Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: oh-mistral-bs512_lr2.00E-06_schedulerconstant_warmup1.00E-01_minlr
+  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. -->
+
+# oh-mistral-bs512_lr2.00E-06_schedulerconstant_warmup1.00E-01_minlr
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
+
+## 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-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 512
+- total_eval_batch_size: 256
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.0.2
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2592120137318400.0,
+    "train_loss": 0.5171875406913363,
+    "train_runtime": 22202.3543,
+    "train_samples_per_second": 35.668,
+    "train_steps_per_second": 0.07
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/marianna/models/mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f3670b59c4641d765e97be97217f04e02afc51ee3ff391351f2f6216973b69
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9323c4bab12c3fab841006c71edc74a3bd4c26a3d3e658bcea839a41787a5e5
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e89203800efdb74ffe2d034da17494772feac7605414fa9b62aafda77834c6d
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2592120137318400.0,
+    "train_loss": 0.5171875406913363,
+    "train_runtime": 22202.3543,
+    "train_samples_per_second": 35.668,
+    "train_steps_per_second": 0.07
+}

trainer_log.jsonl

@@ -0,0 +1,155 @@
+{"current_steps": 10, "total_steps": 1548, "loss": 0.7225, "learning_rate": 2e-06, "epoch": 0.01937984496124031, "percentage": 0.65, "elapsed_time": "0:02:19", "remaining_time": "5:57:03"}
+{"current_steps": 20, "total_steps": 1548, "loss": 0.6518, "learning_rate": 2e-06, "epoch": 0.03875968992248062, "percentage": 1.29, "elapsed_time": "0:04:36", "remaining_time": "5:52:20"}
+{"current_steps": 30, "total_steps": 1548, "loss": 0.6267, "learning_rate": 2e-06, "epoch": 0.05813953488372093, "percentage": 1.94, "elapsed_time": "0:06:56", "remaining_time": "5:51:39"}
+{"current_steps": 40, "total_steps": 1548, "loss": 0.6192, "learning_rate": 2e-06, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:09:17", "remaining_time": "5:50:06"}
+{"current_steps": 50, "total_steps": 1548, "loss": 0.6139, "learning_rate": 2e-06, "epoch": 0.09689922480620156, "percentage": 3.23, "elapsed_time": "0:11:38", "remaining_time": "5:48:36"}
+{"current_steps": 60, "total_steps": 1548, "loss": 0.6069, "learning_rate": 2e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:13:59", "remaining_time": "5:47:06"}
+{"current_steps": 70, "total_steps": 1548, "loss": 0.6026, "learning_rate": 2e-06, "epoch": 0.13565891472868216, "percentage": 4.52, "elapsed_time": "0:16:21", "remaining_time": "5:45:34"}
+{"current_steps": 80, "total_steps": 1548, "loss": 0.6052, "learning_rate": 2e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:18:43", "remaining_time": "5:43:30"}
+{"current_steps": 90, "total_steps": 1548, "loss": 0.5906, "learning_rate": 2e-06, "epoch": 0.1744186046511628, "percentage": 5.81, "elapsed_time": "0:21:04", "remaining_time": "5:41:30"}
+{"current_steps": 100, "total_steps": 1548, "loss": 0.5926, "learning_rate": 2e-06, "epoch": 0.1937984496124031, "percentage": 6.46, "elapsed_time": "0:23:26", "remaining_time": "5:39:27"}
+{"current_steps": 110, "total_steps": 1548, "loss": 0.5956, "learning_rate": 2e-06, "epoch": 0.2131782945736434, "percentage": 7.11, "elapsed_time": "0:25:48", "remaining_time": "5:37:26"}
+{"current_steps": 120, "total_steps": 1548, "loss": 0.587, "learning_rate": 2e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:28:11", "remaining_time": "5:35:25"}
+{"current_steps": 130, "total_steps": 1548, "loss": 0.5969, "learning_rate": 2e-06, "epoch": 0.25193798449612403, "percentage": 8.4, "elapsed_time": "0:30:33", "remaining_time": "5:33:24"}
+{"current_steps": 140, "total_steps": 1548, "loss": 0.5835, "learning_rate": 2e-06, "epoch": 0.2713178294573643, "percentage": 9.04, "elapsed_time": "0:32:57", "remaining_time": "5:31:23"}
+{"current_steps": 150, "total_steps": 1548, "loss": 0.5835, "learning_rate": 2e-06, "epoch": 0.29069767441860467, "percentage": 9.69, "elapsed_time": "0:35:19", "remaining_time": "5:29:13"}
+{"current_steps": 160, "total_steps": 1548, "loss": 0.5818, "learning_rate": 2e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:37:43", "remaining_time": "5:27:12"}
+{"current_steps": 170, "total_steps": 1548, "loss": 0.5766, "learning_rate": 2e-06, "epoch": 0.32945736434108525, "percentage": 10.98, "elapsed_time": "0:40:06", "remaining_time": "5:25:03"}
+{"current_steps": 180, "total_steps": 1548, "loss": 0.581, "learning_rate": 2e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:42:29", "remaining_time": "5:22:53"}
+{"current_steps": 190, "total_steps": 1548, "loss": 0.5743, "learning_rate": 2e-06, "epoch": 0.3682170542635659, "percentage": 12.27, "elapsed_time": "0:44:51", "remaining_time": "5:20:36"}
+{"current_steps": 200, "total_steps": 1548, "loss": 0.5818, "learning_rate": 2e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:47:14", "remaining_time": "5:18:24"}
+{"current_steps": 210, "total_steps": 1548, "loss": 0.5794, "learning_rate": 2e-06, "epoch": 0.4069767441860465, "percentage": 13.57, "elapsed_time": "0:49:37", "remaining_time": "5:16:09"}
+{"current_steps": 220, "total_steps": 1548, "loss": 0.568, "learning_rate": 2e-06, "epoch": 0.4263565891472868, "percentage": 14.21, "elapsed_time": "0:52:00", "remaining_time": "5:13:54"}
+{"current_steps": 230, "total_steps": 1548, "loss": 0.5663, "learning_rate": 2e-06, "epoch": 0.44573643410852715, "percentage": 14.86, "elapsed_time": "0:54:22", "remaining_time": "5:11:36"}
+{"current_steps": 240, "total_steps": 1548, "loss": 0.5701, "learning_rate": 2e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:56:44", "remaining_time": "5:09:15"}
+{"current_steps": 250, "total_steps": 1548, "loss": 0.5709, "learning_rate": 2e-06, "epoch": 0.4844961240310077, "percentage": 16.15, "elapsed_time": "0:59:07", "remaining_time": "5:06:56"}
+{"current_steps": 260, "total_steps": 1548, "loss": 0.5705, "learning_rate": 2e-06, "epoch": 0.5038759689922481, "percentage": 16.8, "elapsed_time": "1:01:30", "remaining_time": "5:04:41"}
+{"current_steps": 270, "total_steps": 1548, "loss": 0.5712, "learning_rate": 2e-06, "epoch": 0.5232558139534884, "percentage": 17.44, "elapsed_time": "1:03:55", "remaining_time": "5:02:32"}
+{"current_steps": 280, "total_steps": 1548, "loss": 0.5666, "learning_rate": 2e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "1:06:18", "remaining_time": "5:00:16"}
+{"current_steps": 290, "total_steps": 1548, "loss": 0.5689, "learning_rate": 2e-06, "epoch": 0.562015503875969, "percentage": 18.73, "elapsed_time": "1:08:41", "remaining_time": "4:57:59"}
+{"current_steps": 300, "total_steps": 1548, "loss": 0.5771, "learning_rate": 2e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "1:11:04", "remaining_time": "4:55:41"}
+{"current_steps": 310, "total_steps": 1548, "loss": 0.5641, "learning_rate": 2e-06, "epoch": 0.6007751937984496, "percentage": 20.03, "elapsed_time": "1:13:28", "remaining_time": "4:53:23"}
+{"current_steps": 320, "total_steps": 1548, "loss": 0.5615, "learning_rate": 2e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "1:15:50", "remaining_time": "4:51:03"}
+{"current_steps": 330, "total_steps": 1548, "loss": 0.5632, "learning_rate": 2e-06, "epoch": 0.6395348837209303, "percentage": 21.32, "elapsed_time": "1:18:13", "remaining_time": "4:48:43"}
+{"current_steps": 340, "total_steps": 1548, "loss": 0.5592, "learning_rate": 2e-06, "epoch": 0.6589147286821705, "percentage": 21.96, "elapsed_time": "1:20:35", "remaining_time": "4:46:21"}
+{"current_steps": 350, "total_steps": 1548, "loss": 0.5563, "learning_rate": 2e-06, "epoch": 0.6782945736434108, "percentage": 22.61, "elapsed_time": "1:22:59", "remaining_time": "4:44:04"}
+{"current_steps": 360, "total_steps": 1548, "loss": 0.5611, "learning_rate": 2e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "1:25:22", "remaining_time": "4:41:45"}
+{"current_steps": 370, "total_steps": 1548, "loss": 0.5665, "learning_rate": 2e-06, "epoch": 0.7170542635658915, "percentage": 23.9, "elapsed_time": "1:27:46", "remaining_time": "4:39:26"}
+{"current_steps": 380, "total_steps": 1548, "loss": 0.5672, "learning_rate": 2e-06, "epoch": 0.7364341085271318, "percentage": 24.55, "elapsed_time": "1:30:09", "remaining_time": "4:37:06"}
+{"current_steps": 390, "total_steps": 1548, "loss": 0.5566, "learning_rate": 2e-06, "epoch": 0.7558139534883721, "percentage": 25.19, "elapsed_time": "1:32:33", "remaining_time": "4:34:49"}
+{"current_steps": 400, "total_steps": 1548, "loss": 0.5576, "learning_rate": 2e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "1:34:56", "remaining_time": "4:32:28"}
+{"current_steps": 410, "total_steps": 1548, "loss": 0.5629, "learning_rate": 2e-06, "epoch": 0.7945736434108527, "percentage": 26.49, "elapsed_time": "1:37:19", "remaining_time": "4:30:08"}
+{"current_steps": 420, "total_steps": 1548, "loss": 0.5579, "learning_rate": 2e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "1:39:42", "remaining_time": "4:27:48"}
+{"current_steps": 430, "total_steps": 1548, "loss": 0.561, "learning_rate": 2e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "1:42:05", "remaining_time": "4:25:26"}
+{"current_steps": 440, "total_steps": 1548, "loss": 0.5593, "learning_rate": 2e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "1:44:29", "remaining_time": "4:23:07"}
+{"current_steps": 450, "total_steps": 1548, "loss": 0.563, "learning_rate": 2e-06, "epoch": 0.872093023255814, "percentage": 29.07, "elapsed_time": "1:46:52", "remaining_time": "4:20:45"}
+{"current_steps": 460, "total_steps": 1548, "loss": 0.5518, "learning_rate": 2e-06, "epoch": 0.8914728682170543, "percentage": 29.72, "elapsed_time": "1:49:15", "remaining_time": "4:18:24"}
+{"current_steps": 470, "total_steps": 1548, "loss": 0.5581, "learning_rate": 2e-06, "epoch": 0.9108527131782945, "percentage": 30.36, "elapsed_time": "1:51:37", "remaining_time": "4:16:01"}
+{"current_steps": 480, "total_steps": 1548, "loss": 0.5586, "learning_rate": 2e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "1:54:14", "remaining_time": "4:14:11"}
+{"current_steps": 490, "total_steps": 1548, "loss": 0.552, "learning_rate": 2e-06, "epoch": 0.9496124031007752, "percentage": 31.65, "elapsed_time": "1:56:37", "remaining_time": "4:11:48"}
+{"current_steps": 500, "total_steps": 1548, "loss": 0.5529, "learning_rate": 2e-06, "epoch": 0.9689922480620154, "percentage": 32.3, "elapsed_time": "1:58:59", "remaining_time": "4:09:25"}
+{"current_steps": 510, "total_steps": 1548, "loss": 0.5575, "learning_rate": 2e-06, "epoch": 0.9883720930232558, "percentage": 32.95, "elapsed_time": "2:01:22", "remaining_time": "4:07:02"}
+{"current_steps": 520, "total_steps": 1548, "loss": 0.5363, "learning_rate": 2e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "2:04:04", "remaining_time": "4:05:17"}
+{"current_steps": 530, "total_steps": 1548, "loss": 0.5103, "learning_rate": 2e-06, "epoch": 1.0271317829457365, "percentage": 34.24, "elapsed_time": "2:06:28", "remaining_time": "4:02:54"}
+{"current_steps": 540, "total_steps": 1548, "loss": 0.5083, "learning_rate": 2e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "2:08:50", "remaining_time": "4:00:30"}
+{"current_steps": 550, "total_steps": 1548, "loss": 0.5059, "learning_rate": 2e-06, "epoch": 1.0658914728682172, "percentage": 35.53, "elapsed_time": "2:11:13", "remaining_time": "3:58:06"}
+{"current_steps": 560, "total_steps": 1548, "loss": 0.5169, "learning_rate": 2e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "2:13:36", "remaining_time": "3:55:42"}
+{"current_steps": 570, "total_steps": 1548, "loss": 0.5102, "learning_rate": 2e-06, "epoch": 1.1046511627906976, "percentage": 36.82, "elapsed_time": "2:15:58", "remaining_time": "3:53:18"}
+{"current_steps": 580, "total_steps": 1548, "loss": 0.5044, "learning_rate": 2e-06, "epoch": 1.124031007751938, "percentage": 37.47, "elapsed_time": "2:18:32", "remaining_time": "3:51:12"}
+{"current_steps": 590, "total_steps": 1548, "loss": 0.5036, "learning_rate": 2e-06, "epoch": 1.1434108527131783, "percentage": 38.11, "elapsed_time": "2:20:55", "remaining_time": "3:48:49"}
+{"current_steps": 600, "total_steps": 1548, "loss": 0.5037, "learning_rate": 2e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "2:23:17", "remaining_time": "3:46:24"}
+{"current_steps": 610, "total_steps": 1548, "loss": 0.5135, "learning_rate": 2e-06, "epoch": 1.1821705426356588, "percentage": 39.41, "elapsed_time": "2:25:40", "remaining_time": "3:43:59"}
+{"current_steps": 620, "total_steps": 1548, "loss": 0.5078, "learning_rate": 2e-06, "epoch": 1.2015503875968991, "percentage": 40.05, "elapsed_time": "2:28:03", "remaining_time": "3:41:35"}
+{"current_steps": 630, "total_steps": 1548, "loss": 0.5078, "learning_rate": 2e-06, "epoch": 1.2209302325581395, "percentage": 40.7, "elapsed_time": "2:30:26", "remaining_time": "3:39:12"}
+{"current_steps": 640, "total_steps": 1548, "loss": 0.5088, "learning_rate": 2e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "2:32:48", "remaining_time": "3:36:48"}
+{"current_steps": 650, "total_steps": 1548, "loss": 0.5098, "learning_rate": 2e-06, "epoch": 1.2596899224806202, "percentage": 41.99, "elapsed_time": "2:35:11", "remaining_time": "3:34:24"}
+{"current_steps": 660, "total_steps": 1548, "loss": 0.5067, "learning_rate": 2e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "2:37:34", "remaining_time": "3:32:00"}
+{"current_steps": 670, "total_steps": 1548, "loss": 0.5122, "learning_rate": 2e-06, "epoch": 1.2984496124031009, "percentage": 43.28, "elapsed_time": "2:39:57", "remaining_time": "3:29:36"}
+{"current_steps": 680, "total_steps": 1548, "loss": 0.5121, "learning_rate": 2e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "2:42:20", "remaining_time": "3:27:13"}
+{"current_steps": 690, "total_steps": 1548, "loss": 0.5088, "learning_rate": 2e-06, "epoch": 1.3372093023255813, "percentage": 44.57, "elapsed_time": "2:44:42", "remaining_time": "3:24:48"}
+{"current_steps": 700, "total_steps": 1548, "loss": 0.5099, "learning_rate": 2e-06, "epoch": 1.3565891472868217, "percentage": 45.22, "elapsed_time": "2:47:05", "remaining_time": "3:22:24"}
+{"current_steps": 710, "total_steps": 1548, "loss": 0.5136, "learning_rate": 2e-06, "epoch": 1.375968992248062, "percentage": 45.87, "elapsed_time": "2:49:27", "remaining_time": "3:20:00"}
+{"current_steps": 720, "total_steps": 1548, "loss": 0.513, "learning_rate": 2e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "2:51:50", "remaining_time": "3:17:36"}
+{"current_steps": 730, "total_steps": 1548, "loss": 0.5087, "learning_rate": 2e-06, "epoch": 1.4147286821705427, "percentage": 47.16, "elapsed_time": "2:54:13", "remaining_time": "3:15:13"}
+{"current_steps": 740, "total_steps": 1548, "loss": 0.5148, "learning_rate": 2e-06, "epoch": 1.4341085271317828, "percentage": 47.8, "elapsed_time": "2:56:35", "remaining_time": "3:12:49"}
+{"current_steps": 750, "total_steps": 1548, "loss": 0.5101, "learning_rate": 2e-06, "epoch": 1.4534883720930232, "percentage": 48.45, "elapsed_time": "2:58:58", "remaining_time": "3:10:25"}
+{"current_steps": 760, "total_steps": 1548, "loss": 0.5075, "learning_rate": 2e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "3:01:22", "remaining_time": "3:08:03"}
+{"current_steps": 770, "total_steps": 1548, "loss": 0.5111, "learning_rate": 2e-06, "epoch": 1.4922480620155039, "percentage": 49.74, "elapsed_time": "3:03:46", "remaining_time": "3:05:40"}
+{"current_steps": 780, "total_steps": 1548, "loss": 0.5136, "learning_rate": 2e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "3:06:11", "remaining_time": "3:03:19"}
+{"current_steps": 790, "total_steps": 1548, "loss": 0.5107, "learning_rate": 2e-06, "epoch": 1.5310077519379846, "percentage": 51.03, "elapsed_time": "3:08:36", "remaining_time": "3:00:58"}
+{"current_steps": 800, "total_steps": 1548, "loss": 0.5076, "learning_rate": 2e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "3:11:01", "remaining_time": "2:58:36"}
+{"current_steps": 810, "total_steps": 1548, "loss": 0.5059, "learning_rate": 2e-06, "epoch": 1.5697674418604652, "percentage": 52.33, "elapsed_time": "3:13:26", "remaining_time": "2:56:14"}
+{"current_steps": 820, "total_steps": 1548, "loss": 0.5047, "learning_rate": 2e-06, "epoch": 1.5891472868217056, "percentage": 52.97, "elapsed_time": "3:15:51", "remaining_time": "2:53:53"}
+{"current_steps": 830, "total_steps": 1548, "loss": 0.5126, "learning_rate": 2e-06, "epoch": 1.6085271317829457, "percentage": 53.62, "elapsed_time": "3:18:16", "remaining_time": "2:51:31"}
+{"current_steps": 840, "total_steps": 1548, "loss": 0.5072, "learning_rate": 2e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "3:20:40", "remaining_time": "2:49:08"}
+{"current_steps": 850, "total_steps": 1548, "loss": 0.5119, "learning_rate": 2e-06, "epoch": 1.6472868217054264, "percentage": 54.91, "elapsed_time": "3:23:04", "remaining_time": "2:46:45"}
+{"current_steps": 860, "total_steps": 1548, "loss": 0.5143, "learning_rate": 2e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "3:25:30", "remaining_time": "2:44:24"}
+{"current_steps": 870, "total_steps": 1548, "loss": 0.5065, "learning_rate": 2e-06, "epoch": 1.6860465116279069, "percentage": 56.2, "elapsed_time": "3:27:54", "remaining_time": "2:42:01"}
+{"current_steps": 880, "total_steps": 1548, "loss": 0.5112, "learning_rate": 2e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "3:30:18", "remaining_time": "2:39:38"}
+{"current_steps": 890, "total_steps": 1548, "loss": 0.5105, "learning_rate": 2e-06, "epoch": 1.7248062015503876, "percentage": 57.49, "elapsed_time": "3:32:56", "remaining_time": "2:37:26"}
+{"current_steps": 900, "total_steps": 1548, "loss": 0.5145, "learning_rate": 2e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "3:35:19", "remaining_time": "2:35:02"}
+{"current_steps": 910, "total_steps": 1548, "loss": 0.5064, "learning_rate": 2e-06, "epoch": 1.7635658914728682, "percentage": 58.79, "elapsed_time": "3:37:42", "remaining_time": "2:32:37"}
+{"current_steps": 920, "total_steps": 1548, "loss": 0.5092, "learning_rate": 2e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "3:40:04", "remaining_time": "2:30:13"}
+{"current_steps": 930, "total_steps": 1548, "loss": 0.5102, "learning_rate": 2e-06, "epoch": 1.802325581395349, "percentage": 60.08, "elapsed_time": "3:42:27", "remaining_time": "2:27:49"}
+{"current_steps": 940, "total_steps": 1548, "loss": 0.5084, "learning_rate": 2e-06, "epoch": 1.8217054263565893, "percentage": 60.72, "elapsed_time": "3:44:50", "remaining_time": "2:25:26"}
+{"current_steps": 950, "total_steps": 1548, "loss": 0.5109, "learning_rate": 2e-06, "epoch": 1.8410852713178296, "percentage": 61.37, "elapsed_time": "3:47:14", "remaining_time": "2:23:02"}
+{"current_steps": 960, "total_steps": 1548, "loss": 0.5129, "learning_rate": 2e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "3:49:37", "remaining_time": "2:20:38"}
+{"current_steps": 970, "total_steps": 1548, "loss": 0.5102, "learning_rate": 2e-06, "epoch": 1.87984496124031, "percentage": 62.66, "elapsed_time": "3:51:59", "remaining_time": "2:18:14"}
+{"current_steps": 980, "total_steps": 1548, "loss": 0.5063, "learning_rate": 2e-06, "epoch": 1.8992248062015504, "percentage": 63.31, "elapsed_time": "3:54:22", "remaining_time": "2:15:50"}
+{"current_steps": 990, "total_steps": 1548, "loss": 0.5125, "learning_rate": 2e-06, "epoch": 1.9186046511627906, "percentage": 63.95, "elapsed_time": "3:56:45", "remaining_time": "2:13:26"}
+{"current_steps": 1000, "total_steps": 1548, "loss": 0.5098, "learning_rate": 2e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "3:59:07", "remaining_time": "2:11:02"}
+{"current_steps": 1010, "total_steps": 1548, "loss": 0.5111, "learning_rate": 2e-06, "epoch": 1.9573643410852712, "percentage": 65.25, "elapsed_time": "4:01:31", "remaining_time": "2:08:39"}
+{"current_steps": 1020, "total_steps": 1548, "loss": 0.5064, "learning_rate": 2e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "4:03:54", "remaining_time": "2:06:15"}
+{"current_steps": 1030, "total_steps": 1548, "loss": 0.5104, "learning_rate": 2e-06, "epoch": 1.996124031007752, "percentage": 66.54, "elapsed_time": "4:06:16", "remaining_time": "2:03:51"}
+{"current_steps": 1040, "total_steps": 1548, "loss": 0.4698, "learning_rate": 2e-06, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "4:08:58", "remaining_time": "2:01:36"}
+{"current_steps": 1050, "total_steps": 1548, "loss": 0.4592, "learning_rate": 2e-06, "epoch": 2.0348837209302326, "percentage": 67.83, "elapsed_time": "4:11:20", "remaining_time": "1:59:12"}
+{"current_steps": 1060, "total_steps": 1548, "loss": 0.458, "learning_rate": 2e-06, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "4:13:42", "remaining_time": "1:56:48"}
+{"current_steps": 1070, "total_steps": 1548, "loss": 0.4595, "learning_rate": 2e-06, "epoch": 2.0736434108527133, "percentage": 69.12, "elapsed_time": "4:16:05", "remaining_time": "1:54:24"}
+{"current_steps": 1080, "total_steps": 1548, "loss": 0.4544, "learning_rate": 2e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "4:18:28", "remaining_time": "1:52:00"}
+{"current_steps": 1090, "total_steps": 1548, "loss": 0.4575, "learning_rate": 2e-06, "epoch": 2.112403100775194, "percentage": 70.41, "elapsed_time": "4:20:50", "remaining_time": "1:49:36"}
+{"current_steps": 1100, "total_steps": 1548, "loss": 0.4574, "learning_rate": 2e-06, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "4:23:12", "remaining_time": "1:47:11"}
+{"current_steps": 1110, "total_steps": 1548, "loss": 0.4604, "learning_rate": 2e-06, "epoch": 2.1511627906976742, "percentage": 71.71, "elapsed_time": "4:25:34", "remaining_time": "1:44:47"}
+{"current_steps": 1120, "total_steps": 1548, "loss": 0.4622, "learning_rate": 2e-06, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "4:27:56", "remaining_time": "1:42:23"}
+{"current_steps": 1130, "total_steps": 1548, "loss": 0.4592, "learning_rate": 2e-06, "epoch": 2.189922480620155, "percentage": 73.0, "elapsed_time": "4:30:18", "remaining_time": "1:39:59"}
+{"current_steps": 1140, "total_steps": 1548, "loss": 0.4572, "learning_rate": 2e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "4:32:40", "remaining_time": "1:37:35"}
+{"current_steps": 1150, "total_steps": 1548, "loss": 0.4596, "learning_rate": 2e-06, "epoch": 2.2286821705426356, "percentage": 74.29, "elapsed_time": "4:35:03", "remaining_time": "1:35:11"}
+{"current_steps": 1160, "total_steps": 1548, "loss": 0.4576, "learning_rate": 2e-06, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "4:37:25", "remaining_time": "1:32:47"}
+{"current_steps": 1170, "total_steps": 1548, "loss": 0.4584, "learning_rate": 2e-06, "epoch": 2.2674418604651163, "percentage": 75.58, "elapsed_time": "4:39:48", "remaining_time": "1:30:23"}
+{"current_steps": 1180, "total_steps": 1548, "loss": 0.4654, "learning_rate": 2e-06, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "4:42:10", "remaining_time": "1:28:00"}
+{"current_steps": 1190, "total_steps": 1548, "loss": 0.4606, "learning_rate": 2e-06, "epoch": 2.306201550387597, "percentage": 76.87, "elapsed_time": "4:44:32", "remaining_time": "1:25:36"}
+{"current_steps": 1200, "total_steps": 1548, "loss": 0.4569, "learning_rate": 2e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "4:46:56", "remaining_time": "1:23:12"}
+{"current_steps": 1210, "total_steps": 1548, "loss": 0.461, "learning_rate": 2e-06, "epoch": 2.3449612403100777, "percentage": 78.17, "elapsed_time": "4:49:18", "remaining_time": "1:20:48"}
+{"current_steps": 1220, "total_steps": 1548, "loss": 0.4646, "learning_rate": 2e-06, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "4:51:40", "remaining_time": "1:18:25"}
+{"current_steps": 1230, "total_steps": 1548, "loss": 0.4598, "learning_rate": 2e-06, "epoch": 2.383720930232558, "percentage": 79.46, "elapsed_time": "4:54:02", "remaining_time": "1:16:01"}
+{"current_steps": 1240, "total_steps": 1548, "loss": 0.4659, "learning_rate": 2e-06, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "4:56:24", "remaining_time": "1:13:37"}
+{"current_steps": 1250, "total_steps": 1548, "loss": 0.4606, "learning_rate": 2e-06, "epoch": 2.4224806201550386, "percentage": 80.75, "elapsed_time": "4:58:47", "remaining_time": "1:11:13"}
+{"current_steps": 1260, "total_steps": 1548, "loss": 0.4629, "learning_rate": 2e-06, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "5:01:09", "remaining_time": "1:08:50"}
+{"current_steps": 1270, "total_steps": 1548, "loss": 0.4643, "learning_rate": 2e-06, "epoch": 2.4612403100775193, "percentage": 82.04, "elapsed_time": "5:03:32", "remaining_time": "1:06:26"}
+{"current_steps": 1280, "total_steps": 1548, "loss": 0.4647, "learning_rate": 2e-06, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "5:05:54", "remaining_time": "1:04:02"}
+{"current_steps": 1290, "total_steps": 1548, "loss": 0.458, "learning_rate": 2e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:08:16", "remaining_time": "1:01:39"}
+{"current_steps": 1300, "total_steps": 1548, "loss": 0.4651, "learning_rate": 2e-06, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "5:10:39", "remaining_time": "0:59:15"}
+{"current_steps": 1310, "total_steps": 1548, "loss": 0.4584, "learning_rate": 2e-06, "epoch": 2.5387596899224807, "percentage": 84.63, "elapsed_time": "5:13:02", "remaining_time": "0:56:52"}
+{"current_steps": 1320, "total_steps": 1548, "loss": 0.4707, "learning_rate": 2e-06, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "5:15:25", "remaining_time": "0:54:28"}
+{"current_steps": 1330, "total_steps": 1548, "loss": 0.4628, "learning_rate": 2e-06, "epoch": 2.5775193798449614, "percentage": 85.92, "elapsed_time": "5:17:47", "remaining_time": "0:52:05"}
+{"current_steps": 1340, "total_steps": 1548, "loss": 0.4716, "learning_rate": 2e-06, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "5:20:10", "remaining_time": "0:49:41"}
+{"current_steps": 1350, "total_steps": 1548, "loss": 0.4629, "learning_rate": 2e-06, "epoch": 2.616279069767442, "percentage": 87.21, "elapsed_time": "5:22:32", "remaining_time": "0:47:18"}
+{"current_steps": 1360, "total_steps": 1548, "loss": 0.4595, "learning_rate": 2e-06, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "5:24:55", "remaining_time": "0:44:55"}
+{"current_steps": 1370, "total_steps": 1548, "loss": 0.4605, "learning_rate": 2e-06, "epoch": 2.6550387596899228, "percentage": 88.5, "elapsed_time": "5:27:19", "remaining_time": "0:42:31"}
+{"current_steps": 1380, "total_steps": 1548, "loss": 0.4687, "learning_rate": 2e-06, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "5:29:41", "remaining_time": "0:40:08"}
+{"current_steps": 1390, "total_steps": 1548, "loss": 0.4603, "learning_rate": 2e-06, "epoch": 2.693798449612403, "percentage": 89.79, "elapsed_time": "5:32:03", "remaining_time": "0:37:44"}
+{"current_steps": 1400, "total_steps": 1548, "loss": 0.4683, "learning_rate": 2e-06, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "5:34:25", "remaining_time": "0:35:21"}
+{"current_steps": 1410, "total_steps": 1548, "loss": 0.4601, "learning_rate": 2e-06, "epoch": 2.7325581395348837, "percentage": 91.09, "elapsed_time": "5:36:48", "remaining_time": "0:32:57"}
+{"current_steps": 1420, "total_steps": 1548, "loss": 0.4617, "learning_rate": 2e-06, "epoch": 2.751937984496124, "percentage": 91.73, "elapsed_time": "5:39:10", "remaining_time": "0:30:34"}
+{"current_steps": 1430, "total_steps": 1548, "loss": 0.4671, "learning_rate": 2e-06, "epoch": 2.7713178294573644, "percentage": 92.38, "elapsed_time": "5:41:33", "remaining_time": "0:28:11"}
+{"current_steps": 1440, "total_steps": 1548, "loss": 0.466, "learning_rate": 2e-06, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "5:43:55", "remaining_time": "0:25:47"}
+{"current_steps": 1450, "total_steps": 1548, "loss": 0.4637, "learning_rate": 2e-06, "epoch": 2.810077519379845, "percentage": 93.67, "elapsed_time": "5:46:18", "remaining_time": "0:23:24"}
+{"current_steps": 1460, "total_steps": 1548, "loss": 0.4707, "learning_rate": 2e-06, "epoch": 2.8294573643410854, "percentage": 94.32, "elapsed_time": "5:48:41", "remaining_time": "0:21:00"}
+{"current_steps": 1470, "total_steps": 1548, "loss": 0.4666, "learning_rate": 2e-06, "epoch": 2.8488372093023253, "percentage": 94.96, "elapsed_time": "5:51:03", "remaining_time": "0:18:37"}
+{"current_steps": 1480, "total_steps": 1548, "loss": 0.467, "learning_rate": 2e-06, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "5:53:26", "remaining_time": "0:16:14"}
+{"current_steps": 1490, "total_steps": 1548, "loss": 0.4699, "learning_rate": 2e-06, "epoch": 2.887596899224806, "percentage": 96.25, "elapsed_time": "5:55:48", "remaining_time": "0:13:51"}
+{"current_steps": 1500, "total_steps": 1548, "loss": 0.4592, "learning_rate": 2e-06, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "5:58:11", "remaining_time": "0:11:27"}
+{"current_steps": 1510, "total_steps": 1548, "loss": 0.4633, "learning_rate": 2e-06, "epoch": 2.9263565891472867, "percentage": 97.55, "elapsed_time": "6:00:33", "remaining_time": "0:09:04"}
+{"current_steps": 1520, "total_steps": 1548, "loss": 0.4684, "learning_rate": 2e-06, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "6:02:55", "remaining_time": "0:06:41"}
+{"current_steps": 1530, "total_steps": 1548, "loss": 0.4635, "learning_rate": 2e-06, "epoch": 2.9651162790697674, "percentage": 98.84, "elapsed_time": "6:05:17", "remaining_time": "0:04:17"}
+{"current_steps": 1540, "total_steps": 1548, "loss": 0.4687, "learning_rate": 2e-06, "epoch": 2.9844961240310077, "percentage": 99.48, "elapsed_time": "6:07:39", "remaining_time": "0:01:54"}
+{"current_steps": 1548, "total_steps": 1548, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:10:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1120 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1548,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01937984496124031,
+      "grad_norm": 3.144579840345173,
+      "learning_rate": 2e-06,
+      "loss": 0.7225,
+      "step": 10
+    },
+    {
+      "epoch": 0.03875968992248062,
+      "grad_norm": 1.4635286655772066,
+      "learning_rate": 2e-06,
+      "loss": 0.6518,
+      "step": 20
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "grad_norm": 1.3391923941713981,
+      "learning_rate": 2e-06,
+      "loss": 0.6267,
+      "step": 30
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 1.6579265991584125,
+      "learning_rate": 2e-06,
+      "loss": 0.6192,
+      "step": 40
+    },
+    {
+      "epoch": 0.09689922480620156,
+      "grad_norm": 1.4605383147970585,
+      "learning_rate": 2e-06,
+      "loss": 0.6139,
+      "step": 50
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 3.0164024994264924,
+      "learning_rate": 2e-06,
+      "loss": 0.6069,
+      "step": 60
+    },
+    {
+      "epoch": 0.13565891472868216,
+      "grad_norm": 3.0735559741358043,
+      "learning_rate": 2e-06,
+      "loss": 0.6026,
+      "step": 70
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 2.179805880693448,
+      "learning_rate": 2e-06,
+      "loss": 0.6052,
+      "step": 80
+    },
+    {
+      "epoch": 0.1744186046511628,
+      "grad_norm": 1.362604075543814,
+      "learning_rate": 2e-06,
+      "loss": 0.5906,
+      "step": 90
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 1.3800184946057543,
+      "learning_rate": 2e-06,
+      "loss": 0.5926,
+      "step": 100
+    },
+    {
+      "epoch": 0.2131782945736434,
+      "grad_norm": 1.5751853135874878,
+      "learning_rate": 2e-06,
+      "loss": 0.5956,
+      "step": 110
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.3581579120999256,
+      "learning_rate": 2e-06,
+      "loss": 0.587,
+      "step": 120
+    },
+    {
+      "epoch": 0.25193798449612403,
+      "grad_norm": 1.4725915485732346,
+      "learning_rate": 2e-06,
+      "loss": 0.5969,
+      "step": 130
+    },
+    {
+      "epoch": 0.2713178294573643,
+      "grad_norm": 2.3468819417923297,
+      "learning_rate": 2e-06,
+      "loss": 0.5835,
+      "step": 140
+    },
+    {
+      "epoch": 0.29069767441860467,
+      "grad_norm": 1.7250281157703675,
+      "learning_rate": 2e-06,
+      "loss": 0.5835,
+      "step": 150
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.697210370789681,
+      "learning_rate": 2e-06,
+      "loss": 0.5818,
+      "step": 160
+    },
+    {
+      "epoch": 0.32945736434108525,
+      "grad_norm": 1.4878874477377635,
+      "learning_rate": 2e-06,
+      "loss": 0.5766,
+      "step": 170
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 1.4577800027661107,
+      "learning_rate": 2e-06,
+      "loss": 0.581,
+      "step": 180
+    },
+    {
+      "epoch": 0.3682170542635659,
+      "grad_norm": 1.5593039073057922,
+      "learning_rate": 2e-06,
+      "loss": 0.5743,
+      "step": 190
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 1.5848277223563478,
+      "learning_rate": 2e-06,
+      "loss": 0.5818,
+      "step": 200
+    },
+    {
+      "epoch": 0.4069767441860465,
+      "grad_norm": 1.8749305561105472,
+      "learning_rate": 2e-06,
+      "loss": 0.5794,
+      "step": 210
+    },
+    {
+      "epoch": 0.4263565891472868,
+      "grad_norm": 1.9776238010410143,
+      "learning_rate": 2e-06,
+      "loss": 0.568,
+      "step": 220
+    },
+    {
+      "epoch": 0.44573643410852715,
+      "grad_norm": 1.8367468157602185,
+      "learning_rate": 2e-06,
+      "loss": 0.5663,
+      "step": 230
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.4796763755300497,
+      "learning_rate": 2e-06,
+      "loss": 0.5701,
+      "step": 240
+    },
+    {
+      "epoch": 0.4844961240310077,
+      "grad_norm": 1.3277578070972216,
+      "learning_rate": 2e-06,
+      "loss": 0.5709,
+      "step": 250
+    },
+    {
+      "epoch": 0.5038759689922481,
+      "grad_norm": 1.3619348918199545,
+      "learning_rate": 2e-06,
+      "loss": 0.5705,
+      "step": 260
+    },
+    {
+      "epoch": 0.5232558139534884,
+      "grad_norm": 1.3242792342849865,
+      "learning_rate": 2e-06,
+      "loss": 0.5712,
+      "step": 270
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.208195333886979,
+      "learning_rate": 2e-06,
+      "loss": 0.5666,
+      "step": 280
+    },
+    {
+      "epoch": 0.562015503875969,
+      "grad_norm": 1.2067351750756312,
+      "learning_rate": 2e-06,
+      "loss": 0.5689,
+      "step": 290
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 1.4904068289049572,
+      "learning_rate": 2e-06,
+      "loss": 0.5771,
+      "step": 300
+    },
+    {
+      "epoch": 0.6007751937984496,
+      "grad_norm": 1.2308496450990478,
+      "learning_rate": 2e-06,
+      "loss": 0.5641,
+      "step": 310
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.646171689094913,
+      "learning_rate": 2e-06,
+      "loss": 0.5615,
+      "step": 320
+    },
+    {
+      "epoch": 0.6395348837209303,
+      "grad_norm": 1.486911287484255,
+      "learning_rate": 2e-06,
+      "loss": 0.5632,
+      "step": 330
+    },
+    {
+      "epoch": 0.6589147286821705,
+      "grad_norm": 1.367582942415251,
+      "learning_rate": 2e-06,
+      "loss": 0.5592,
+      "step": 340
+    },
+    {
+      "epoch": 0.6782945736434108,
+      "grad_norm": 1.6042437679665664,
+      "learning_rate": 2e-06,
+      "loss": 0.5563,
+      "step": 350
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.3440772301905874,
+      "learning_rate": 2e-06,
+      "loss": 0.5611,
+      "step": 360
+    },
+    {
+      "epoch": 0.7170542635658915,
+      "grad_norm": 1.5512652472297026,
+      "learning_rate": 2e-06,
+      "loss": 0.5665,
+      "step": 370
+    },
+    {
+      "epoch": 0.7364341085271318,
+      "grad_norm": 1.2275175025786087,
+      "learning_rate": 2e-06,
+      "loss": 0.5672,
+      "step": 380
+    },
+    {
+      "epoch": 0.7558139534883721,
+      "grad_norm": 1.584906298076075,
+      "learning_rate": 2e-06,
+      "loss": 0.5566,
+      "step": 390
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.2472749697240508,
+      "learning_rate": 2e-06,
+      "loss": 0.5576,
+      "step": 400
+    },
+    {
+      "epoch": 0.7945736434108527,
+      "grad_norm": 1.3014141414308267,
+      "learning_rate": 2e-06,
+      "loss": 0.5629,
+      "step": 410
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.1170221459908387,
+      "learning_rate": 2e-06,
+      "loss": 0.5579,
+      "step": 420
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.2375437974864687,
+      "learning_rate": 2e-06,
+      "loss": 0.561,
+      "step": 430
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.2886237743320625,
+      "learning_rate": 2e-06,
+      "loss": 0.5593,
+      "step": 440
+    },
+    {
+      "epoch": 0.872093023255814,
+      "grad_norm": 1.2840806861492629,
+      "learning_rate": 2e-06,
+      "loss": 0.563,
+      "step": 450
+    },
+    {
+      "epoch": 0.8914728682170543,
+      "grad_norm": 1.1374554276601674,
+      "learning_rate": 2e-06,
+      "loss": 0.5518,
+      "step": 460
+    },
+    {
+      "epoch": 0.9108527131782945,
+      "grad_norm": 1.5460088934957399,
+      "learning_rate": 2e-06,
+      "loss": 0.5581,
+      "step": 470
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.3649006878214347,
+      "learning_rate": 2e-06,
+      "loss": 0.5586,
+      "step": 480
+    },
+    {
+      "epoch": 0.9496124031007752,
+      "grad_norm": 1.4127688073512672,
+      "learning_rate": 2e-06,
+      "loss": 0.552,
+      "step": 490
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 1.6637865739686932,
+      "learning_rate": 2e-06,
+      "loss": 0.5529,
+      "step": 500
+    },
+    {
+      "epoch": 0.9883720930232558,
+      "grad_norm": 1.1603715309408054,
+      "learning_rate": 2e-06,
+      "loss": 0.5575,
+      "step": 510
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 1.9471029922347483,
+      "learning_rate": 2e-06,
+      "loss": 0.5363,
+      "step": 520
+    },
+    {
+      "epoch": 1.0271317829457365,
+      "grad_norm": 1.501943317728709,
+      "learning_rate": 2e-06,
+      "loss": 0.5103,
+      "step": 530
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 2.210385554433354,
+      "learning_rate": 2e-06,
+      "loss": 0.5083,
+      "step": 540
+    },
+    {
+      "epoch": 1.0658914728682172,
+      "grad_norm": 1.4456437528958064,
+      "learning_rate": 2e-06,
+      "loss": 0.5059,
+      "step": 550
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.3747977066368522,
+      "learning_rate": 2e-06,
+      "loss": 0.5169,
+      "step": 560
+    },
+    {
+      "epoch": 1.1046511627906976,
+      "grad_norm": 1.3671143459062107,
+      "learning_rate": 2e-06,
+      "loss": 0.5102,
+      "step": 570
+    },
+    {
+      "epoch": 1.124031007751938,
+      "grad_norm": 1.6112053859893298,
+      "learning_rate": 2e-06,
+      "loss": 0.5044,
+      "step": 580
+    },
+    {
+      "epoch": 1.1434108527131783,
+      "grad_norm": 1.2311741203329047,
+      "learning_rate": 2e-06,
+      "loss": 0.5036,
+      "step": 590
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.2615707450710407,
+      "learning_rate": 2e-06,
+      "loss": 0.5037,
+      "step": 600
+    },
+    {
+      "epoch": 1.1821705426356588,
+      "grad_norm": 1.247560640905585,
+      "learning_rate": 2e-06,
+      "loss": 0.5135,
+      "step": 610
+    },
+    {
+      "epoch": 1.2015503875968991,
+      "grad_norm": 1.4713651285134284,
+      "learning_rate": 2e-06,
+      "loss": 0.5078,
+      "step": 620
+    },
+    {
+      "epoch": 1.2209302325581395,
+      "grad_norm": 1.8788503215188699,
+      "learning_rate": 2e-06,
+      "loss": 0.5078,
+      "step": 630
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.9570944633210832,
+      "learning_rate": 2e-06,
+      "loss": 0.5088,
+      "step": 640
+    },
+    {
+      "epoch": 1.2596899224806202,
+      "grad_norm": 1.519042994554157,
+      "learning_rate": 2e-06,
+      "loss": 0.5098,
+      "step": 650
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.7929648758582426,
+      "learning_rate": 2e-06,
+      "loss": 0.5067,
+      "step": 660
+    },
+    {
+      "epoch": 1.2984496124031009,
+      "grad_norm": 1.4987560500572878,
+      "learning_rate": 2e-06,
+      "loss": 0.5122,
+      "step": 670
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 1.2086756990648462,
+      "learning_rate": 2e-06,
+      "loss": 0.5121,
+      "step": 680
+    },
+    {
+      "epoch": 1.3372093023255813,
+      "grad_norm": 1.3866302425582229,
+      "learning_rate": 2e-06,
+      "loss": 0.5088,
+      "step": 690
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 1.4943167093290222,
+      "learning_rate": 2e-06,
+      "loss": 0.5099,
+      "step": 700
+    },
+    {
+      "epoch": 1.375968992248062,
+      "grad_norm": 1.4190704125897742,
+      "learning_rate": 2e-06,
+      "loss": 0.5136,
+      "step": 710
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.201854415277148,
+      "learning_rate": 2e-06,
+      "loss": 0.513,
+      "step": 720
+    },
+    {
+      "epoch": 1.4147286821705427,
+      "grad_norm": 1.5552807283991774,
+      "learning_rate": 2e-06,
+      "loss": 0.5087,
+      "step": 730
+    },
+    {
+      "epoch": 1.4341085271317828,
+      "grad_norm": 1.2711570348118688,
+      "learning_rate": 2e-06,
+      "loss": 0.5148,
+      "step": 740
+    },
+    {
+      "epoch": 1.4534883720930232,
+      "grad_norm": 1.5027858680147197,
+      "learning_rate": 2e-06,
+      "loss": 0.5101,
+      "step": 750
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 1.3009800268853209,
+      "learning_rate": 2e-06,
+      "loss": 0.5075,
+      "step": 760
+    },
+    {
+      "epoch": 1.4922480620155039,
+      "grad_norm": 1.195133004986583,
+      "learning_rate": 2e-06,
+      "loss": 0.5111,
+      "step": 770
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.3544355872789209,
+      "learning_rate": 2e-06,
+      "loss": 0.5136,
+      "step": 780
+    },
+    {
+      "epoch": 1.5310077519379846,
+      "grad_norm": 1.22732892168229,
+      "learning_rate": 2e-06,
+      "loss": 0.5107,
+      "step": 790
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 1.2500964364741391,
+      "learning_rate": 2e-06,
+      "loss": 0.5076,
+      "step": 800
+    },
+    {
+      "epoch": 1.5697674418604652,
+      "grad_norm": 1.2443445799817128,
+      "learning_rate": 2e-06,
+      "loss": 0.5059,
+      "step": 810
+    },
+    {
+      "epoch": 1.5891472868217056,
+      "grad_norm": 1.3642427980887037,
+      "learning_rate": 2e-06,
+      "loss": 0.5047,
+      "step": 820
+    },
+    {
+      "epoch": 1.6085271317829457,
+      "grad_norm": 1.3132643052702235,
+      "learning_rate": 2e-06,
+      "loss": 0.5126,
+      "step": 830
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.245951139796731,
+      "learning_rate": 2e-06,
+      "loss": 0.5072,
+      "step": 840
+    },
+    {
+      "epoch": 1.6472868217054264,
+      "grad_norm": 1.151992957120151,
+      "learning_rate": 2e-06,
+      "loss": 0.5119,
+      "step": 850
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.44482076559048,
+      "learning_rate": 2e-06,
+      "loss": 0.5143,
+      "step": 860
+    },
+    {
+      "epoch": 1.6860465116279069,
+      "grad_norm": 1.2014633120651383,
+      "learning_rate": 2e-06,
+      "loss": 0.5065,
+      "step": 870
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 1.1421759011867347,
+      "learning_rate": 2e-06,
+      "loss": 0.5112,
+      "step": 880
+    },
+    {
+      "epoch": 1.7248062015503876,
+      "grad_norm": 1.3662761429999075,
+      "learning_rate": 2e-06,
+      "loss": 0.5105,
+      "step": 890
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 1.731081249332488,
+      "learning_rate": 2e-06,
+      "loss": 0.5145,
+      "step": 900
+    },
+    {
+      "epoch": 1.7635658914728682,
+      "grad_norm": 1.8386868390815672,
+      "learning_rate": 2e-06,
+      "loss": 0.5064,
+      "step": 910
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.945733381736797,
+      "learning_rate": 2e-06,
+      "loss": 0.5092,
+      "step": 920
+    },
+    {
+      "epoch": 1.802325581395349,
+      "grad_norm": 1.1658591371712888,
+      "learning_rate": 2e-06,
+      "loss": 0.5102,
+      "step": 930
+    },
+    {
+      "epoch": 1.8217054263565893,
+      "grad_norm": 1.2964175995286236,
+      "learning_rate": 2e-06,
+      "loss": 0.5084,
+      "step": 940
+    },
+    {
+      "epoch": 1.8410852713178296,
+      "grad_norm": 1.368071275379517,
+      "learning_rate": 2e-06,
+      "loss": 0.5109,
+      "step": 950
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.150103079484035,
+      "learning_rate": 2e-06,
+      "loss": 0.5129,
+      "step": 960
+    },
+    {
+      "epoch": 1.87984496124031,
+      "grad_norm": 1.741489344099722,
+      "learning_rate": 2e-06,
+      "loss": 0.5102,
+      "step": 970
+    },
+    {
+      "epoch": 1.8992248062015504,
+      "grad_norm": 1.4368003237003146,
+      "learning_rate": 2e-06,
+      "loss": 0.5063,
+      "step": 980
+    },
+    {
+      "epoch": 1.9186046511627906,
+      "grad_norm": 1.198714228722542,
+      "learning_rate": 2e-06,
+      "loss": 0.5125,
+      "step": 990
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 1.2050714331345398,
+      "learning_rate": 2e-06,
+      "loss": 0.5098,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9573643410852712,
+      "grad_norm": 1.2467265326889772,
+      "learning_rate": 2e-06,
+      "loss": 0.5111,
+      "step": 1010
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 1.2245457081729416,
+      "learning_rate": 2e-06,
+      "loss": 0.5064,
+      "step": 1020
+    },
+    {
+      "epoch": 1.996124031007752,
+      "grad_norm": 1.3046841459793526,
+      "learning_rate": 2e-06,
+      "loss": 0.5104,
+      "step": 1030
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 1.69236342694069,
+      "learning_rate": 2e-06,
+      "loss": 0.4698,
+      "step": 1040
+    },
+    {
+      "epoch": 2.0348837209302326,
+      "grad_norm": 1.482227404306843,
+      "learning_rate": 2e-06,
+      "loss": 0.4592,
+      "step": 1050
+    },
+    {
+      "epoch": 2.054263565891473,
+      "grad_norm": 1.472873774310932,
+      "learning_rate": 2e-06,
+      "loss": 0.458,
+      "step": 1060
+    },
+    {
+      "epoch": 2.0736434108527133,
+      "grad_norm": 1.5478690868120868,
+      "learning_rate": 2e-06,
+      "loss": 0.4595,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.3832474558503782,
+      "learning_rate": 2e-06,
+      "loss": 0.4544,
+      "step": 1080
+    },
+    {
+      "epoch": 2.112403100775194,
+      "grad_norm": 1.4739915975741762,
+      "learning_rate": 2e-06,
+      "loss": 0.4575,
+      "step": 1090
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 1.4093716459091368,
+      "learning_rate": 2e-06,
+      "loss": 0.4574,
+      "step": 1100
+    },
+    {
+      "epoch": 2.1511627906976742,
+      "grad_norm": 1.4597325989125942,
+      "learning_rate": 2e-06,
+      "loss": 0.4604,
+      "step": 1110
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 1.2596618218820486,
+      "learning_rate": 2e-06,
+      "loss": 0.4622,
+      "step": 1120
+    },
+    {
+      "epoch": 2.189922480620155,
+      "grad_norm": 1.8149063252784816,
+      "learning_rate": 2e-06,
+      "loss": 0.4592,
+      "step": 1130
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 1.552162424271938,
+      "learning_rate": 2e-06,
+      "loss": 0.4572,
+      "step": 1140
+    },
+    {
+      "epoch": 2.2286821705426356,
+      "grad_norm": 1.4310808330644234,
+      "learning_rate": 2e-06,
+      "loss": 0.4596,
+      "step": 1150
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 1.1994256997594486,
+      "learning_rate": 2e-06,
+      "loss": 0.4576,
+      "step": 1160
+    },
+    {
+      "epoch": 2.2674418604651163,
+      "grad_norm": 1.539587341902846,
+      "learning_rate": 2e-06,
+      "loss": 0.4584,
+      "step": 1170
+    },
+    {
+      "epoch": 2.2868217054263567,
+      "grad_norm": 1.333352666406639,
+      "learning_rate": 2e-06,
+      "loss": 0.4654,
+      "step": 1180
+    },
+    {
+      "epoch": 2.306201550387597,
+      "grad_norm": 1.443832387313447,
+      "learning_rate": 2e-06,
+      "loss": 0.4606,
+      "step": 1190
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 1.2947150626163912,
+      "learning_rate": 2e-06,
+      "loss": 0.4569,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3449612403100777,
+      "grad_norm": 1.2733884019792792,
+      "learning_rate": 2e-06,
+      "loss": 0.461,
+      "step": 1210
+    },
+    {
+      "epoch": 2.3643410852713176,
+      "grad_norm": 1.2445241956347013,
+      "learning_rate": 2e-06,
+      "loss": 0.4646,
+      "step": 1220
+    },
+    {
+      "epoch": 2.383720930232558,
+      "grad_norm": 1.3643853680636246,
+      "learning_rate": 2e-06,
+      "loss": 0.4598,
+      "step": 1230
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 1.3508030176182113,
+      "learning_rate": 2e-06,
+      "loss": 0.4659,
+      "step": 1240
+    },
+    {
+      "epoch": 2.4224806201550386,
+      "grad_norm": 1.4315788663602833,
+      "learning_rate": 2e-06,
+      "loss": 0.4606,
+      "step": 1250
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 1.2723100725181913,
+      "learning_rate": 2e-06,
+      "loss": 0.4629,
+      "step": 1260
+    },
+    {
+      "epoch": 2.4612403100775193,
+      "grad_norm": 1.3005627010479606,
+      "learning_rate": 2e-06,
+      "loss": 0.4643,
+      "step": 1270
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 1.3858018789769277,
+      "learning_rate": 2e-06,
+      "loss": 0.4647,
+      "step": 1280
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.441079130557343,
+      "learning_rate": 2e-06,
+      "loss": 0.458,
+      "step": 1290
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 1.20329198310741,
+      "learning_rate": 2e-06,
+      "loss": 0.4651,
+      "step": 1300
+    },
+    {
+      "epoch": 2.5387596899224807,
+      "grad_norm": 1.2598982072621057,
+      "learning_rate": 2e-06,
+      "loss": 0.4584,
+      "step": 1310
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.2079452297185667,
+      "learning_rate": 2e-06,
+      "loss": 0.4707,
+      "step": 1320
+    },
+    {
+      "epoch": 2.5775193798449614,
+      "grad_norm": 1.2529237840070613,
+      "learning_rate": 2e-06,
+      "loss": 0.4628,
+      "step": 1330
+    },
+    {
+      "epoch": 2.5968992248062017,
+      "grad_norm": 1.524625077175533,
+      "learning_rate": 2e-06,
+      "loss": 0.4716,
+      "step": 1340
+    },
+    {
+      "epoch": 2.616279069767442,
+      "grad_norm": 1.32372209621441,
+      "learning_rate": 2e-06,
+      "loss": 0.4629,
+      "step": 1350
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 1.5832090394160376,
+      "learning_rate": 2e-06,
+      "loss": 0.4595,
+      "step": 1360
+    },
+    {
+      "epoch": 2.6550387596899228,
+      "grad_norm": 1.2622980294640742,
+      "learning_rate": 2e-06,
+      "loss": 0.4605,
+      "step": 1370
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 1.235197532731858,
+      "learning_rate": 2e-06,
+      "loss": 0.4687,
+      "step": 1380
+    },
+    {
+      "epoch": 2.693798449612403,
+      "grad_norm": 1.2791276926102568,
+      "learning_rate": 2e-06,
+      "loss": 0.4603,
+      "step": 1390
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 1.2282558958052718,
+      "learning_rate": 2e-06,
+      "loss": 0.4683,
+      "step": 1400
+    },
+    {
+      "epoch": 2.7325581395348837,
+      "grad_norm": 1.3538612143623057,
+      "learning_rate": 2e-06,
+      "loss": 0.4601,
+      "step": 1410
+    },
+    {
+      "epoch": 2.751937984496124,
+      "grad_norm": 1.3291955159874183,
+      "learning_rate": 2e-06,
+      "loss": 0.4617,
+      "step": 1420
+    },
+    {
+      "epoch": 2.7713178294573644,
+      "grad_norm": 1.2058531615141939,
+      "learning_rate": 2e-06,
+      "loss": 0.4671,
+      "step": 1430
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 1.3306346445143116,
+      "learning_rate": 2e-06,
+      "loss": 0.466,
+      "step": 1440
+    },
+    {
+      "epoch": 2.810077519379845,
+      "grad_norm": 1.4572481853030812,
+      "learning_rate": 2e-06,
+      "loss": 0.4637,
+      "step": 1450
+    },
+    {
+      "epoch": 2.8294573643410854,
+      "grad_norm": 1.4181222197142325,
+      "learning_rate": 2e-06,
+      "loss": 0.4707,
+      "step": 1460
+    },
+    {
+      "epoch": 2.8488372093023253,
+      "grad_norm": 1.2329063854513693,
+      "learning_rate": 2e-06,
+      "loss": 0.4666,
+      "step": 1470
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 1.4499016075739342,
+      "learning_rate": 2e-06,
+      "loss": 0.467,
+      "step": 1480
+    },
+    {
+      "epoch": 2.887596899224806,
+      "grad_norm": 1.4376308105469073,
+      "learning_rate": 2e-06,
+      "loss": 0.4699,
+      "step": 1490
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 1.3931682854746266,
+      "learning_rate": 2e-06,
+      "loss": 0.4592,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9263565891472867,
+      "grad_norm": 1.3848029694873079,
+      "learning_rate": 2e-06,
+      "loss": 0.4633,
+      "step": 1510
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 1.2870479115717015,
+      "learning_rate": 2e-06,
+      "loss": 0.4684,
+      "step": 1520
+    },
+    {
+      "epoch": 2.9651162790697674,
+      "grad_norm": 1.348746763089945,
+      "learning_rate": 2e-06,
+      "loss": 0.4635,
+      "step": 1530
+    },
+    {
+      "epoch": 2.9844961240310077,
+      "grad_norm": 1.2816015840213701,
+      "learning_rate": 2e-06,
+      "loss": 0.4687,
+      "step": 1540
+    },
+    {
+      "epoch": 3.0,
+      "step": 1548,
+      "total_flos": 2592120137318400.0,
+      "train_loss": 0.5171875406913363,
+      "train_runtime": 22202.3543,
+      "train_samples_per_second": 35.668,
+      "train_steps_per_second": 0.07
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1548,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2592120137318400.0,
+  "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 sha256:8586d6ce3c4d3fea613180e1d49f3dbae2f40f1b73f1f02327e8955ab5e8e6b8
+size 7544