Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/Minitron-8B-Base
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: minitron-8b-tulu-v2-mix
+  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. -->
+
+# minitron-8b-tulu-v2-mix
+
+This model is a fine-tuned version of [nvidia/Minitron-8B-Base](https://huggingface.co/nvidia/Minitron-8B-Base) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6678
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8625        | 0.9992 | 566  | 0.7793          |
+| 0.724         | 1.9992 | 1132 | 0.6678          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9984552576409578,
+    "total_flos": 2844841381724160.0,
+    "train_loss": 0.0,
+    "train_runtime": 8.0551,
+    "train_samples": 326149,
+    "train_samples_per_second": 27002.356,
+    "train_steps_per_second": 210.799
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nvidia/Minitron-8B-Base",
+  "architectures": [
+    "NemotronForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 128,
+  "hidden_act": "relu2",
+  "hidden_size": 4096,
+  "initializer_range": 0.0134,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "nemotron",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.5,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "transformers_version": "4.44.2",
+  "use_cache": false
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b395959e38c018a37ac45d2bfa4ceb3653acca41306640a25d158ce6304f61
+size 4915962352

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94c22778644f259f5daea25e7b8f65e25df19b0aa5f43316a7cd9d7d3cf353d
+size 4966496880

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0c45c2ff54e9d7405e70a9c9a994ae7076f904e48a767d5a057db55bd34a84
+size 4563826112

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dfc16d4c9d1ea292935c8dfa8efd24bd3e341e84caa335fb238f24debace088
+size 2097152128

model.safetensors.index.json

@@ -0,0 +1,331 @@
+{
+  "metadata": {
+    "total_size": 16543399936
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.bias": "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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "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.bias": "model-00002-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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "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.bias": "model-00001-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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "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.bias": "model-00003-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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "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-00003-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.bias": "model-00003-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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "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.bias": "model-00001-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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "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.bias": "model-00003-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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-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.bias": "model-00001-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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "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.bias": "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.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00002-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.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d0648daa0467fb02ddef7ff25460321dab2fbb20c280ae0bc1ea8052f7df90
+size 18143149

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9984552576409578,
+    "total_flos": 2844841381724160.0,
+    "train_loss": 0.0,
+    "train_runtime": 8.0551,
+    "train_samples": 326149,
+    "train_samples_per_second": 27002.356,
+    "train_steps_per_second": 210.799
+}

trainer_state.json

@@ -0,0 +1,1241 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9984552576409578,
+  "eval_steps": 500,
+  "global_step": 1698,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017654198389054396,
+      "grad_norm": 11.075085595262578,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 1.3624,
+      "step": 10
+    },
+    {
+      "epoch": 0.03530839677810879,
+      "grad_norm": 0.8268832619967722,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 1.0988,
+      "step": 20
+    },
+    {
+      "epoch": 0.052962595167163194,
+      "grad_norm": 0.6592198895247919,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 1.0279,
+      "step": 30
+    },
+    {
+      "epoch": 0.07061679355621758,
+      "grad_norm": 0.7345400249936768,
+      "learning_rate": 1.568627450980392e-05,
+      "loss": 1.0346,
+      "step": 40
+    },
+    {
+      "epoch": 0.08827099194527198,
+      "grad_norm": 0.6520880282674657,
+      "learning_rate": 1.9607843137254903e-05,
+      "loss": 1.0161,
+      "step": 50
+    },
+    {
+      "epoch": 0.10592519033432639,
+      "grad_norm": 0.6267314186354508,
+      "learning_rate": 1.999852647705027e-05,
+      "loss": 0.9827,
+      "step": 60
+    },
+    {
+      "epoch": 0.12357938872338078,
+      "grad_norm": 0.5990775699580297,
+      "learning_rate": 1.9993433374984987e-05,
+      "loss": 0.9727,
+      "step": 70
+    },
+    {
+      "epoch": 0.14123358711243517,
+      "grad_norm": 0.7072632521466412,
+      "learning_rate": 1.9984704354748582e-05,
+      "loss": 0.9887,
+      "step": 80
+    },
+    {
+      "epoch": 0.15888778550148958,
+      "grad_norm": 0.6302011892410732,
+      "learning_rate": 1.9972342592226873e-05,
+      "loss": 0.9639,
+      "step": 90
+    },
+    {
+      "epoch": 0.17654198389054396,
+      "grad_norm": 0.6228020691113849,
+      "learning_rate": 1.9956352585008946e-05,
+      "loss": 0.9584,
+      "step": 100
+    },
+    {
+      "epoch": 0.19419618227959837,
+      "grad_norm": 0.6537080367025939,
+      "learning_rate": 1.9936740150750825e-05,
+      "loss": 0.9517,
+      "step": 110
+    },
+    {
+      "epoch": 0.21185038066865278,
+      "grad_norm": 0.7111863399924561,
+      "learning_rate": 1.9913512425058803e-05,
+      "loss": 0.9408,
+      "step": 120
+    },
+    {
+      "epoch": 0.22950457905770716,
+      "grad_norm": 0.6710168558236342,
+      "learning_rate": 1.9886677858893303e-05,
+      "loss": 0.9374,
+      "step": 130
+    },
+    {
+      "epoch": 0.24715877744676157,
+      "grad_norm": 0.6547246997110331,
+      "learning_rate": 1.9856246215494147e-05,
+      "loss": 0.9353,
+      "step": 140
+    },
+    {
+      "epoch": 0.264812975835816,
+      "grad_norm": 0.5595831632061861,
+      "learning_rate": 1.982222856682841e-05,
+      "loss": 0.9508,
+      "step": 150
+    },
+    {
+      "epoch": 0.28246717422487033,
+      "grad_norm": 0.6617569180053982,
+      "learning_rate": 1.9784637289562067e-05,
+      "loss": 0.9385,
+      "step": 160
+    },
+    {
+      "epoch": 0.30012137261392474,
+      "grad_norm": 0.7260939928287287,
+      "learning_rate": 1.9743486060557015e-05,
+      "loss": 0.9226,
+      "step": 170
+    },
+    {
+      "epoch": 0.31777557100297915,
+      "grad_norm": 0.6291820154599896,
+      "learning_rate": 1.9698789851894986e-05,
+      "loss": 0.9262,
+      "step": 180
+    },
+    {
+      "epoch": 0.33542976939203356,
+      "grad_norm": 0.5974647680183809,
+      "learning_rate": 1.9650564925430257e-05,
+      "loss": 0.9207,
+      "step": 190
+    },
+    {
+      "epoch": 0.3530839677810879,
+      "grad_norm": 0.5295497383864004,
+      "learning_rate": 1.9598828826873085e-05,
+      "loss": 0.9259,
+      "step": 200
+    },
+    {
+      "epoch": 0.3707381661701423,
+      "grad_norm": 0.5999369621481067,
+      "learning_rate": 1.9543600379406027e-05,
+      "loss": 0.931,
+      "step": 210
+    },
+    {
+      "epoch": 0.38839236455919673,
+      "grad_norm": 0.7118598829666988,
+      "learning_rate": 1.9484899676835504e-05,
+      "loss": 0.9132,
+      "step": 220
+    },
+    {
+      "epoch": 0.40604656294825114,
+      "grad_norm": 0.5244866233662618,
+      "learning_rate": 1.9422748076281054e-05,
+      "loss": 0.9165,
+      "step": 230
+    },
+    {
+      "epoch": 0.42370076133730555,
+      "grad_norm": 0.5981442443509013,
+      "learning_rate": 1.9357168190404937e-05,
+      "loss": 0.9145,
+      "step": 240
+    },
+    {
+      "epoch": 0.4413549597263599,
+      "grad_norm": 0.5814732591931184,
+      "learning_rate": 1.9288183879184986e-05,
+      "loss": 0.9108,
+      "step": 250
+    },
+    {
+      "epoch": 0.4590091581154143,
+      "grad_norm": 0.6328453186407658,
+      "learning_rate": 1.9215820241233585e-05,
+      "loss": 0.9256,
+      "step": 260
+    },
+    {
+      "epoch": 0.4766633565044687,
+      "grad_norm": 0.6253638836302401,
+      "learning_rate": 1.9140103604666035e-05,
+      "loss": 0.903,
+      "step": 270
+    },
+    {
+      "epoch": 0.49431755489352314,
+      "grad_norm": 0.6443153938386799,
+      "learning_rate": 1.9061061517521575e-05,
+      "loss": 0.9085,
+      "step": 280
+    },
+    {
+      "epoch": 0.5119717532825775,
+      "grad_norm": 0.5794297240032266,
+      "learning_rate": 1.897872273774056e-05,
+      "loss": 0.9142,
+      "step": 290
+    },
+    {
+      "epoch": 0.529625951671632,
+      "grad_norm": 0.5506943177514773,
+      "learning_rate": 1.8893117222701435e-05,
+      "loss": 0.8941,
+      "step": 300
+    },
+    {
+      "epoch": 0.5472801500606863,
+      "grad_norm": 0.7158873616368372,
+      "learning_rate": 1.8804276118321328e-05,
+      "loss": 0.912,
+      "step": 310
+    },
+    {
+      "epoch": 0.5649343484497407,
+      "grad_norm": 0.6761743351092112,
+      "learning_rate": 1.8712231747724194e-05,
+      "loss": 0.909,
+      "step": 320
+    },
+    {
+      "epoch": 0.5825885468387951,
+      "grad_norm": 0.5834711748627983,
+      "learning_rate": 1.861701759948068e-05,
+      "loss": 0.8963,
+      "step": 330
+    },
+    {
+      "epoch": 0.6002427452278495,
+      "grad_norm": 0.5603155829035662,
+      "learning_rate": 1.8518668315423962e-05,
+      "loss": 0.8995,
+      "step": 340
+    },
+    {
+      "epoch": 0.617896943616904,
+      "grad_norm": 0.522797804575778,
+      "learning_rate": 1.8417219678045953e-05,
+      "loss": 0.8962,
+      "step": 350
+    },
+    {
+      "epoch": 0.6355511420059583,
+      "grad_norm": 0.6835351293213303,
+      "learning_rate": 1.831270859747857e-05,
+      "loss": 0.8916,
+      "step": 360
+    },
+    {
+      "epoch": 0.6532053403950127,
+      "grad_norm": 0.5938476091687838,
+      "learning_rate": 1.8205173098064656e-05,
+      "loss": 0.8726,
+      "step": 370
+    },
+    {
+      "epoch": 0.6708595387840671,
+      "grad_norm": 0.634802092406171,
+      "learning_rate": 1.8094652304523584e-05,
+      "loss": 0.8841,
+      "step": 380
+    },
+    {
+      "epoch": 0.6885137371731215,
+      "grad_norm": 0.6742253195098137,
+      "learning_rate": 1.7981186427716478e-05,
+      "loss": 0.8817,
+      "step": 390
+    },
+    {
+      "epoch": 0.7061679355621758,
+      "grad_norm": 0.5772838179810406,
+      "learning_rate": 1.7864816750016246e-05,
+      "loss": 0.8803,
+      "step": 400
+    },
+    {
+      "epoch": 0.7238221339512303,
+      "grad_norm": 0.6030744898202103,
+      "learning_rate": 1.7745585610287812e-05,
+      "loss": 0.876,
+      "step": 410
+    },
+    {
+      "epoch": 0.7414763323402846,
+      "grad_norm": 0.5955540196255147,
+      "learning_rate": 1.7623536388483902e-05,
+      "loss": 0.879,
+      "step": 420
+    },
+    {
+      "epoch": 0.7591305307293391,
+      "grad_norm": 0.6933702635166431,
+      "learning_rate": 1.7498713489862133e-05,
+      "loss": 0.8917,
+      "step": 430
+    },
+    {
+      "epoch": 0.7767847291183935,
+      "grad_norm": 0.5817510021566383,
+      "learning_rate": 1.737116232882895e-05,
+      "loss": 0.8731,
+      "step": 440
+    },
+    {
+      "epoch": 0.7944389275074478,
+      "grad_norm": 0.6017117570992859,
+      "learning_rate": 1.7240929312416545e-05,
+      "loss": 0.8758,
+      "step": 450
+    },
+    {
+      "epoch": 0.8120931258965023,
+      "grad_norm": 0.52374499191387,
+      "learning_rate": 1.710806182339848e-05,
+      "loss": 0.8728,
+      "step": 460
+    },
+    {
+      "epoch": 0.8297473242855566,
+      "grad_norm": 0.5995068247811851,
+      "learning_rate": 1.697260820305044e-05,
+      "loss": 0.8867,
+      "step": 470
+    },
+    {
+      "epoch": 0.8474015226746111,
+      "grad_norm": 0.5610337196661641,
+      "learning_rate": 1.683461773356213e-05,
+      "loss": 0.865,
+      "step": 480
+    },
+    {
+      "epoch": 0.8650557210636655,
+      "grad_norm": 0.5740324652987965,
+      "learning_rate": 1.669414062010696e-05,
+      "loss": 0.8795,
+      "step": 490
+    },
+    {
+      "epoch": 0.8827099194527198,
+      "grad_norm": 0.6580353279100991,
+      "learning_rate": 1.6551227972575823e-05,
+      "loss": 0.8642,
+      "step": 500
+    },
+    {
+      "epoch": 0.9003641178417743,
+      "grad_norm": 0.5609839098459638,
+      "learning_rate": 1.6405931786981753e-05,
+      "loss": 0.8666,
+      "step": 510
+    },
+    {
+      "epoch": 0.9180183162308286,
+      "grad_norm": 0.606711772111839,
+      "learning_rate": 1.6258304926542183e-05,
+      "loss": 0.85,
+      "step": 520
+    },
+    {
+      "epoch": 0.935672514619883,
+      "grad_norm": 0.5282629393908134,
+      "learning_rate": 1.610840110244568e-05,
+      "loss": 0.8703,
+      "step": 530
+    },
+    {
+      "epoch": 0.9533267130089375,
+      "grad_norm": 0.5716697646332912,
+      "learning_rate": 1.5956274854310157e-05,
+      "loss": 0.8878,
+      "step": 540
+    },
+    {
+      "epoch": 0.9709809113979918,
+      "grad_norm": 0.6293891083073122,
+      "learning_rate": 1.5801981530339695e-05,
+      "loss": 0.8505,
+      "step": 550
+    },
+    {
+      "epoch": 0.9886351097870463,
+      "grad_norm": 0.5032178564593078,
+      "learning_rate": 1.5645577267187163e-05,
+      "loss": 0.8625,
+      "step": 560
+    },
+    {
+      "epoch": 0.9992276288204789,
+      "eval_loss": 0.7792695760726929,
+      "eval_runtime": 577.071,
+      "eval_samples_per_second": 9.642,
+      "eval_steps_per_second": 2.41,
+      "step": 566
+    },
+    {
+      "epoch": 1.0070616793556217,
+      "grad_norm": 0.565136350859829,
+      "learning_rate": 1.5487118969529973e-05,
+      "loss": 0.7727,
+      "step": 570
+    },
+    {
+      "epoch": 1.024715877744676,
+      "grad_norm": 0.4954225833969141,
+      "learning_rate": 1.5326664289366406e-05,
+      "loss": 0.7606,
+      "step": 580
+    },
+    {
+      "epoch": 1.0423700761337304,
+      "grad_norm": 0.523592237844004,
+      "learning_rate": 1.516427160504006e-05,
+      "loss": 0.7597,
+      "step": 590
+    },
+    {
+      "epoch": 1.060024274522785,
+      "grad_norm": 0.5408055640730495,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7536,
+      "step": 600
+    },
+    {
+      "epoch": 1.0776784729118394,
+      "grad_norm": 0.5246834404536742,
+      "learning_rate": 1.4833909241304391e-05,
+      "loss": 0.7562,
+      "step": 610
+    },
+    {
+      "epoch": 1.0953326713008937,
+      "grad_norm": 0.5643207747274573,
+      "learning_rate": 1.4666059757875397e-05,
+      "loss": 0.7612,
+      "step": 620
+    },
+    {
+      "epoch": 1.112986869689948,
+      "grad_norm": 0.517010952574902,
+      "learning_rate": 1.4496512618513289e-05,
+      "loss": 0.7575,
+      "step": 630
+    },
+    {
+      "epoch": 1.1306410680790024,
+      "grad_norm": 0.5261650605787747,
+      "learning_rate": 1.4325329509677743e-05,
+      "loss": 0.7473,
+      "step": 640
+    },
+    {
+      "epoch": 1.148295266468057,
+      "grad_norm": 0.5342217209976181,
+      "learning_rate": 1.4152572713044397e-05,
+      "loss": 0.7645,
+      "step": 650
+    },
+    {
+      "epoch": 1.1659494648571114,
+      "grad_norm": 0.5394360986026229,
+      "learning_rate": 1.3978305082844876e-05,
+      "loss": 0.7456,
+      "step": 660
+    },
+    {
+      "epoch": 1.1836036632461657,
+      "grad_norm": 0.5251341793704711,
+      "learning_rate": 1.3802590022998483e-05,
+      "loss": 0.7564,
+      "step": 670
+    },
+    {
+      "epoch": 1.20125786163522,
+      "grad_norm": 0.5365883139849793,
+      "learning_rate": 1.3625491464043909e-05,
+      "loss": 0.7662,
+      "step": 680
+    },
+    {
+      "epoch": 1.2189120600242744,
+      "grad_norm": 0.5851452149462395,
+      "learning_rate": 1.3447073839879339e-05,
+      "loss": 0.7467,
+      "step": 690
+    },
+    {
+      "epoch": 1.236566258413329,
+      "grad_norm": 0.49698239669222605,
+      "learning_rate": 1.3267402064319415e-05,
+      "loss": 0.7468,
+      "step": 700
+    },
+    {
+      "epoch": 1.2542204568023834,
+      "grad_norm": 0.5490853297859661,
+      "learning_rate": 1.3086541507477598e-05,
+      "loss": 0.7496,
+      "step": 710
+    },
+    {
+      "epoch": 1.2718746551914377,
+      "grad_norm": 0.49838225273553083,
+      "learning_rate": 1.2904557971982514e-05,
+      "loss": 0.7465,
+      "step": 720
+    },
+    {
+      "epoch": 1.289528853580492,
+      "grad_norm": 0.5406712310299336,
+      "learning_rate": 1.2721517669036929e-05,
+      "loss": 0.7473,
+      "step": 730
+    },
+    {
+      "epoch": 1.3071830519695464,
+      "grad_norm": 0.5048219957782835,
+      "learning_rate": 1.253748719432809e-05,
+      "loss": 0.734,
+      "step": 740
+    },
+    {
+      "epoch": 1.324837250358601,
+      "grad_norm": 0.47951222482587946,
+      "learning_rate": 1.2352533503798156e-05,
+      "loss": 0.7431,
+      "step": 750
+    },
+    {
+      "epoch": 1.3424914487476554,
+      "grad_norm": 0.5851936786168687,
+      "learning_rate": 1.2166723889283574e-05,
+      "loss": 0.7472,
+      "step": 760
+    },
+    {
+      "epoch": 1.3601456471367097,
+      "grad_norm": 0.485279585177607,
+      "learning_rate": 1.1980125954032239e-05,
+      "loss": 0.7366,
+      "step": 770
+    },
+    {
+      "epoch": 1.377799845525764,
+      "grad_norm": 0.5453687928417636,
+      "learning_rate": 1.1792807588107358e-05,
+      "loss": 0.746,
+      "step": 780
+    },
+    {
+      "epoch": 1.3954540439148184,
+      "grad_norm": 0.5866620790608368,
+      "learning_rate": 1.1604836943686957e-05,
+      "loss": 0.7487,
+      "step": 790
+    },
+    {
+      "epoch": 1.4131082423038728,
+      "grad_norm": 0.5056556922549863,
+      "learning_rate": 1.141628241026802e-05,
+      "loss": 0.7384,
+      "step": 800
+    },
+    {
+      "epoch": 1.4307624406929274,
+      "grad_norm": 0.5141576590110138,
+      "learning_rate": 1.1227212589784297e-05,
+      "loss": 0.7398,
+      "step": 810
+    },
+    {
+      "epoch": 1.4484166390819817,
+      "grad_norm": 0.48402830116887263,
+      "learning_rate": 1.1037696271646805e-05,
+      "loss": 0.7369,
+      "step": 820
+    },
+    {
+      "epoch": 1.466070837471036,
+      "grad_norm": 0.5165402289756648,
+      "learning_rate": 1.0847802407716128e-05,
+      "loss": 0.7482,
+      "step": 830
+    },
+    {
+      "epoch": 1.4837250358600904,
+      "grad_norm": 0.4874182996900902,
+      "learning_rate": 1.0657600087215618e-05,
+      "loss": 0.7375,
+      "step": 840
+    },
+    {
+      "epoch": 1.501379234249145,
+      "grad_norm": 0.49738455424585243,
+      "learning_rate": 1.0467158511594595e-05,
+      "loss": 0.7397,
+      "step": 850
+    },
+    {
+      "epoch": 1.5190334326381993,
+      "grad_norm": 0.49991861283295536,
+      "learning_rate": 1.0276546969350757e-05,
+      "loss": 0.7278,
+      "step": 860
+    },
+    {
+      "epoch": 1.5366876310272537,
+      "grad_norm": 0.5667368371430999,
+      "learning_rate": 1.0085834810820871e-05,
+      "loss": 0.7301,
+      "step": 870
+    },
+    {
+      "epoch": 1.554341829416308,
+      "grad_norm": 0.5144068476500945,
+      "learning_rate": 9.89509142294901e-06,
+      "loss": 0.7378,
+      "step": 880
+    },
+    {
+      "epoch": 1.5719960278053624,
+      "grad_norm": 0.5137627935948821,
+      "learning_rate": 9.704386204041438e-06,
+      "loss": 0.7517,
+      "step": 890
+    },
+    {
+      "epoch": 1.5896502261944168,
+      "grad_norm": 0.52904044022737,
+      "learning_rate": 9.513788538517375e-06,
+      "loss": 0.7407,
+      "step": 900
+    },
+    {
+      "epoch": 1.6073044245834711,
+      "grad_norm": 0.5115595110168406,
+      "learning_rate": 9.323367771664819e-06,
+      "loss": 0.7338,
+      "step": 910
+    },
+    {
+      "epoch": 1.6249586229725257,
+      "grad_norm": 0.48147125209335884,
+      "learning_rate": 9.133193184410589e-06,
+      "loss": 0.7362,
+      "step": 920
+    },
+    {
+      "epoch": 1.64261282136158,
+      "grad_norm": 0.49180548035958394,
+      "learning_rate": 8.943333968113808e-06,
+      "loss": 0.7398,
+      "step": 930
+    },
+    {
+      "epoch": 1.6602670197506344,
+      "grad_norm": 0.4867013851446762,
+      "learning_rate": 8.753859199391951e-06,
+      "loss": 0.7483,
+      "step": 940
+    },
+    {
+      "epoch": 1.677921218139689,
+      "grad_norm": 0.4804051538514883,
+      "learning_rate": 8.564837814988638e-06,
+      "loss": 0.7307,
+      "step": 950
+    },
+    {
+      "epoch": 1.6955754165287433,
+      "grad_norm": 0.4863063091894713,
+      "learning_rate": 8.376338586692367e-06,
+      "loss": 0.7311,
+      "step": 960
+    },
+    {
+      "epoch": 1.7132296149177977,
+      "grad_norm": 0.5169386880097873,
+      "learning_rate": 8.188430096315168e-06,
+      "loss": 0.7327,
+      "step": 970
+    },
+    {
+      "epoch": 1.730883813306852,
+      "grad_norm": 0.5153036409881078,
+      "learning_rate": 8.00118071074049e-06,
+      "loss": 0.7328,
+      "step": 980
+    },
+    {
+      "epoch": 1.7485380116959064,
+      "grad_norm": 0.5006840768446958,
+      "learning_rate": 7.814658557049175e-06,
+      "loss": 0.746,
+      "step": 990
+    },
+    {
+      "epoch": 1.7661922100849607,
+      "grad_norm": 0.5193653515770323,
+      "learning_rate": 7.62893149773278e-06,
+      "loss": 0.738,
+      "step": 1000
+    },
+    {
+      "epoch": 1.783846408474015,
+      "grad_norm": 0.5162239370053442,
+      "learning_rate": 7.4440671060030725e-06,
+      "loss": 0.73,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8015006068630697,
+      "grad_norm": 0.48852121302241314,
+      "learning_rate": 7.260132641206861e-06,
+      "loss": 0.7394,
+      "step": 1020
+    },
+    {
+      "epoch": 1.819154805252124,
+      "grad_norm": 0.5463945098209841,
+      "learning_rate": 7.077195024354939e-06,
+      "loss": 0.722,
+      "step": 1030
+    },
+    {
+      "epoch": 1.8368090036411784,
+      "grad_norm": 0.49951753268549337,
+      "learning_rate": 6.895320813774206e-06,
+      "loss": 0.7133,
+      "step": 1040
+    },
+    {
+      "epoch": 1.854463202030233,
+      "grad_norm": 0.5119500277521447,
+      "learning_rate": 6.714576180891653e-06,
+      "loss": 0.7184,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8721174004192873,
+      "grad_norm": 0.6424312472729824,
+      "learning_rate": 6.535026886159221e-06,
+      "loss": 0.7186,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8897715988083417,
+      "grad_norm": 0.5373842851342149,
+      "learning_rate": 6.356738255128068e-06,
+      "loss": 0.7211,
+      "step": 1070
+    },
+    {
+      "epoch": 1.907425797197396,
+      "grad_norm": 0.4982902687166508,
+      "learning_rate": 6.179775154681184e-06,
+      "loss": 0.7161,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9250799955864504,
+      "grad_norm": 0.5414062516129651,
+      "learning_rate": 6.004201969432771e-06,
+      "loss": 0.7303,
+      "step": 1090
+    },
+    {
+      "epoch": 1.9427341939755047,
+      "grad_norm": 0.462895367066655,
+      "learning_rate": 5.830082578303193e-06,
+      "loss": 0.7249,
+      "step": 1100
+    },
+    {
+      "epoch": 1.960388392364559,
+      "grad_norm": 0.49592685426373223,
+      "learning_rate": 5.6574803312778196e-06,
+      "loss": 0.7253,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9780425907536134,
+      "grad_norm": 0.4758478775588506,
+      "learning_rate": 5.486458026358381e-06,
+      "loss": 0.7126,
+      "step": 1120
+    },
+    {
+      "epoch": 1.995696789142668,
+      "grad_norm": 0.4969466321267014,
+      "learning_rate": 5.317077886715105e-06,
+      "loss": 0.724,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9992276288204789,
+      "eval_loss": 0.6677735447883606,
+      "eval_runtime": 527.1683,
+      "eval_samples_per_second": 10.555,
+      "eval_steps_per_second": 2.639,
+      "step": 1132
+    },
+    {
+      "epoch": 2.0133509875317226,
+      "grad_norm": 0.5185737619412808,
+      "learning_rate": 5.14940153804804e-06,
+      "loss": 0.6582,
+      "step": 1140
+    },
+    {
+      "epoch": 2.031005185920777,
+      "grad_norm": 0.447637858983293,
+      "learning_rate": 4.983489986165708e-06,
+      "loss": 0.6365,
+      "step": 1150
+    },
+    {
+      "epoch": 2.0486593843098313,
+      "grad_norm": 0.5152236160209434,
+      "learning_rate": 4.819403594789335e-06,
+      "loss": 0.6351,
+      "step": 1160
+    },
+    {
+      "epoch": 2.0663135826988857,
+      "grad_norm": 0.6273558161173919,
+      "learning_rate": 4.6572020635906535e-06,
+      "loss": 0.6414,
+      "step": 1170
+    },
+    {
+      "epoch": 2.08396778108794,
+      "grad_norm": 0.4926770781993292,
+      "learning_rate": 4.4969444064713506e-06,
+      "loss": 0.6335,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1016219794769944,
+      "grad_norm": 0.48793300929617467,
+      "learning_rate": 4.338688930091982e-06,
+      "loss": 0.6397,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1192761778660487,
+      "grad_norm": 0.48663482440046746,
+      "learning_rate": 4.182493212658224e-06,
+      "loss": 0.652,
+      "step": 1200
+    },
+    {
+      "epoch": 2.136930376255103,
+      "grad_norm": 0.4760935997684315,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.6416,
+      "step": 1210
+    },
+    {
+      "epoch": 2.1545845746441574,
+      "grad_norm": 0.4582415888721039,
+      "learning_rate": 3.876507599756136e-06,
+      "loss": 0.6295,
+      "step": 1220
+    },
+    {
+      "epoch": 2.172238773033212,
+      "grad_norm": 0.4464518146441672,
+      "learning_rate": 3.7268290312570622e-06,
+      "loss": 0.6518,
+      "step": 1230
+    },
+    {
+      "epoch": 2.1898929714222666,
+      "grad_norm": 0.4796659798369155,
+      "learning_rate": 3.579432835137928e-06,
+      "loss": 0.6376,
+      "step": 1240
+    },
+    {
+      "epoch": 2.207547169811321,
+      "grad_norm": 0.4613709158191507,
+      "learning_rate": 3.434372638664526e-06,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2252013682003753,
+      "grad_norm": 0.4620560070335567,
+      "learning_rate": 3.2917012191941955e-06,
+      "loss": 0.6331,
+      "step": 1260
+    },
+    {
+      "epoch": 2.2428555665894296,
+      "grad_norm": 0.4403307799157334,
+      "learning_rate": 3.151470484973792e-06,
+      "loss": 0.6448,
+      "step": 1270
+    },
+    {
+      "epoch": 2.260509764978484,
+      "grad_norm": 0.46979962256612806,
+      "learning_rate": 3.0137314562538742e-06,
+      "loss": 0.6333,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2781639633675383,
+      "grad_norm": 0.47605403770220545,
+      "learning_rate": 2.8785342467259568e-06,
+      "loss": 0.6372,
+      "step": 1290
+    },
+    {
+      "epoch": 2.2958181617565927,
+      "grad_norm": 0.44577983389984577,
+      "learning_rate": 2.745928045289631e-06,
+      "loss": 0.6464,
+      "step": 1300
+    },
+    {
+      "epoch": 2.313472360145647,
+      "grad_norm": 0.44706989287780297,
+      "learning_rate": 2.6159610981561134e-06,
+      "loss": 0.626,
+      "step": 1310
+    },
+    {
+      "epoch": 2.3311265585347014,
+      "grad_norm": 0.44473280016435734,
+      "learning_rate": 2.4886806912948034e-06,
+      "loss": 0.6362,
+      "step": 1320
+    },
+    {
+      "epoch": 2.3487807569237558,
+      "grad_norm": 0.4674495930967707,
+      "learning_rate": 2.3641331332291793e-06,
+      "loss": 0.6453,
+      "step": 1330
+    },
+    {
+      "epoch": 2.36643495531281,
+      "grad_norm": 0.4455415304277737,
+      "learning_rate": 2.2423637381883533e-06,
+      "loss": 0.6289,
+      "step": 1340
+    },
+    {
+      "epoch": 2.384089153701865,
+      "grad_norm": 0.4544071638805097,
+      "learning_rate": 2.123416809620351e-06,
+      "loss": 0.6331,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4017433520909193,
+      "grad_norm": 0.4723689800288618,
+      "learning_rate": 2.007335624073157e-06,
+      "loss": 0.645,
+      "step": 1360
+    },
+    {
+      "epoch": 2.4193975504799736,
+      "grad_norm": 0.45220258933192226,
+      "learning_rate": 1.8941624154493731e-06,
+      "loss": 0.6451,
+      "step": 1370
+    },
+    {
+      "epoch": 2.437051748869028,
+      "grad_norm": 0.4387363718825142,
+      "learning_rate": 1.7839383596402382e-06,
+      "loss": 0.6339,
+      "step": 1380
+    },
+    {
+      "epoch": 2.4547059472580823,
+      "grad_norm": 0.52315736570108,
+      "learning_rate": 1.6767035595445614e-06,
+      "loss": 0.6289,
+      "step": 1390
+    },
+    {
+      "epoch": 2.4723601456471367,
+      "grad_norm": 0.44143122222775955,
+      "learning_rate": 1.5724970304780662e-06,
+      "loss": 0.6307,
+      "step": 1400
+    },
+    {
+      "epoch": 2.490014344036191,
+      "grad_norm": 0.49564787712258485,
+      "learning_rate": 1.4713566859784045e-06,
+      "loss": 0.6426,
+      "step": 1410
+    },
+    {
+      "epoch": 2.5076685424252454,
+      "grad_norm": 0.44402047508915227,
+      "learning_rate": 1.373319324011061e-06,
+      "loss": 0.6368,
+      "step": 1420
+    },
+    {
+      "epoch": 2.5253227408142997,
+      "grad_norm": 0.44130611579940193,
+      "learning_rate": 1.2784206135811184e-06,
+      "loss": 0.6398,
+      "step": 1430
+    },
+    {
+      "epoch": 2.5429769392033545,
+      "grad_norm": 0.4764351411669087,
+      "learning_rate": 1.1866950817557743e-06,
+      "loss": 0.6349,
+      "step": 1440
+    },
+    {
+      "epoch": 2.5606311375924085,
+      "grad_norm": 0.4398014393212803,
+      "learning_rate": 1.0981761011023317e-06,
+      "loss": 0.6218,
+      "step": 1450
+    },
+    {
+      "epoch": 2.5782853359814633,
+      "grad_norm": 0.4470462981839341,
+      "learning_rate": 1.0128958775462393e-06,
+      "loss": 0.6241,
+      "step": 1460
+    },
+    {
+      "epoch": 2.5959395343705176,
+      "grad_norm": 0.43673398026523563,
+      "learning_rate": 9.308854386535849e-07,
+      "loss": 0.6408,
+      "step": 1470
+    },
+    {
+      "epoch": 2.613593732759572,
+      "grad_norm": 0.4505573168779551,
+      "learning_rate": 8.521746223423088e-07,
+      "loss": 0.6283,
+      "step": 1480
+    },
+    {
+      "epoch": 2.6312479311486263,
+      "grad_norm": 0.4440648392714403,
+      "learning_rate": 7.767920660262529e-07,
+      "loss": 0.6285,
+      "step": 1490
+    },
+    {
+      "epoch": 2.6489021295376807,
+      "grad_norm": 0.4414194215856468,
+      "learning_rate": 7.047651961959978e-07,
+      "loss": 0.6244,
+      "step": 1500
+    },
+    {
+      "epoch": 2.666556327926735,
+      "grad_norm": 0.4440446143190118,
+      "learning_rate": 6.361202184402515e-07,
+      "loss": 0.6332,
+      "step": 1510
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.4706364746939079,
+      "learning_rate": 5.708821079114612e-07,
+      "loss": 0.6362,
+      "step": 1520
+    },
+    {
+      "epoch": 2.7018647247048437,
+      "grad_norm": 0.43340031061371953,
+      "learning_rate": 5.090746002390734e-07,
+      "loss": 0.6349,
+      "step": 1530
+    },
+    {
+      "epoch": 2.719518923093898,
+      "grad_norm": 0.4246335933712338,
+      "learning_rate": 4.507201828937935e-07,
+      "loss": 0.6383,
+      "step": 1540
+    },
+    {
+      "epoch": 2.737173121482953,
+      "grad_norm": 0.44029888263426625,
+      "learning_rate": 3.958400870059476e-07,
+      "loss": 0.6353,
+      "step": 1550
+    },
+    {
+      "epoch": 2.754827319872007,
+      "grad_norm": 0.4317011108249921,
+      "learning_rate": 3.444542796409478e-07,
+      "loss": 0.632,
+      "step": 1560
+    },
+    {
+      "epoch": 2.7724815182610616,
+      "grad_norm": 0.43100429391620887,
+      "learning_rate": 2.965814565346548e-07,
+      "loss": 0.6382,
+      "step": 1570
+    },
+    {
+      "epoch": 2.790135716650116,
+      "grad_norm": 0.4769391216396139,
+      "learning_rate": 2.522390352912985e-07,
+      "loss": 0.6281,
+      "step": 1580
+    },
+    {
+      "epoch": 2.8077899150391703,
+      "grad_norm": 0.44400518164711406,
+      "learning_rate": 2.1144314904642194e-07,
+      "loss": 0.6312,
+      "step": 1590
+    },
+    {
+      "epoch": 2.8254441134282247,
+      "grad_norm": 0.4518349510084993,
+      "learning_rate": 1.7420864059714215e-07,
+      "loss": 0.6319,
+      "step": 1600
+    },
+    {
+      "epoch": 2.843098311817279,
+      "grad_norm": 0.4353149820484635,
+      "learning_rate": 1.405490570018908e-07,
+      "loss": 0.6352,
+      "step": 1610
+    },
+    {
+      "epoch": 2.8607525102063334,
+      "grad_norm": 0.4249015575790441,
+      "learning_rate": 1.1047664465157592e-07,
+      "loss": 0.6471,
+      "step": 1620
+    },
+    {
+      "epoch": 2.8784067085953877,
+      "grad_norm": 0.42688299650964856,
+      "learning_rate": 8.400234481397041e-08,
+      "loss": 0.6232,
+      "step": 1630
+    },
+    {
+      "epoch": 2.896060906984442,
+      "grad_norm": 0.4550228428201464,
+      "learning_rate": 6.113578965293854e-08,
+      "loss": 0.6426,
+      "step": 1640
+    },
+    {
+      "epoch": 2.9137151053734964,
+      "grad_norm": 0.4424051249216907,
+      "learning_rate": 4.188529872396374e-08,
+      "loss": 0.6162,
+      "step": 1650
+    },
+    {
+      "epoch": 2.9313693037625512,
+      "grad_norm": 0.43719698480253905,
+      "learning_rate": 2.625787594723428e-08,
+      "loss": 0.6353,
+      "step": 1660
+    },
+    {
+      "epoch": 2.9490235021516056,
+      "grad_norm": 0.4552786221630045,
+      "learning_rate": 1.4259207059403868e-08,
+      "loss": 0.6355,
+      "step": 1670
+    },
+    {
+      "epoch": 2.96667770054066,
+      "grad_norm": 0.4300462034554104,
+      "learning_rate": 5.8936575449475284e-09,
+      "loss": 0.6366,
+      "step": 1680
+    },
+    {
+      "epoch": 2.9843318989297143,
+      "grad_norm": 0.4321948802854605,
+      "learning_rate": 1.1642710478598772e-09,
+      "loss": 0.6383,
+      "step": 1690
+    },
+    {
+      "epoch": 2.9984552576409578,
+      "step": 1698,
+      "total_flos": 2844841381724160.0,
+      "train_loss": 0.0,
+      "train_runtime": 8.0551,
+      "train_samples_per_second": 27002.356,
+      "train_steps_per_second": 210.799
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1698,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2844841381724160.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8ce67324298f9ddb67845255861822f8ad75fba1bc2a1c7855ae2171a5ea2d
+size 6904