed_time": "0:47:37", "remaining_time": "0:30:35"}
+{"current_steps": 860, "total_steps": 1396, "loss": 0.6275, "learning_rate": 3.302065435713763e-05, "epoch": 1.2320916905444126, "percentage": 61.6, "elapsed_time": "0:48:05", "remaining_time": "0:29:58"}
+{"current_steps": 870, "total_steps": 1396, "loss": 0.6342, "learning_rate": 3.196662167164877e-05, "epoch": 1.2464183381088825, "percentage": 62.32, "elapsed_time": "0:48:33", "remaining_time": "0:29:21"}
+{"current_steps": 880, "total_steps": 1396, "loss": 0.6357, "learning_rate": 3.092172275241933e-05, "epoch": 1.2607449856733524, "percentage": 63.04, "elapsed_time": "0:49:00", "remaining_time": "0:28:44"}
+{"current_steps": 890, "total_steps": 1396, "loss": 0.6189, "learning_rate": 2.9886486832647835e-05, "epoch": 1.2750716332378222, "percentage": 63.75, "elapsed_time": "0:49:28", "remaining_time": "0:28:07"}
+{"current_steps": 900, "total_steps": 1396, "loss": 0.6544, "learning_rate": 2.8861438251298512e-05, "epoch": 1.2893982808022924, "percentage": 64.47, "elapsed_time": "0:49:56", "remaining_time": "0:27:31"}
+{"current_steps": 900, "total_steps": 1396, "eval_loss": 1.1817691326141357, "epoch": 1.2893982808022924, "percentage": 64.47, "elapsed_time": "0:50:49", "remaining_time": "0:28:00"}
+{"current_steps": 910, "total_steps": 1396, "loss": 0.6359, "learning_rate": 2.784709618752776e-05, "epoch": 1.3037249283667622, "percentage": 65.19, "elapsed_time": "0:51:17", "remaining_time": "0:27:23"}
+{"current_steps": 920, "total_steps": 1396, "loss": 0.621, "learning_rate": 2.6843974397723753e-05, "epoch": 1.3180515759312321, "percentage": 65.9, "elapsed_time": "0:51:46", "remaining_time": "0:26:47"}
+{"current_steps": 930, "total_steps": 1396, "loss": 0.6265, "learning_rate": 2.5852580955293003e-05, "epoch": 1.332378223495702, "percentage": 66.62, "elapsed_time": "0:52:14", "remaining_time": "0:26:10"}
+{"current_steps": 940, "total_steps": 1396, "loss": 0.6441, "learning_rate": 2.4873417993325042e-05, "epoch": 1.346704871060172, "percentage": 67.34, "elapsed_time": "0:52:42", "remaining_time": "0:25:34"}
+{"current_steps": 950, "total_steps": 1396, "loss": 0.6173, "learning_rate": 2.3906981450265836e-05, "epoch": 1.3610315186246418, "percentage": 68.05, "elapsed_time": "0:53:09", "remaining_time": "0:24:57"}
+{"current_steps": 960, "total_steps": 1396, "loss": 0.6193, "learning_rate": 2.295376081872895e-05, "epoch": 1.3753581661891117, "percentage": 68.77, "elapsed_time": "0:53:37", "remaining_time": "0:24:21"}
+{"current_steps": 970, "total_steps": 1396, "loss": 0.6466, "learning_rate": 2.201423889757122e-05, "epoch": 1.3896848137535818, "percentage": 69.48, "elapsed_time": "0:54:05", "remaining_time": "0:23:45"}
+{"current_steps": 980, "total_steps": 1396, "loss": 0.6124, "learning_rate": 2.108889154735895e-05, "epoch": 1.4040114613180517, "percentage": 70.2, "elapsed_time": "0:54:33", "remaining_time": "0:23:09"}
+{"current_steps": 990, "total_steps": 1396, "loss": 0.6183, "learning_rate": 2.0178187449348208e-05, "epoch": 1.4183381088825215, "percentage": 70.92, "elapsed_time": "0:55:01", "remaining_time": "0:22:34"}
+{"current_steps": 1000, "total_steps": 1396, "loss": 0.6017, "learning_rate": 1.9282587868101308e-05, "epoch": 1.4326647564469914, "percentage": 71.63, "elapsed_time": "0:55:29", "remaining_time": "0:21:58"}
+{"current_steps": 1000, "total_steps": 1396, "eval_loss": 1.120739459991455, "epoch": 1.4326647564469914, "percentage": 71.63, "elapsed_time": "0:56:22", "remaining_time": "0:22:19"}
+{"current_steps": 1010, "total_steps": 1396, "loss": 0.5614, "learning_rate": 1.840254641786006e-05, "epoch": 1.4469914040114613, "percentage": 72.35, "elapsed_time": "0:57:34", "remaining_time": "0:22:00"}
+{"current_steps": 1020, "total_steps": 1396, "loss": 0.5797, "learning_rate": 1.7538508832793578e-05, "epoch": 1.4613180515759312, "percentage": 73.07, "elapsed_time": "0:58:02", "remaining_time": "0:21:23"}
+{"current_steps": 1030, "total_steps": 1396, "loss": 0.6184, "learning_rate": 1.669091274123732e-05, "epoch": 1.475644699140401, "percentage": 73.78, "elapsed_time": "0:58:30", "remaining_time": "0:20:47"}
+{"current_steps": 1040, "total_steps": 1396, "loss": 0.5813, "learning_rate": 1.586018744403787e-05, "epoch": 1.4899713467048712, "percentage": 74.5, "elapsed_time": "0:58:57", "remaining_time": "0:20:11"}
+{"current_steps": 1050, "total_steps": 1396, "loss": 0.5667, "learning_rate": 1.504675369711529e-05, "epoch": 1.5042979942693409, "percentage": 75.21, "elapsed_time": "0:59:26", "remaining_time": "0:19:35"}
+{"current_steps": 1060, "total_steps": 1396, "loss": 0.582, "learning_rate": 1.4251023498353533e-05, "epoch": 1.518624641833811, "percentage": 75.93, "elapsed_time": "0:59:54", "remaining_time": "0:18:59"}
+{"current_steps": 1070, "total_steps": 1396, "loss": 0.563, "learning_rate": 1.3473399878926746e-05, "epoch": 1.5329512893982808, "percentage": 76.65, "elapsed_time": "1:00:22", "remaining_time": "0:18:23"}
+{"current_steps": 1080, "total_steps": 1396, "loss": 0.5466, "learning_rate": 1.2714276699166994e-05, "epoch": 1.5472779369627507, "percentage": 77.36, "elapsed_time": "1:00:50", "remaining_time": "0:17:48"}
+{"current_steps": 1090, "total_steps": 1396, "loss": 0.5239, "learning_rate": 1.1974038449077258e-05, "epoch": 1.5616045845272206, "percentage": 78.08, "elapsed_time": "1:01:17", "remaining_time": "0:17:12"}
+{"current_steps": 1100, "total_steps": 1396, "loss": 0.5763, "learning_rate": 1.1253060053589997e-05, "epoch": 1.5759312320916905, "percentage": 78.8, "elapsed_time": "1:01:44", "remaining_time": "0:16:36"}
+{"current_steps": 1100, "total_steps": 1396, "eval_loss": 1.0708156824111938, "epoch": 1.5759312320916905, "percentage": 78.8, "elapsed_time": "1:02:38", "remaining_time": "0:16:51"}
+{"current_steps": 1110, "total_steps": 1396, "loss": 0.5511, "learning_rate": 1.0551706682670748e-05, "epoch": 1.5902578796561606, "percentage": 79.51, "elapsed_time": "1:03:05", "remaining_time": "0:16:15"}
+{"current_steps": 1120, "total_steps": 1396, "loss": 0.5645, "learning_rate": 9.870333566362322e-06, "epoch": 1.6045845272206303, "percentage": 80.23, "elapsed_time": "1:03:33", "remaining_time": "0:15:39"}
+{"current_steps": 1130, "total_steps": 1396, "loss": 0.5301, "learning_rate": 9.209285814863477e-06, "epoch": 1.6189111747851004, "percentage": 80.95, "elapsed_time": "1:04:01", "remaining_time": "0:15:04"}
+{"current_steps": 1140, "total_steps": 1396, "loss": 0.5371, "learning_rate": 8.568898243733386e-06, "epoch": 1.63323782234957, "percentage": 81.66, "elapsed_time": "1:04:29", "remaining_time": "0:14:28"}
+{"current_steps": 1150, "total_steps": 1396, "loss": 0.5555, "learning_rate": 7.949495204310104e-06, "epoch": 1.6475644699140402, "percentage": 82.38, "elapsed_time": "1:04:57", "remaining_time": "0:13:53"}
+{"current_steps": 1160, "total_steps": 1396, "loss": 0.5616, "learning_rate": 7.351390419429083e-06, "epoch": 1.66189111747851, "percentage": 83.09, "elapsed_time": "1:05:26", "remaining_time": "0:13:18"}
+{"current_steps": 1170, "total_steps": 1396, "loss": 0.539, "learning_rate": 6.774886824525073e-06, "epoch": 1.67621776504298, "percentage": 83.81, "elapsed_time": "1:05:53", "remaining_time": "0:12:43"}
+{"current_steps": 1180, "total_steps": 1396, "loss": 0.5366, "learning_rate": 6.2202764141976346e-06, "epoch": 1.6905444126074498, "percentage": 84.53, "elapsed_time": "1:06:21", "remaining_time": "0:12:08"}
+{"current_steps": 1190, "total_steps": 1396, "loss": 0.5072, "learning_rate": 5.687840094318125e-06, "epoch": 1.7048710601719197, "percentage": 85.24, "elapsed_time": "1:06:48", "remaining_time": "0:11:33"}
+{"current_steps": 1200, "total_steps": 1396, "loss": 0.5599, "learning_rate": 5.177847539753084e-06, "epoch": 1.7191977077363898, "percentage": 85.96, "elapsed_time": "1:07:16", "remaining_time": "0:10:59"}
+{"current_steps": 1200, "total_steps": 1396, "eval_loss": 1.036474347114563, "epoch": 1.7191977077363898, "percentage": 85.96, "elapsed_time": "1:08:10", "remaining_time": "0:11:08"}
+{"current_steps": 1210, "total_steps": 1396, "loss": 0.5367, "learning_rate": 4.690557057775974e-06, "epoch": 1.7335243553008595, "percentage": 86.68, "elapsed_time": "1:08:38", "remaining_time": "0:10:33"}
+{"current_steps": 1220, "total_steps": 1396, "loss": 0.5388, "learning_rate": 4.226215457236565e-06, "epoch": 1.7478510028653296, "percentage": 87.39, "elapsed_time": "1:09:06", "remaining_time": "0:09:58"}
+{"current_steps": 1230, "total_steps": 1396, "loss": 0.5238, "learning_rate": 3.785057923554197e-06, "epoch": 1.7621776504297995, "percentage": 88.11, "elapsed_time": "1:09:33", "remaining_time": "0:09:23"}
+{"current_steps": 1240, "total_steps": 1396, "loss": 0.4981, "learning_rate": 3.36730789959811e-06, "epoch": 1.7765042979942693, "percentage": 88.83, "elapsed_time": "1:10:01", "remaining_time": "0:08:48"}
+{"current_steps": 1250, "total_steps": 1396, "loss": 0.5294, "learning_rate": 2.9731769725154514e-06, "epoch": 1.7908309455587392, "percentage": 89.54, "elapsed_time": "1:10:29", "remaining_time": "0:08:13"}
+{"current_steps": 1260, "total_steps": 1396, "loss": 0.5275, "learning_rate": 2.6028647665639672e-06, "epoch": 1.8051575931232091, "percentage": 90.26, "elapsed_time": "1:10:57", "remaining_time": "0:07:39"}
+{"current_steps": 1270, "total_steps": 1396, "loss": 0.5253, "learning_rate": 2.256558842003892e-06, "epoch": 1.8194842406876792, "percentage": 90.97, "elapsed_time": "1:11:24", "remaining_time": "0:07:05"}
+{"current_steps": 1280, "total_steps": 1396, "loss": 0.5442, "learning_rate": 1.9344346001001377e-06, "epoch": 1.8338108882521489, "percentage": 91.69, "elapsed_time": "1:11:52", "remaining_time": "0:06:30"}
+{"current_steps": 1290, "total_steps": 1396, "loss": 0.5483, "learning_rate": 1.6366551942828711e-06, "epoch": 1.848137535816619, "percentage": 92.41, "elapsed_time": "1:12:19", "remaining_time": "0:05:56"}
+{"current_steps": 1300, "total_steps": 1396, "loss": 0.5101, "learning_rate": 1.363371447511619e-06, "epoch": 1.8624641833810889, "percentage": 93.12, "elapsed_time": "1:12:46", "remaining_time": "0:05:22"}
+{"current_steps": 1300, "total_steps": 1396, "eval_loss": 1.0169659852981567, "epoch": 1.8624641833810889, "percentage": 93.12, "elapsed_time": "1:13:39", "remaining_time": "0:05:26"}
+{"current_steps": 1310, "total_steps": 1396, "loss": 0.5469, "learning_rate": 1.1147217758845751e-06, "epoch": 1.8767908309455588, "percentage": 93.84, "elapsed_time": "1:14:07", "remaining_time": "0:04:52"}
+{"current_steps": 1320, "total_steps": 1396, "loss": 0.5319, "learning_rate": 8.908321185319312e-07, "epoch": 1.8911174785100286, "percentage": 94.56, "elapsed_time": "1:14:35", "remaining_time": "0:04:17"}
+{"current_steps": 1330, "total_steps": 1396, "loss": 0.5126, "learning_rate": 6.918158738286884e-07, "epoch": 1.9054441260744985, "percentage": 95.27, "elapsed_time": "1:15:04", "remaining_time": "0:03:43"}
+{"current_steps": 1340, "total_steps": 1396, "loss": 0.5276, "learning_rate": 5.177738419592515e-07, "epoch": 1.9197707736389686, "percentage": 95.99, "elapsed_time": "1:15:32", "remaining_time": "0:03:09"}
+{"current_steps": 1350, "total_steps": 1396, "loss": 0.53, "learning_rate": 3.687941738629186e-07, "epoch": 1.9340974212034383, "percentage": 96.7, "elapsed_time": "1:16:00", "remaining_time": "0:02:35"}
+{"current_steps": 1360, "total_steps": 1396, "loss": 0.4903, "learning_rate": 2.449523265861176e-07, "epoch": 1.9484240687679084, "percentage": 97.42, "elapsed_time": "1:16:28", "remaining_time": "0:02:01"}
+{"current_steps": 1370, "total_steps": 1396, "loss": 0.5025, "learning_rate": 1.4631102506399985e-07, "epoch": 1.962750716332378, "percentage": 98.14, "elapsed_time": "1:16:56", "remaining_time": "0:01:27"}
+{"current_steps": 1380, "total_steps": 1396, "loss": 0.5428, "learning_rate": 7.292023035074813e-08, "epoch": 1.9770773638968482, "percentage": 98.85, "elapsed_time": "1:17:24", "remaining_time": "0:00:53"}
+{"current_steps": 1390, "total_steps": 1396, "loss": 0.52, "learning_rate": 2.4817114314662493e-08, "epoch": 1.991404011461318, "percentage": 99.57, "elapsed_time": "1:17:52", "remaining_time": "0:00:20"}
+{"current_steps": 1396, "total_steps": 1396, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:18:09", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 100,
+  "global_step": 1396,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014326647564469915,
+      "grad_norm": 219.6043368919095,
+      "learning_rate": 9.9998935058887e-05,
+      "loss": 3.6922,
+      "step": 10
+    },
+    {
+      "epoch": 0.02865329512893983,
+      "grad_norm": 164.46657899747223,
+      "learning_rate": 9.99820692232566e-05,
+      "loss": 5.6597,
+      "step": 20
+    },
+    {
+      "epoch": 0.04297994269340974,
+      "grad_norm": 6.412857819851782,
+      "learning_rate": 9.993928004395286e-05,
+      "loss": 2.5057,
+      "step": 30
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "grad_norm": 69.62252521072725,
+      "learning_rate": 9.987119700662767e-05,
+      "loss": 1.984,
+      "step": 40
+    },
+    {
+      "epoch": 0.07163323782234957,
+      "grad_norm": 2.911386364058055,
+      "learning_rate": 9.977785459481133e-05,
+      "loss": 1.9796,
+      "step": 50
+    },
+    {
+      "epoch": 0.08595988538681948,
+      "grad_norm": 2.928138422380621,
+      "learning_rate": 9.965930008571152e-05,
+      "loss": 1.9357,
+      "step": 60
+    },
+    {
+      "epoch": 0.10028653295128939,
+      "grad_norm": 2.718649753716308,
+      "learning_rate": 9.951559352626757e-05,
+      "loss": 1.9499,
+      "step": 70
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 3.2224244565131954,
+      "learning_rate": 9.934680770273733e-05,
+      "loss": 1.9316,
+      "step": 80
+    },
+    {
+      "epoch": 0.12893982808022922,
+      "grad_norm": 2.35688226018453,
+      "learning_rate": 9.915302810383132e-05,
+      "loss": 1.9162,
+      "step": 90
+    },
+    {
+      "epoch": 0.14326647564469913,
+      "grad_norm": 2.332818455987922,
+      "learning_rate": 9.893435287741343e-05,
+      "loss": 1.9155,
+      "step": 100
+    },
+    {
+      "epoch": 0.14326647564469913,
+      "eval_loss": 1.8934402465820312,
+      "eval_runtime": 53.9021,
+      "eval_samples_per_second": 184.112,
+      "eval_steps_per_second": 1.447,
+      "step": 100
+    },
+    {
+      "epoch": 0.15759312320916904,
+      "grad_norm": 2.188522515670293,
+      "learning_rate": 9.869089278078987e-05,
+      "loss": 1.8955,
+      "step": 110
+    },
+    {
+      "epoch": 0.17191977077363896,
+      "grad_norm": 2.0681470915932927,
+      "learning_rate": 9.842277112461131e-05,
+      "loss": 1.8796,
+      "step": 120
+    },
+    {
+      "epoch": 0.18624641833810887,
+      "grad_norm": 2.0222340151069544,
+      "learning_rate": 9.813012371041714e-05,
+      "loss": 1.8806,
+      "step": 130
+    },
+    {
+      "epoch": 0.20057306590257878,
+      "grad_norm": 2.192495513300194,
+      "learning_rate": 9.781309876185291e-05,
+      "loss": 1.8566,
+      "step": 140
+    },
+    {
+      "epoch": 0.2148997134670487,
+      "grad_norm": 2.17884511538925,
+      "learning_rate": 9.747185684959626e-05,
+      "loss": 1.8784,
+      "step": 150
+    },
+    {
+      "epoch": 0.22922636103151864,
+      "grad_norm": 2.2802921311633972,
+      "learning_rate": 9.710657081002914e-05,
+      "loss": 1.8404,
+      "step": 160
+    },
+    {
+      "epoch": 0.24355300859598855,
+      "grad_norm": 2.12926899758067,
+      "learning_rate": 9.671742565769749e-05,
+      "loss": 1.8486,
+      "step": 170
+    },
+    {
+      "epoch": 0.25787965616045844,
+      "grad_norm": 1.9971883700915698,
+      "learning_rate": 9.630461849160281e-05,
+      "loss": 1.8228,
+      "step": 180
+    },
+    {
+      "epoch": 0.2722063037249284,
+      "grad_norm": 2.3808879139034613,
+      "learning_rate": 9.586835839537311e-05,
+      "loss": 1.8419,
+      "step": 190
+    },
+    {
+      "epoch": 0.28653295128939826,
+      "grad_norm": 2.1250632793004702,
+      "learning_rate": 9.540886633136352e-05,
+      "loss": 1.7826,
+      "step": 200
+    },
+    {
+      "epoch": 0.28653295128939826,
+      "eval_loss": 1.7807523012161255,
+      "eval_runtime": 53.6847,
+      "eval_samples_per_second": 184.857,
+      "eval_steps_per_second": 1.453,
+      "step": 200
+    },
+    {
+      "epoch": 0.3008595988538682,
+      "grad_norm": 2.074489802943034,
+      "learning_rate": 9.492637502874073e-05,
+      "loss": 1.7436,
+      "step": 210
+    },
+    {
+      "epoch": 0.3151862464183381,
+      "grad_norm": 1.8033562678630226,
+      "learning_rate": 9.44211288656074e-05,
+      "loss": 1.7747,
+      "step": 220
+    },
+    {
+      "epoch": 0.32951289398280803,
+      "grad_norm": 1.7937171543469097,
+      "learning_rate": 9.389338374522656e-05,
+      "loss": 1.8156,
+      "step": 230
+    },
+    {
+      "epoch": 0.3438395415472779,
+      "grad_norm": 1.7554977702779284,
+      "learning_rate": 9.334340696640855e-05,
+      "loss": 1.767,
+      "step": 240
+    },
+    {
+      "epoch": 0.35816618911174786,
+      "grad_norm": 2.2371815357457208,
+      "learning_rate": 9.277147708812635e-05,
+      "loss": 1.7629,
+      "step": 250
+    },
+    {
+      "epoch": 0.37249283667621774,
+      "grad_norm": 2.0086148480908297,
+      "learning_rate": 9.217788378842749e-05,
+      "loss": 1.7388,
+      "step": 260
+    },
+    {
+      "epoch": 0.3868194842406877,
+      "grad_norm": 1.6807840994252192,
+      "learning_rate": 9.156292771771447e-05,
+      "loss": 1.7428,
+      "step": 270
+    },
+    {
+      "epoch": 0.40114613180515757,
+      "grad_norm": 1.7341861848893365,
+      "learning_rate": 9.09269203464676e-05,
+      "loss": 1.7206,
+      "step": 280
+    },
+    {
+      "epoch": 0.4154727793696275,
+      "grad_norm": 1.8322321070759275,
+      "learning_rate": 9.027018380748766e-05,
+      "loss": 1.6931,
+      "step": 290
+    },
+    {
+      "epoch": 0.4297994269340974,
+      "grad_norm": 1.615978489405473,
+      "learning_rate": 8.959305073273809e-05,
+      "loss": 1.6897,
+      "step": 300
+    },
+    {
+      "epoch": 0.4297994269340974,
+      "eval_loss": 1.6719396114349365,
+      "eval_runtime": 53.4447,
+      "eval_samples_per_second": 185.687,
+      "eval_steps_per_second": 1.459,
+      "step": 300
+    },
+    {
+      "epoch": 0.44412607449856734,
+      "grad_norm": 1.8985940929478535,
+      "learning_rate": 8.889586408486953e-05,
+      "loss": 1.6554,
+      "step": 310
+    },
+    {
+      "epoch": 0.4584527220630373,
+      "grad_norm": 1.9424706081821295,
+      "learning_rate": 8.817897698351185e-05,
+      "loss": 1.6655,
+      "step": 320
+    },
+    {
+      "epoch": 0.47277936962750716,
+      "grad_norm": 1.9287612597705355,
+      "learning_rate": 8.744275252642184e-05,
+      "loss": 1.638,
+      "step": 330
+    },
+    {
+      "epoch": 0.4871060171919771,
+      "grad_norm": 1.5833650317049555,
+      "learning_rate": 8.668756360557697e-05,
+      "loss": 1.6386,
+      "step": 340
+    },
+    {
+      "epoch": 0.501432664756447,
+      "grad_norm": 1.9070708361736106,
+      "learning_rate": 8.591379271830855e-05,
+      "loss": 1.6365,
+      "step": 350
+    },
+    {
+      "epoch": 0.5157593123209169,
+      "grad_norm": 1.7717200377491302,
+      "learning_rate": 8.512183177356973e-05,
+      "loss": 1.6135,
+      "step": 360
+    },
+    {
+      "epoch": 0.5300859598853869,
+      "grad_norm": 1.5741330801409983,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 1.6001,
+      "step": 370
+    },
+    {
+      "epoch": 0.5444126074498568,
+      "grad_norm": 2.216205258530314,
+      "learning_rate": 8.348495320994345e-05,
+      "loss": 1.6161,
+      "step": 380
+    },
+    {
+      "epoch": 0.5587392550143266,
+      "grad_norm": 1.6749338500257063,
+      "learning_rate": 8.264086465735312e-05,
+      "loss": 1.5873,
+      "step": 390
+    },
+    {
+      "epoch": 0.5730659025787965,
+      "grad_norm": 1.6669193921386205,
+      "learning_rate": 8.178024375997097e-05,
+      "loss": 1.5887,
+      "step": 400
+    },
+    {
+      "epoch": 0.5730659025787965,
+      "eval_loss": 1.5738122463226318,
+      "eval_runtime": 53.5809,
+      "eval_samples_per_second": 185.215,
+      "eval_steps_per_second": 1.456,
+      "step": 400
+    },
+    {
+      "epoch": 0.5873925501432665,
+      "grad_norm": 1.6738558434456052,
+      "learning_rate": 8.090352641560668e-05,
+      "loss": 1.6297,
+      "step": 410
+    },
+    {
+      "epoch": 0.6017191977077364,
+      "grad_norm": 1.6812511762700748,
+      "learning_rate": 8.001115667479552e-05,
+      "loss": 1.5987,
+      "step": 420
+    },
+    {
+      "epoch": 0.6160458452722063,
+      "grad_norm": 1.6615769390951736,
+      "learning_rate": 7.910358651589015e-05,
+      "loss": 1.5509,
+      "step": 430
+    },
+    {
+      "epoch": 0.6303724928366762,
+      "grad_norm": 1.696391678445336,
+      "learning_rate": 7.818127561613707e-05,
+      "loss": 1.5429,
+      "step": 440
+    },
+    {
+      "epoch": 0.6446991404011462,
+      "grad_norm": 1.5660326039107408,
+      "learning_rate": 7.724469111885371e-05,
+      "loss": 1.5396,
+      "step": 450
+    },
+    {
+      "epoch": 0.6590257879656161,
+      "grad_norm": 2.028710946062277,
+      "learning_rate": 7.629430739682398e-05,
+      "loss": 1.5266,
+      "step": 460
+    },
+    {
+      "epoch": 0.673352435530086,
+      "grad_norm": 2.116807818224008,
+      "learning_rate": 7.533060581203201e-05,
+      "loss": 1.5824,
+      "step": 470
+    },
+    {
+      "epoch": 0.6876790830945558,
+      "grad_norm": 1.637751947026498,
+      "learning_rate": 7.435407447185623e-05,
+      "loss": 1.4828,
+      "step": 480
+    },
+    {
+      "epoch": 0.7020057306590258,
+      "grad_norm": 1.5564501538035538,
+      "learning_rate": 7.336520798184664e-05,
+      "loss": 1.4991,
+      "step": 490
+    },
+    {
+      "epoch": 0.7163323782234957,
+      "grad_norm": 1.575375723060998,
+      "learning_rate": 7.236450719521092e-05,
+      "loss": 1.4628,
+      "step": 500
+    },
+    {
+      "epoch": 0.7163323782234957,
+      "eval_loss": 1.4659688472747803,
+      "eval_runtime": 53.8819,
+      "eval_samples_per_second": 184.18,
+      "eval_steps_per_second": 1.448,
+      "step": 500
+    },
+    {
+      "epoch": 0.7306590257879656,
+      "grad_norm": 1.5701973244119096,
+      "learning_rate": 7.135247895913623e-05,
+      "loss": 1.485,
+      "step": 510
+    },
+    {
+      "epoch": 0.7449856733524355,
+      "grad_norm": 1.7014160396040479,
+      "learning_rate": 7.032963585807501e-05,
+      "loss": 1.454,
+      "step": 520
+    },
+    {
+      "epoch": 0.7593123209169055,
+      "grad_norm": 1.4812078348628686,
+      "learning_rate": 6.929649595412497e-05,
+      "loss": 1.4675,
+      "step": 530
+    },
+    {
+      "epoch": 0.7736389684813754,
+      "grad_norm": 1.6254083780903348,
+      "learning_rate": 6.825358252463461e-05,
+      "loss": 1.4232,
+      "step": 540
+    },
+    {
+      "epoch": 0.7879656160458453,
+      "grad_norm": 1.593996844960836,
+      "learning_rate": 6.720142379716728e-05,
+      "loss": 1.4084,
+      "step": 550
+    },
+    {
+      "epoch": 0.8022922636103151,
+      "grad_norm": 1.4683667712701527,
+      "learning_rate": 6.614055268195805e-05,
+      "loss": 1.4034,
+      "step": 560
+    },
+    {
+      "epoch": 0.8166189111747851,
+      "grad_norm": 1.6604556204013439,
+      "learning_rate": 6.507150650199886e-05,
+      "loss": 1.439,
+      "step": 570
+    },
+    {
+      "epoch": 0.830945558739255,
+      "grad_norm": 1.5795992163148025,
+      "learning_rate": 6.399482672088852e-05,
+      "loss": 1.3767,
+      "step": 580
+    },
+    {
+      "epoch": 0.8452722063037249,
+      "grad_norm": 1.7278879653526587,
+      "learning_rate": 6.291105866858562e-05,
+      "loss": 1.4084,
+      "step": 590
+    },
+    {
+      "epoch": 0.8595988538681948,
+      "grad_norm": 1.4915922467967875,
+      "learning_rate": 6.18207512652031e-05,
+      "loss": 1.3751,
+      "step": 600
+    },
+    {
+      "epoch": 0.8595988538681948,
+      "eval_loss": 1.3670978546142578,
+      "eval_runtime": 53.4401,
+      "eval_samples_per_second": 185.703,
+      "eval_steps_per_second": 1.46,
+      "step": 600
+    },
+    {
+      "epoch": 0.8739255014326648,
+      "grad_norm": 1.5055751912412483,
+      "learning_rate": 6.0724456742984535e-05,
+      "loss": 1.3799,
+      "step": 610
+    },
+    {
+      "epoch": 0.8882521489971347,
+      "grad_norm": 1.5174029894001677,
+      "learning_rate": 5.962273036660276e-05,
+      "loss": 1.372,
+      "step": 620
+    },
+    {
+      "epoch": 0.9025787965616046,
+      "grad_norm": 1.6367622819691852,
+      "learning_rate": 5.851613015192261e-05,
+      "loss": 1.3514,
+      "step": 630
+    },
+    {
+      "epoch": 0.9169054441260746,
+      "grad_norm": 1.556482139125314,
+      "learning_rate": 5.74052165833702e-05,
+      "loss": 1.3283,
+      "step": 640
+    },
+    {
+      "epoch": 0.9312320916905444,
+      "grad_norm": 1.6450518726375203,
+      "learning_rate": 5.6290552330051946e-05,
+      "loss": 1.3257,
+      "step": 650
+    },
+    {
+      "epoch": 0.9455587392550143,
+      "grad_norm": 1.3993302544976038,
+      "learning_rate": 5.5172701960767006e-05,
+      "loss": 1.3279,
+      "step": 660
+    },
+    {
+      "epoch": 0.9598853868194842,
+      "grad_norm": 1.6965193543443504,
+      "learning_rate": 5.405223165805755e-05,
+      "loss": 1.2695,
+      "step": 670
+    },
+    {
+      "epoch": 0.9742120343839542,
+      "grad_norm": 1.4956063904398584,
+      "learning_rate": 5.292970893144172e-05,
+      "loss": 1.2958,
+      "step": 680
+    },
+    {
+      "epoch": 0.9885386819484241,
+      "grad_norm": 1.3407355333418884,
+      "learning_rate": 5.180570232997446e-05,
+      "loss": 1.2763,
+      "step": 690
+    },
+    {
+      "epoch": 1.002865329512894,
+      "grad_norm": 1.8406934340144963,
+      "learning_rate": 5.06807811542818e-05,
+      "loss": 1.1263,
+      "step": 700
+    },
+    {
+      "epoch": 1.002865329512894,
+      "eval_loss": 1.2830663919448853,
+      "eval_runtime": 53.5866,
+      "eval_samples_per_second": 185.196,
+      "eval_steps_per_second": 1.456,
+      "step": 700
+    },
+    {
+      "epoch": 1.0171919770773639,
+      "grad_norm": 1.466971080200883,
+      "learning_rate": 4.9555515168214514e-05,
+      "loss": 0.7167,
+      "step": 710
+    },
+    {
+      "epoch": 1.0315186246418337,
+      "grad_norm": 1.3865994721327555,
+      "learning_rate": 4.8430474310267185e-05,
+      "loss": 0.6893,
+      "step": 720
+    },
+    {
+      "epoch": 1.0458452722063036,
+      "grad_norm": 1.5632728482959424,
+      "learning_rate": 4.7306228404908706e-05,
+      "loss": 0.6935,
+      "step": 730
+    },
+    {
+      "epoch": 1.0601719197707737,
+      "grad_norm": 1.3730426755979892,
+      "learning_rate": 4.6183346873970704e-05,
+      "loss": 0.7053,
+      "step": 740
+    },
+    {
+      "epoch": 1.0744985673352436,
+      "grad_norm": 1.469352640225314,
+      "learning_rate": 4.506239844823972e-05,
+      "loss": 0.6848,
+      "step": 750
+    },
+    {
+      "epoch": 1.0888252148997135,
+      "grad_norm": 1.4293421992017694,
+      "learning_rate": 4.394395087939947e-05,
+      "loss": 0.6677,
+      "step": 760
+    },
+    {
+      "epoch": 1.1031518624641834,
+      "grad_norm": 1.497199630056392,
+      "learning_rate": 4.282857065246908e-05,
+      "loss": 0.6844,
+      "step": 770
+    },
+    {
+      "epoch": 1.1174785100286533,
+      "grad_norm": 1.4739240120513313,
+      "learning_rate": 4.1716822698882826e-05,
+      "loss": 0.6735,
+      "step": 780
+    },
+    {
+      "epoch": 1.1318051575931232,
+      "grad_norm": 1.4505373708013058,
+      "learning_rate": 4.0609270110356625e-05,
+      "loss": 0.6405,
+      "step": 790
+    },
+    {
+      "epoch": 1.146131805157593,
+      "grad_norm": 1.507546317576944,
+      "learning_rate": 3.9506473853686586e-05,
+      "loss": 0.688,
+      "step": 800
+    },
+    {
+      "epoch": 1.146131805157593,
+      "eval_loss": 1.2491989135742188,
+      "eval_runtime": 53.6109,
+      "eval_samples_per_second": 185.112,
+      "eval_steps_per_second": 1.455,
+      "step": 800
+    },
+    {
+      "epoch": 1.1604584527220632,
+      "grad_norm": 1.6233022720214296,
+      "learning_rate": 3.8408992486623595e-05,
+      "loss": 0.662,
+      "step": 810
+    },
+    {
+      "epoch": 1.174785100286533,
+      "grad_norm": 1.2645448426600083,
+      "learning_rate": 3.7317381874968207e-05,
+      "loss": 0.6901,
+      "step": 820
+    },
+    {
+      "epoch": 1.189111747851003,
+      "grad_norm": 1.4745754772070392,
+      "learning_rate": 3.6232194911028874e-05,
+      "loss": 0.6705,
+      "step": 830
+    },
+    {
+      "epoch": 1.2034383954154728,
+      "grad_norm": 1.3592040417066167,
+      "learning_rate": 3.515398123358627e-05,
+      "loss": 0.6764,
+      "step": 840
+    },
+    {
+      "epoch": 1.2177650429799427,
+      "grad_norm": 1.3029544883514448,
+      "learning_rate": 3.40832869495056e-05,
+      "loss": 0.6761,
+      "step": 850
+    },
+    {
+      "epoch": 1.2320916905444126,
+      "grad_norm": 2.098968282444413,
+      "learning_rate": 3.302065435713763e-05,
+      "loss": 0.6275,
+      "step": 860
+    },
+    {
+      "epoch": 1.2464183381088825,
+      "grad_norm": 1.3448595848587355,
+      "learning_rate": 3.196662167164877e-05,
+      "loss": 0.6342,
+      "step": 870
+    },
+    {
+      "epoch": 1.2607449856733524,
+      "grad_norm": 1.3928584326736022,
+      "learning_rate": 3.092172275241933e-05,
+      "loss": 0.6357,
+      "step": 880
+    },
+    {
+      "epoch": 1.2750716332378222,
+      "grad_norm": 1.408932176758002,
+      "learning_rate": 2.9886486832647835e-05,
+      "loss": 0.6189,
+      "step": 890
+    },
+    {
+      "epoch": 1.2893982808022924,
+      "grad_norm": 1.3715405151520115,
+      "learning_rate": 2.8861438251298512e-05,
+      "loss": 0.6544,
+      "step": 900
+    },
+    {
+      "epoch": 1.2893982808022924,
+      "eval_loss": 1.1817691326141357,
+      "eval_runtime": 53.5943,
+      "eval_samples_per_second": 185.169,
+      "eval_steps_per_second": 1.455,
+      "step": 900
+    },
+    {
+      "epoch": 1.3037249283667622,
+      "grad_norm": 1.188564778298211,
+      "learning_rate": 2.784709618752776e-05,
+      "loss": 0.6359,
+      "step": 910
+    },
+    {
+      "epoch": 1.3180515759312321,
+      "grad_norm": 1.2862274938371403,
+      "learning_rate": 2.6843974397723753e-05,
+      "loss": 0.621,
+      "step": 920
+    },
+    {
+      "epoch": 1.332378223495702,
+      "grad_norm": 1.316124517086862,
+      "learning_rate": 2.5852580955293003e-05,
+      "loss": 0.6265,
+      "step": 930
+    },
+    {
+      "epoch": 1.346704871060172,
+      "grad_norm": 1.3322773186587833,
+      "learning_rate": 2.4873417993325042e-05,
+      "loss": 0.6441,
+      "step": 940
+    },
+    {
+      "epoch": 1.3610315186246418,
+      "grad_norm": 1.2889293368365848,
+      "learning_rate": 2.3906981450265836e-05,
+      "loss": 0.6173,
+      "step": 950
+    },
+    {
+      "epoch": 1.3753581661891117,
+      "grad_norm": 1.4909707916630004,
+      "learning_rate": 2.295376081872895e-05,
+      "loss": 0.6193,
+      "step": 960
+    },
+    {
+      "epoch": 1.3896848137535818,
+      "grad_norm": 1.3688980598451725,
+      "learning_rate": 2.201423889757122e-05,
+      "loss": 0.6466,
+      "step": 970
+    },
+    {
+      "epoch": 1.4040114613180517,
+      "grad_norm": 1.3684687851700825,
+      "learning_rate": 2.108889154735895e-05,
+      "loss": 0.6124,
+      "step": 980
+    },
+    {
+      "epoch": 1.4183381088825215,
+      "grad_norm": 1.2359362156168956,
+      "learning_rate": 2.0178187449348208e-05,
+      "loss": 0.6183,
+      "step": 990
+    },
+    {
+      "epoch": 1.4326647564469914,
+      "grad_norm": 1.2595878525492465,
+      "learning_rate": 1.9282587868101308e-05,
+      "loss": 0.6017,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4326647564469914,
+      "eval_loss": 1.120739459991455,
+      "eval_runtime": 53.3734,
+      "eval_samples_per_second": 185.935,
+      "eval_steps_per_second": 1.461,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4469914040114613,
+      "grad_norm": 1.384961270564966,
+      "learning_rate": 1.840254641786006e-05,
+      "loss": 0.5614,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4613180515759312,
+      "grad_norm": 1.4232024294510734,
+      "learning_rate": 1.7538508832793578e-05,
+      "loss": 0.5797,
+      "step": 1020
+    },
+    {
+      "epoch": 1.475644699140401,
+      "grad_norm": 1.1618822443190342,
+      "learning_rate": 1.669091274123732e-05,
+      "loss": 0.6184,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4899713467048712,
+      "grad_norm": 1.3507488640615957,
+      "learning_rate": 1.586018744403787e-05,
+      "loss": 0.5813,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5042979942693409,
+      "grad_norm": 1.3443442941285704,
+      "learning_rate": 1.504675369711529e-05,
+      "loss": 0.5667,
+      "step": 1050
+    },
+    {
+      "epoch": 1.518624641833811,
+      "grad_norm": 1.2877577958996937,
+      "learning_rate": 1.4251023498353533e-05,
+      "loss": 0.582,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5329512893982808,
+      "grad_norm": 1.1575931882275956,
+      "learning_rate": 1.3473399878926746e-05,
+      "loss": 0.563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5472779369627507,
+      "grad_norm": 1.1621133893036653,
+      "learning_rate": 1.2714276699166994e-05,
+      "loss": 0.5466,
+      "step": 1080
+    },
+    {
+      "epoch": 1.5616045845272206,
+      "grad_norm": 1.228237925890841,
+      "learning_rate": 1.1974038449077258e-05,
+      "loss": 0.5239,
+      "step": 1090
+    },
+    {
+      "epoch": 1.5759312320916905,
+      "grad_norm": 1.1901152329499263,
+      "learning_rate": 1.1253060053589997e-05,
+      "loss": 0.5763,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5759312320916905,
+      "eval_loss": 1.0708156824111938,
+      "eval_runtime": 53.5345,
+      "eval_samples_per_second": 185.376,
+      "eval_steps_per_second": 1.457,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5902578796561606,
+      "grad_norm": 1.321031783530892,
+      "learning_rate": 1.0551706682670748e-05,
+      "loss": 0.5511,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6045845272206303,
+      "grad_norm": 1.263841226648576,
+      "learning_rate": 9.870333566362322e-06,
+      "loss": 0.5645,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6189111747851004,
+      "grad_norm": 1.2601683852009655,
+      "learning_rate": 9.209285814863477e-06,
+      "loss": 0.5301,
+      "step": 1130
+    },
+    {
+      "epoch": 1.63323782234957,
+      "grad_norm": 1.1853670920081087,
+      "learning_rate": 8.568898243733386e-06,
+      "loss": 0.5371,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6475644699140402,
+      "grad_norm": 1.2370950402879501,
+      "learning_rate": 7.949495204310104e-06,
+      "loss": 0.5555,
+      "step": 1150
+    },
+    {
+      "epoch": 1.66189111747851,
+      "grad_norm": 1.3089349313138638,
+      "learning_rate": 7.351390419429083e-06,
+      "loss": 0.5616,
+      "step": 1160
+    },
+    {
+      "epoch": 1.67621776504298,
+      "grad_norm": 1.3007158953895024,
+      "learning_rate": 6.774886824525073e-06,
+      "loss": 0.539,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6905444126074498,
+      "grad_norm": 1.2215575024934626,
+      "learning_rate": 6.2202764141976346e-06,
+      "loss": 0.5366,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7048710601719197,
+      "grad_norm": 1.1917522774279614,
+      "learning_rate": 5.687840094318125e-06,
+      "loss": 0.5072,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7191977077363898,
+      "grad_norm": 1.2065112378383362,
+      "learning_rate": 5.177847539753084e-06,
+      "loss": 0.5599,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7191977077363898,
+      "eval_loss": 1.036474347114563,
+      "eval_runtime": 53.4293,
+      "eval_samples_per_second": 185.741,
+      "eval_steps_per_second": 1.46,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7335243553008595,
+      "grad_norm": 1.240311618648056,
+      "learning_rate": 4.690557057775974e-06,
+      "loss": 0.5367,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7478510028653296,
+      "grad_norm": 1.2440347942531507,
+      "learning_rate": 4.226215457236565e-06,
+      "loss": 0.5388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.7621776504297995,
+      "grad_norm": 1.2299956356695219,
+      "learning_rate": 3.785057923554197e-06,
+      "loss": 0.5238,
+      "step": 1230
+    },
+    {
+      "epoch": 1.7765042979942693,
+      "grad_norm": 1.3887050995508965,
+      "learning_rate": 3.36730789959811e-06,
+      "loss": 0.4981,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7908309455587392,
+      "grad_norm": 1.1031870914219795,
+      "learning_rate": 2.9731769725154514e-06,
+      "loss": 0.5294,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8051575931232091,
+      "grad_norm": 1.4024610914172573,
+      "learning_rate": 2.6028647665639672e-06,
+      "loss": 0.5275,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8194842406876792,
+      "grad_norm": 1.233183532537092,
+      "learning_rate": 2.256558842003892e-06,
+      "loss": 0.5253,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8338108882521489,
+      "grad_norm": 1.2308977898401474,
+      "learning_rate": 1.9344346001001377e-06,
+      "loss": 0.5442,
+      "step": 1280
+    },
+    {
+      "epoch": 1.848137535816619,
+      "grad_norm": 1.1860759958409324,
+      "learning_rate": 1.6366551942828711e-06,
+      "loss": 0.5483,
+      "step": 1290
+    },
+    {
+      "epoch": 1.8624641833810889,
+      "grad_norm": 1.3493855244370383,
+      "learning_rate": 1.363371447511619e-06,
+      "loss": 0.5101,
+      "step": 1300
+    },
+    {
+      "epoch": 1.8624641833810889,
+      "eval_loss": 1.0169659852981567,
+      "eval_runtime": 53.5386,
+      "eval_samples_per_second": 185.361,
+      "eval_steps_per_second": 1.457,
+      "step": 1300
+    },
+    {
+      "epoch": 1.8767908309455588,
+      "grad_norm": 1.3172256182801068,
+      "learning_rate": 1.1147217758845751e-06,
+      "loss": 0.5469,
+      "step": 1310
+    },
+    {
+      "epoch": 1.8911174785100286,
+      "grad_norm": 1.2977180424743335,
+      "learning_rate": 8.908321185319312e-07,
+      "loss": 0.5319,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9054441260744985,
+      "grad_norm": 1.1849694099091805,
+      "learning_rate": 6.918158738286884e-07,
+      "loss": 0.5126,
+      "step": 1330
+    },
+    {
+      "epoch": 1.9197707736389686,
+      "grad_norm": 1.2190235185481941,
+      "learning_rate": 5.177738419592515e-07,
+      "loss": 0.5276,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9340974212034383,
+      "grad_norm": 1.1093762195623071,
+      "learning_rate": 3.687941738629186e-07,
+      "loss": 0.53,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9484240687679084,
+      "grad_norm": 1.0282807771775446,
+      "learning_rate": 2.449523265861176e-07,
+      "loss": 0.4903,
+      "step": 1360
+    },
+    {
+      "epoch": 1.962750716332378,
+      "grad_norm": 1.3409900754803958,
+      "learning_rate": 1.4631102506399985e-07,
+      "loss": 0.5025,
+      "step": 1370
+    },
+    {
+      "epoch": 1.9770773638968482,
+      "grad_norm": 1.2011587981462408,
+      "learning_rate": 7.292023035074813e-08,
+      "loss": 0.5428,
+      "step": 1380
+    },
+    {
+      "epoch": 1.991404011461318,
+      "grad_norm": 1.2347668278605959,
+      "learning_rate": 2.4817114314662493e-08,
+      "loss": 0.52,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0,
+      "step": 1396,
+      "total_flos": 192624989306880.0,
+      "train_loss": 1.1565231682577926,
+      "train_runtime": 4692.4705,
+      "train_samples_per_second": 38.067,
+      "train_steps_per_second": 0.297
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1396,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 192624989306880.0,
+  "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:a174ae483a495cbf79cea41593780ddb50a7144a434eb105dbe54152608241cd
+size 6968