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_warmup5.00E-02_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_warmup5.00E-02_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: 0.05
+- 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": 2591282618695680.0,
+    "train_loss": 0.1541580106552873,
+    "train_runtime": 7454.5076,
+    "train_samples_per_second": 106.232,
+    "train_steps_per_second": 0.208
+}

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 sha256:649ea13a50cba9e7a69e6d1c171db07cacf3b31f1bc995997f7615734f955081
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584b6ce9965f30b4cbb750ad54e44c5adcb32389211b120187250335c0a820ee
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec34d56a5f035f3d657343a9735b9559b9480abc219aee6674e28a68c439c66f
+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": 2591282618695680.0,
+    "train_loss": 0.1541580106552873,
+    "train_runtime": 7454.5076,
+    "train_samples_per_second": 106.232,
+    "train_steps_per_second": 0.208
+}

trainer_log.jsonl

@@ -0,0 +1,192 @@
+{"current_steps": 10, "total_steps": 1548, "loss": 0.7225, "learning_rate": 2e-06, "epoch": 0.01937984496124031, "percentage": 0.65, "elapsed_time": "0:02:27", "remaining_time": "6:18:14"}
+{"current_steps": 20, "total_steps": 1548, "loss": 0.6518, "learning_rate": 2e-06, "epoch": 0.03875968992248062, "percentage": 1.29, "elapsed_time": "0:04:53", "remaining_time": "6:13:23"}
+{"current_steps": 30, "total_steps": 1548, "loss": 0.6267, "learning_rate": 2e-06, "epoch": 0.05813953488372093, "percentage": 1.94, "elapsed_time": "0:07:17", "remaining_time": "6:09:06"}
+{"current_steps": 40, "total_steps": 1548, "loss": 0.6193, "learning_rate": 2e-06, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:09:41", "remaining_time": "6:05:17"}
+{"current_steps": 50, "total_steps": 1548, "loss": 0.6139, "learning_rate": 2e-06, "epoch": 0.09689922480620156, "percentage": 3.23, "elapsed_time": "0:12:04", "remaining_time": "6:01:58"}
+{"current_steps": 60, "total_steps": 1548, "loss": 0.6069, "learning_rate": 2e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:14:29", "remaining_time": "5:59:12"}
+{"current_steps": 70, "total_steps": 1548, "loss": 0.6024, "learning_rate": 2e-06, "epoch": 0.13565891472868216, "percentage": 4.52, "elapsed_time": "0:16:52", "remaining_time": "5:56:24"}
+{"current_steps": 80, "total_steps": 1548, "loss": 0.6052, "learning_rate": 2e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:19:16", "remaining_time": "5:53:44"}
+{"current_steps": 90, "total_steps": 1548, "loss": 0.5906, "learning_rate": 2e-06, "epoch": 0.1744186046511628, "percentage": 5.81, "elapsed_time": "0:21:39", "remaining_time": "5:50:57"}
+{"current_steps": 100, "total_steps": 1548, "loss": 0.5929, "learning_rate": 2e-06, "epoch": 0.1937984496124031, "percentage": 6.46, "elapsed_time": "0:24:04", "remaining_time": "5:48:40"}
+{"current_steps": 110, "total_steps": 1548, "loss": 0.5958, "learning_rate": 2e-06, "epoch": 0.2131782945736434, "percentage": 7.11, "elapsed_time": "0:26:29", "remaining_time": "5:46:21"}
+{"current_steps": 120, "total_steps": 1548, "loss": 0.587, "learning_rate": 2e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:28:54", "remaining_time": "5:43:57"}
+{"current_steps": 130, "total_steps": 1548, "loss": 0.5972, "learning_rate": 2e-06, "epoch": 0.25193798449612403, "percentage": 8.4, "elapsed_time": "0:31:18", "remaining_time": "5:41:31"}
+{"current_steps": 140, "total_steps": 1548, "loss": 0.5837, "learning_rate": 2e-06, "epoch": 0.2713178294573643, "percentage": 9.04, "elapsed_time": "0:33:43", "remaining_time": "5:39:08"}
+{"current_steps": 150, "total_steps": 1548, "loss": 0.5837, "learning_rate": 2e-06, "epoch": 0.29069767441860467, "percentage": 9.69, "elapsed_time": "0:36:07", "remaining_time": "5:36:43"}
+{"current_steps": 160, "total_steps": 1548, "loss": 0.5824, "learning_rate": 2e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:38:30", "remaining_time": "5:34:04"}
+{"current_steps": 170, "total_steps": 1548, "loss": 0.5776, "learning_rate": 2e-06, "epoch": 0.32945736434108525, "percentage": 10.98, "elapsed_time": "0:41:00", "remaining_time": "5:32:23"}
+{"current_steps": 180, "total_steps": 1548, "loss": 0.5817, "learning_rate": 2e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:43:24", "remaining_time": "5:29:53"}
+{"current_steps": 190, "total_steps": 1548, "loss": 0.5745, "learning_rate": 2e-06, "epoch": 0.3682170542635659, "percentage": 12.27, "elapsed_time": "0:45:48", "remaining_time": "5:27:21"}
+{"current_steps": 200, "total_steps": 1548, "loss": 0.5822, "learning_rate": 2e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:48:12", "remaining_time": "5:24:55"}
+{"current_steps": 210, "total_steps": 1548, "loss": 0.5803, "learning_rate": 2e-06, "epoch": 0.4069767441860465, "percentage": 13.57, "elapsed_time": "0:50:37", "remaining_time": "5:22:30"}
+{"current_steps": 220, "total_steps": 1548, "loss": 0.5683, "learning_rate": 2e-06, "epoch": 0.4263565891472868, "percentage": 14.21, "elapsed_time": "0:53:01", "remaining_time": "5:20:03"}
+{"current_steps": 230, "total_steps": 1548, "loss": 0.5669, "learning_rate": 2e-06, "epoch": 0.44573643410852715, "percentage": 14.86, "elapsed_time": "0:55:24", "remaining_time": "5:17:32"}
+{"current_steps": 240, "total_steps": 1548, "loss": 0.5711, "learning_rate": 2e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:57:48", "remaining_time": "5:15:01"}
+{"current_steps": 250, "total_steps": 1548, "loss": 0.5715, "learning_rate": 2e-06, "epoch": 0.4844961240310077, "percentage": 16.15, "elapsed_time": "1:00:12", "remaining_time": "5:12:36"}
+{"current_steps": 260, "total_steps": 1548, "loss": 0.5706, "learning_rate": 2e-06, "epoch": 0.5038759689922481, "percentage": 16.8, "elapsed_time": "1:02:36", "remaining_time": "5:10:09"}
+{"current_steps": 270, "total_steps": 1548, "loss": 0.5711, "learning_rate": 2e-06, "epoch": 0.5232558139534884, "percentage": 17.44, "elapsed_time": "1:05:00", "remaining_time": "5:07:42"}
+{"current_steps": 280, "total_steps": 1548, "loss": 0.5665, "learning_rate": 2e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "1:07:24", "remaining_time": "5:05:13"}
+{"current_steps": 290, "total_steps": 1548, "loss": 0.5685, "learning_rate": 2e-06, "epoch": 0.562015503875969, "percentage": 18.73, "elapsed_time": "1:09:50", "remaining_time": "5:02:59"}
+{"current_steps": 300, "total_steps": 1548, "loss": 0.5767, "learning_rate": 2e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "1:12:14", "remaining_time": "5:00:29"}
+{"current_steps": 310, "total_steps": 1548, "loss": 0.5639, "learning_rate": 2e-06, "epoch": 0.6007751937984496, "percentage": 20.03, "elapsed_time": "1:14:36", "remaining_time": "4:57:59"}
+{"current_steps": 320, "total_steps": 1548, "loss": 0.5613, "learning_rate": 2e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "1:17:00", "remaining_time": "4:55:32"}
+{"current_steps": 330, "total_steps": 1548, "loss": 0.5629, "learning_rate": 2e-06, "epoch": 0.6395348837209303, "percentage": 21.32, "elapsed_time": "1:19:24", "remaining_time": "4:53:05"}
+{"current_steps": 340, "total_steps": 1548, "loss": 0.5591, "learning_rate": 2e-06, "epoch": 0.6589147286821705, "percentage": 21.96, "elapsed_time": "1:21:47", "remaining_time": "4:50:36"}
+{"current_steps": 350, "total_steps": 1548, "loss": 0.5561, "learning_rate": 2e-06, "epoch": 0.6782945736434108, "percentage": 22.61, "elapsed_time": "1:24:11", "remaining_time": "4:48:10"}
+{"current_steps": 360, "total_steps": 1548, "loss": 0.561, "learning_rate": 2e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "1:26:33", "remaining_time": "4:45:40"}
+{"current_steps": 370, "total_steps": 1548, "loss": 0.5662, "learning_rate": 2e-06, "epoch": 0.7170542635658915, "percentage": 23.9, "elapsed_time": "1:28:56", "remaining_time": "4:43:08"}
+{"current_steps": 380, "total_steps": 1548, "loss": 0.5671, "learning_rate": 2e-06, "epoch": 0.7364341085271318, "percentage": 24.55, "elapsed_time": "1:31:19", "remaining_time": "4:40:41"}
+{"current_steps": 390, "total_steps": 1548, "loss": 0.5568, "learning_rate": 2e-06, "epoch": 0.7558139534883721, "percentage": 25.19, "elapsed_time": "1:33:42", "remaining_time": "4:38:14"}
+{"current_steps": 400, "total_steps": 1548, "loss": 0.5581, "learning_rate": 2e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "1:36:05", "remaining_time": "4:35:47"}
+{"current_steps": 410, "total_steps": 1548, "loss": 0.5637, "learning_rate": 2e-06, "epoch": 0.7945736434108527, "percentage": 26.49, "elapsed_time": "1:38:28", "remaining_time": "4:33:18"}
+{"current_steps": 420, "total_steps": 1548, "loss": 0.5582, "learning_rate": 2e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "1:40:50", "remaining_time": "4:30:49"}
+{"current_steps": 430, "total_steps": 1548, "loss": 0.5612, "learning_rate": 2e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "1:43:16", "remaining_time": "4:28:30"}
+{"current_steps": 440, "total_steps": 1548, "loss": 0.5588, "learning_rate": 2e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "1:45:39", "remaining_time": "4:26:04"}
+{"current_steps": 450, "total_steps": 1548, "loss": 0.5621, "learning_rate": 2e-06, "epoch": 0.872093023255814, "percentage": 29.07, "elapsed_time": "1:48:03", "remaining_time": "4:23:39"}
+{"current_steps": 460, "total_steps": 1548, "loss": 0.5513, "learning_rate": 2e-06, "epoch": 0.8914728682170543, "percentage": 29.72, "elapsed_time": "1:50:26", "remaining_time": "4:21:13"}
+{"current_steps": 470, "total_steps": 1548, "loss": 0.5577, "learning_rate": 2e-06, "epoch": 0.9108527131782945, "percentage": 30.36, "elapsed_time": "1:52:49", "remaining_time": "4:18:46"}
+{"current_steps": 480, "total_steps": 1548, "loss": 0.5584, "learning_rate": 2e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "1:55:12", "remaining_time": "4:16:21"}
+{"current_steps": 490, "total_steps": 1548, "loss": 0.5517, "learning_rate": 2e-06, "epoch": 0.9496124031007752, "percentage": 31.65, "elapsed_time": "1:57:39", "remaining_time": "4:14:02"}
+{"current_steps": 500, "total_steps": 1548, "loss": 0.5528, "learning_rate": 2e-06, "epoch": 0.9689922480620154, "percentage": 32.3, "elapsed_time": "2:00:02", "remaining_time": "4:11:37"}
+{"current_steps": 510, "total_steps": 1548, "loss": 0.5573, "learning_rate": 2e-06, "epoch": 0.9883720930232558, "percentage": 32.95, "elapsed_time": "2:02:26", "remaining_time": "4:09:11"}
+{"current_steps": 520, "total_steps": 1548, "loss": 0.5359, "learning_rate": 2e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "2:05:12", "remaining_time": "4:07:31"}
+{"current_steps": 530, "total_steps": 1548, "loss": 0.5096, "learning_rate": 2e-06, "epoch": 1.0271317829457365, "percentage": 34.24, "elapsed_time": "2:07:35", "remaining_time": "4:05:04"}
+{"current_steps": 540, "total_steps": 1548, "loss": 0.5072, "learning_rate": 2e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "2:09:59", "remaining_time": "4:02:38"}
+{"current_steps": 550, "total_steps": 1548, "loss": 0.5052, "learning_rate": 2e-06, "epoch": 1.0658914728682172, "percentage": 35.53, "elapsed_time": "2:12:23", "remaining_time": "4:00:12"}
+{"current_steps": 560, "total_steps": 1548, "loss": 0.5169, "learning_rate": 2e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "2:14:45", "remaining_time": "3:57:45"}
+{"current_steps": 570, "total_steps": 1548, "loss": 0.5102, "learning_rate": 2e-06, "epoch": 1.1046511627906976, "percentage": 36.82, "elapsed_time": "2:17:08", "remaining_time": "3:55:18"}
+{"current_steps": 580, "total_steps": 1548, "loss": 0.5038, "learning_rate": 2e-06, "epoch": 1.124031007751938, "percentage": 37.47, "elapsed_time": "2:19:30", "remaining_time": "3:52:50"}
+{"current_steps": 590, "total_steps": 1548, "loss": 0.5034, "learning_rate": 2e-06, "epoch": 1.1434108527131783, "percentage": 38.11, "elapsed_time": "2:21:54", "remaining_time": "3:50:24"}
+{"current_steps": 600, "total_steps": 1548, "loss": 0.5038, "learning_rate": 2e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "2:24:17", "remaining_time": "3:47:58"}
+{"current_steps": 610, "total_steps": 1548, "loss": 0.5137, "learning_rate": 2e-06, "epoch": 1.1821705426356588, "percentage": 39.41, "elapsed_time": "2:26:40", "remaining_time": "3:45:32"}
+{"current_steps": 620, "total_steps": 1548, "loss": 0.5076, "learning_rate": 2e-06, "epoch": 1.2015503875968991, "percentage": 40.05, "elapsed_time": "2:29:03", "remaining_time": "3:43:06"}
+{"current_steps": 630, "total_steps": 1548, "loss": 0.5077, "learning_rate": 2e-06, "epoch": 1.2209302325581395, "percentage": 40.7, "elapsed_time": "2:31:27", "remaining_time": "3:40:41"}
+{"current_steps": 640, "total_steps": 1548, "loss": 0.5083, "learning_rate": 2e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "2:33:50", "remaining_time": "3:38:15"}
+{"current_steps": 650, "total_steps": 1548, "loss": 0.5096, "learning_rate": 2e-06, "epoch": 1.2596899224806202, "percentage": 41.99, "elapsed_time": "2:36:13", "remaining_time": "3:35:49"}
+{"current_steps": 660, "total_steps": 1548, "loss": 0.5063, "learning_rate": 2e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "2:38:36", "remaining_time": "3:33:23"}
+{"current_steps": 670, "total_steps": 1548, "loss": 0.5122, "learning_rate": 2e-06, "epoch": 1.2984496124031009, "percentage": 43.28, "elapsed_time": "2:41:00", "remaining_time": "3:30:58"}
+{"current_steps": 680, "total_steps": 1548, "loss": 0.5121, "learning_rate": 2e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "2:43:23", "remaining_time": "3:28:34"}
+{"current_steps": 690, "total_steps": 1548, "loss": 0.5089, "learning_rate": 2e-06, "epoch": 1.3372093023255813, "percentage": 44.57, "elapsed_time": "2:45:47", "remaining_time": "3:26:09"}
+{"current_steps": 700, "total_steps": 1548, "loss": 0.5099, "learning_rate": 2e-06, "epoch": 1.3565891472868217, "percentage": 45.22, "elapsed_time": "2:48:10", "remaining_time": "3:23:44"}
+{"current_steps": 710, "total_steps": 1548, "loss": 0.5134, "learning_rate": 2e-06, "epoch": 1.375968992248062, "percentage": 45.87, "elapsed_time": "2:50:34", "remaining_time": "3:21:19"}
+{"current_steps": 720, "total_steps": 1548, "loss": 0.5123, "learning_rate": 2e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "2:52:57", "remaining_time": "3:18:54"}
+{"current_steps": 730, "total_steps": 1548, "loss": 0.5078, "learning_rate": 2e-06, "epoch": 1.4147286821705427, "percentage": 47.16, "elapsed_time": "2:55:20", "remaining_time": "3:16:29"}
+{"current_steps": 740, "total_steps": 1548, "loss": 0.5137, "learning_rate": 2e-06, "epoch": 1.4341085271317828, "percentage": 47.8, "elapsed_time": "2:57:44", "remaining_time": "3:14:04"}
+{"current_steps": 750, "total_steps": 1548, "loss": 0.5094, "learning_rate": 2e-06, "epoch": 1.4534883720930232, "percentage": 48.45, "elapsed_time": "3:00:08", "remaining_time": "3:11:39"}
+{"current_steps": 760, "total_steps": 1548, "loss": 0.5063, "learning_rate": 2e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "3:02:30", "remaining_time": "3:09:14"}
+{"current_steps": 770, "total_steps": 1548, "loss": 0.5097, "learning_rate": 2e-06, "epoch": 1.4922480620155039, "percentage": 49.74, "elapsed_time": "3:04:53", "remaining_time": "3:06:48"}
+{"current_steps": 780, "total_steps": 1548, "loss": 0.5127, "learning_rate": 2e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "3:07:18", "remaining_time": "3:04:25"}
+{"current_steps": 790, "total_steps": 1548, "loss": 0.5097, "learning_rate": 2e-06, "epoch": 1.5310077519379846, "percentage": 51.03, "elapsed_time": "3:09:43", "remaining_time": "3:02:02"}
+{"current_steps": 800, "total_steps": 1548, "loss": 0.507, "learning_rate": 2e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "3:12:08", "remaining_time": "2:59:39"}
+{"current_steps": 810, "total_steps": 1548, "loss": 0.5052, "learning_rate": 2e-06, "epoch": 1.5697674418604652, "percentage": 52.33, "elapsed_time": "3:14:34", "remaining_time": "2:57:16"}
+{"current_steps": 820, "total_steps": 1548, "loss": 0.5039, "learning_rate": 2e-06, "epoch": 1.5891472868217056, "percentage": 52.97, "elapsed_time": "3:16:59", "remaining_time": "2:54:53"}
+{"current_steps": 830, "total_steps": 1548, "loss": 0.512, "learning_rate": 2e-06, "epoch": 1.6085271317829457, "percentage": 53.62, "elapsed_time": "3:19:23", "remaining_time": "2:52:29"}
+{"current_steps": 840, "total_steps": 1548, "loss": 0.5066, "learning_rate": 2e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "3:21:49", "remaining_time": "2:50:06"}
+{"current_steps": 850, "total_steps": 1548, "loss": 0.5113, "learning_rate": 2e-06, "epoch": 1.6472868217054264, "percentage": 54.91, "elapsed_time": "3:24:14", "remaining_time": "2:47:43"}
+{"current_steps": 860, "total_steps": 1548, "loss": 0.5137, "learning_rate": 2e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "3:26:39", "remaining_time": "2:45:19"}
+{"current_steps": 870, "total_steps": 1548, "loss": 0.506, "learning_rate": 2e-06, "epoch": 1.6860465116279069, "percentage": 56.2, "elapsed_time": "3:29:04", "remaining_time": "2:42:55"}
+{"current_steps": 880, "total_steps": 1548, "loss": 0.5107, "learning_rate": 2e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "3:31:29", "remaining_time": "2:40:32"}
+{"current_steps": 890, "total_steps": 1548, "loss": 0.5099, "learning_rate": 2e-06, "epoch": 1.7248062015503876, "percentage": 57.49, "elapsed_time": "3:33:54", "remaining_time": "2:38:09"}
+{"current_steps": 900, "total_steps": 1548, "loss": 0.5139, "learning_rate": 2e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "3:36:21", "remaining_time": "2:35:46"}
+{"current_steps": 910, "total_steps": 1548, "loss": 0.5059, "learning_rate": 2e-06, "epoch": 1.7635658914728682, "percentage": 58.79, "elapsed_time": "3:38:46", "remaining_time": "2:33:22"}
+{"current_steps": 920, "total_steps": 1548, "loss": 0.5088, "learning_rate": 2e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "3:41:10", "remaining_time": "2:30:58"}
+{"current_steps": 930, "total_steps": 1548, "loss": 0.5096, "learning_rate": 2e-06, "epoch": 1.802325581395349, "percentage": 60.08, "elapsed_time": "3:43:35", "remaining_time": "2:28:35"}
+{"current_steps": 940, "total_steps": 1548, "loss": 0.5077, "learning_rate": 2e-06, "epoch": 1.8217054263565893, "percentage": 60.72, "elapsed_time": "3:46:01", "remaining_time": "2:26:11"}
+{"current_steps": 950, "total_steps": 1548, "loss": 0.5102, "learning_rate": 2e-06, "epoch": 1.8410852713178296, "percentage": 61.37, "elapsed_time": "3:48:26", "remaining_time": "2:23:47"}
+{"current_steps": 960, "total_steps": 1548, "loss": 0.512, "learning_rate": 2e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "3:50:51", "remaining_time": "2:21:24"}
+{"current_steps": 970, "total_steps": 1548, "loss": 0.5096, "learning_rate": 2e-06, "epoch": 1.87984496124031, "percentage": 62.66, "elapsed_time": "3:53:16", "remaining_time": "2:19:00"}
+{"current_steps": 980, "total_steps": 1548, "loss": 0.5057, "learning_rate": 2e-06, "epoch": 1.8992248062015504, "percentage": 63.31, "elapsed_time": "3:55:41", "remaining_time": "2:16:36"}
+{"current_steps": 990, "total_steps": 1548, "loss": 0.5118, "learning_rate": 2e-06, "epoch": 1.9186046511627906, "percentage": 63.95, "elapsed_time": "3:58:07", "remaining_time": "2:14:12"}
+{"current_steps": 1000, "total_steps": 1548, "loss": 0.5092, "learning_rate": 2e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "4:00:31", "remaining_time": "2:11:48"}
+{"current_steps": 1010, "total_steps": 1548, "loss": 0.5104, "learning_rate": 2e-06, "epoch": 1.9573643410852712, "percentage": 65.25, "elapsed_time": "4:02:57", "remaining_time": "2:09:25"}
+{"current_steps": 1020, "total_steps": 1548, "loss": 0.5059, "learning_rate": 2e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "4:05:23", "remaining_time": "2:07:01"}
+{"current_steps": 1030, "total_steps": 1548, "loss": 0.51, "learning_rate": 2e-06, "epoch": 1.996124031007752, "percentage": 66.54, "elapsed_time": "4:07:48", "remaining_time": "2:04:37"}
+{"current_steps": 1040, "total_steps": 1548, "loss": 0.4691, "learning_rate": 2e-06, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "4:10:40", "remaining_time": "2:02:26"}
+{"current_steps": 1050, "total_steps": 1548, "loss": 0.4585, "learning_rate": 2e-06, "epoch": 2.0348837209302326, "percentage": 67.83, "elapsed_time": "4:13:06", "remaining_time": "2:00:02"}
+{"current_steps": 1060, "total_steps": 1548, "loss": 0.4571, "learning_rate": 2e-06, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "4:15:30", "remaining_time": "1:57:37"}
+{"current_steps": 1070, "total_steps": 1548, "loss": 0.4591, "learning_rate": 2e-06, "epoch": 2.0736434108527133, "percentage": 69.12, "elapsed_time": "4:17:55", "remaining_time": "1:55:13"}
+{"current_steps": 1080, "total_steps": 1548, "loss": 0.4538, "learning_rate": 2e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "4:20:19", "remaining_time": "1:52:48"}
+{"current_steps": 1090, "total_steps": 1548, "loss": 0.4568, "learning_rate": 2e-06, "epoch": 2.112403100775194, "percentage": 70.41, "elapsed_time": "4:22:43", "remaining_time": "1:50:23"}
+{"current_steps": 1100, "total_steps": 1548, "loss": 0.4564, "learning_rate": 2e-06, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "4:25:07", "remaining_time": "1:47:58"}
+{"current_steps": 1110, "total_steps": 1548, "loss": 0.4598, "learning_rate": 2e-06, "epoch": 2.1511627906976742, "percentage": 71.71, "elapsed_time": "4:27:31", "remaining_time": "1:45:33"}
+{"current_steps": 1120, "total_steps": 1548, "loss": 0.4612, "learning_rate": 2e-06, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "4:29:56", "remaining_time": "1:43:09"}
+{"current_steps": 1130, "total_steps": 1548, "loss": 0.4583, "learning_rate": 2e-06, "epoch": 2.189922480620155, "percentage": 73.0, "elapsed_time": "4:32:19", "remaining_time": "1:40:44"}
+{"current_steps": 1140, "total_steps": 1548, "loss": 0.4568, "learning_rate": 2e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "4:34:43", "remaining_time": "1:38:19"}
+{"current_steps": 1150, "total_steps": 1548, "loss": 0.4594, "learning_rate": 2e-06, "epoch": 2.2286821705426356, "percentage": 74.29, "elapsed_time": "4:37:07", "remaining_time": "1:35:54"}
+{"current_steps": 1160, "total_steps": 1548, "loss": 0.4571, "learning_rate": 2e-06, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "4:39:32", "remaining_time": "1:33:30"}
+{"current_steps": 1170, "total_steps": 1548, "loss": 0.4577, "learning_rate": 2e-06, "epoch": 2.2674418604651163, "percentage": 75.58, "elapsed_time": "4:41:56", "remaining_time": "1:31:05"}
+{"current_steps": 1180, "total_steps": 1548, "loss": 0.4649, "learning_rate": 2e-06, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "4:44:21", "remaining_time": "1:28:40"}
+{"current_steps": 1190, "total_steps": 1548, "loss": 0.4601, "learning_rate": 2e-06, "epoch": 2.306201550387597, "percentage": 76.87, "elapsed_time": "4:46:46", "remaining_time": "1:26:16"}
+{"current_steps": 1200, "total_steps": 1548, "loss": 0.4564, "learning_rate": 2e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "4:49:11", "remaining_time": "1:23:51"}
+{"current_steps": 1210, "total_steps": 1548, "loss": 0.4605, "learning_rate": 2e-06, "epoch": 2.3449612403100777, "percentage": 78.17, "elapsed_time": "4:51:35", "remaining_time": "1:21:27"}
+{"current_steps": 1220, "total_steps": 1548, "loss": 0.4639, "learning_rate": 2e-06, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "4:53:59", "remaining_time": "1:19:02"}
+{"current_steps": 1230, "total_steps": 1548, "loss": 0.4591, "learning_rate": 2e-06, "epoch": 2.383720930232558, "percentage": 79.46, "elapsed_time": "4:56:23", "remaining_time": "1:16:37"}
+{"current_steps": 1240, "total_steps": 1548, "loss": 0.4655, "learning_rate": 2e-06, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "4:58:47", "remaining_time": "1:14:13"}
+{"current_steps": 1250, "total_steps": 1548, "loss": 0.46, "learning_rate": 2e-06, "epoch": 2.4224806201550386, "percentage": 80.75, "elapsed_time": "5:01:11", "remaining_time": "1:11:48"}
+{"current_steps": 1260, "total_steps": 1548, "loss": 0.462, "learning_rate": 2e-06, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "5:03:34", "remaining_time": "1:09:23"}
+{"current_steps": 1270, "total_steps": 1548, "loss": 0.4637, "learning_rate": 2e-06, "epoch": 2.4612403100775193, "percentage": 82.04, "elapsed_time": "5:05:57", "remaining_time": "1:06:58"}
+{"current_steps": 1280, "total_steps": 1548, "loss": 0.4639, "learning_rate": 2e-06, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "5:08:21", "remaining_time": "1:04:33"}
+{"current_steps": 1290, "total_steps": 1548, "loss": 0.4573, "learning_rate": 2e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:10:46", "remaining_time": "1:02:09"}
+{"current_steps": 1300, "total_steps": 1548, "loss": 0.4643, "learning_rate": 2e-06, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "5:13:10", "remaining_time": "0:59:44"}
+{"current_steps": 1310, "total_steps": 1548, "loss": 0.4579, "learning_rate": 2e-06, "epoch": 2.5387596899224807, "percentage": 84.63, "elapsed_time": "5:15:35", "remaining_time": "0:57:20"}
+{"current_steps": 1320, "total_steps": 1548, "loss": 0.4701, "learning_rate": 2e-06, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "5:17:59", "remaining_time": "0:54:55"}
+{"current_steps": 1330, "total_steps": 1548, "loss": 0.4622, "learning_rate": 2e-06, "epoch": 2.5775193798449614, "percentage": 85.92, "elapsed_time": "5:20:24", "remaining_time": "0:52:31"}
+{"current_steps": 1340, "total_steps": 1548, "loss": 0.4708, "learning_rate": 2e-06, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "5:22:48", "remaining_time": "0:50:06"}
+{"current_steps": 1350, "total_steps": 1548, "loss": 0.4622, "learning_rate": 2e-06, "epoch": 2.616279069767442, "percentage": 87.21, "elapsed_time": "5:25:12", "remaining_time": "0:47:41"}
+{"current_steps": 1360, "total_steps": 1548, "loss": 0.459, "learning_rate": 2e-06, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "5:27:36", "remaining_time": "0:45:17"}
+{"current_steps": 1370, "total_steps": 1548, "loss": 0.4597, "learning_rate": 2e-06, "epoch": 2.6550387596899228, "percentage": 88.5, "elapsed_time": "5:30:00", "remaining_time": "0:42:52"}
+{"current_steps": 1380, "total_steps": 1548, "loss": 0.468, "learning_rate": 2e-06, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "5:32:23", "remaining_time": "0:40:27"}
+{"current_steps": 1390, "total_steps": 1548, "loss": 0.4598, "learning_rate": 2e-06, "epoch": 2.693798449612403, "percentage": 89.79, "elapsed_time": "5:34:47", "remaining_time": "0:38:03"}
+{"current_steps": 1400, "total_steps": 1548, "loss": 0.4678, "learning_rate": 2e-06, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "5:37:12", "remaining_time": "0:35:38"}
+{"current_steps": 1040, "total_steps": 1548, "loss": 0.4603, "learning_rate": 2e-06, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "0:01:55", "remaining_time": "0:00:56"}
+{"current_steps": 1050, "total_steps": 1548, "loss": 0.4585, "learning_rate": 2e-06, "epoch": 2.0348837209302326, "percentage": 67.83, "elapsed_time": "0:04:19", "remaining_time": "0:02:02"}
+{"current_steps": 1060, "total_steps": 1548, "loss": 0.4571, "learning_rate": 2e-06, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "0:06:43", "remaining_time": "0:03:05"}
+{"current_steps": 1070, "total_steps": 1548, "loss": 0.4591, "learning_rate": 2e-06, "epoch": 2.0736434108527133, "percentage": 69.12, "elapsed_time": "0:09:07", "remaining_time": "0:04:04"}
+{"current_steps": 1080, "total_steps": 1548, "loss": 0.4537, "learning_rate": 2e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "0:11:30", "remaining_time": "0:04:59"}
+{"current_steps": 1090, "total_steps": 1548, "loss": 0.4567, "learning_rate": 2e-06, "epoch": 2.112403100775194, "percentage": 70.41, "elapsed_time": "0:13:53", "remaining_time": "0:05:50"}
+{"current_steps": 1100, "total_steps": 1548, "loss": 0.4564, "learning_rate": 2e-06, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "0:16:16", "remaining_time": "0:06:37"}
+{"current_steps": 1110, "total_steps": 1548, "loss": 0.4597, "learning_rate": 2e-06, "epoch": 2.1511627906976742, "percentage": 71.71, "elapsed_time": "0:18:40", "remaining_time": "0:07:22"}
+{"current_steps": 1120, "total_steps": 1548, "loss": 0.4613, "learning_rate": 2e-06, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "0:21:04", "remaining_time": "0:08:03"}
+{"current_steps": 1130, "total_steps": 1548, "loss": 0.4582, "learning_rate": 2e-06, "epoch": 2.189922480620155, "percentage": 73.0, "elapsed_time": "0:23:28", "remaining_time": "0:08:41"}
+{"current_steps": 1140, "total_steps": 1548, "loss": 0.4567, "learning_rate": 2e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "0:25:53", "remaining_time": "0:09:15"}
+{"current_steps": 1150, "total_steps": 1548, "loss": 0.4593, "learning_rate": 2e-06, "epoch": 2.2286821705426356, "percentage": 74.29, "elapsed_time": "0:28:17", "remaining_time": "0:09:47"}
+{"current_steps": 1160, "total_steps": 1548, "loss": 0.4571, "learning_rate": 2e-06, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "0:30:41", "remaining_time": "0:10:15"}
+{"current_steps": 1170, "total_steps": 1548, "loss": 0.4576, "learning_rate": 2e-06, "epoch": 2.2674418604651163, "percentage": 75.58, "elapsed_time": "0:33:05", "remaining_time": "0:10:41"}
+{"current_steps": 1180, "total_steps": 1548, "loss": 0.4648, "learning_rate": 2e-06, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "0:35:29", "remaining_time": "0:11:04"}
+{"current_steps": 1190, "total_steps": 1548, "loss": 0.46, "learning_rate": 2e-06, "epoch": 2.306201550387597, "percentage": 76.87, "elapsed_time": "0:37:52", "remaining_time": "0:11:23"}
+{"current_steps": 1200, "total_steps": 1548, "loss": 0.4564, "learning_rate": 2e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "0:40:16", "remaining_time": "0:11:40"}
+{"current_steps": 1210, "total_steps": 1548, "loss": 0.4605, "learning_rate": 2e-06, "epoch": 2.3449612403100777, "percentage": 78.17, "elapsed_time": "0:42:41", "remaining_time": "0:11:55"}
+{"current_steps": 1220, "total_steps": 1548, "loss": 0.4639, "learning_rate": 2e-06, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "0:45:05", "remaining_time": "0:12:07"}
+{"current_steps": 1230, "total_steps": 1548, "loss": 0.4591, "learning_rate": 2e-06, "epoch": 2.383720930232558, "percentage": 79.46, "elapsed_time": "0:47:29", "remaining_time": "0:12:16"}
+{"current_steps": 1240, "total_steps": 1548, "loss": 0.4654, "learning_rate": 2e-06, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "0:49:54", "remaining_time": "0:12:23"}
+{"current_steps": 1250, "total_steps": 1548, "loss": 0.46, "learning_rate": 2e-06, "epoch": 2.4224806201550386, "percentage": 80.75, "elapsed_time": "0:52:17", "remaining_time": "0:12:27"}
+{"current_steps": 1260, "total_steps": 1548, "loss": 0.462, "learning_rate": 2e-06, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "0:54:41", "remaining_time": "0:12:30"}
+{"current_steps": 1270, "total_steps": 1548, "loss": 0.4636, "learning_rate": 2e-06, "epoch": 2.4612403100775193, "percentage": 82.04, "elapsed_time": "0:57:05", "remaining_time": "0:12:29"}
+{"current_steps": 1280, "total_steps": 1548, "loss": 0.4637, "learning_rate": 2e-06, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "0:59:29", "remaining_time": "0:12:27"}
+{"current_steps": 1290, "total_steps": 1548, "loss": 0.4572, "learning_rate": 2e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:01:53", "remaining_time": "0:12:22"}
+{"current_steps": 1300, "total_steps": 1548, "loss": 0.4643, "learning_rate": 2e-06, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "1:04:16", "remaining_time": "0:12:15"}
+{"current_steps": 1310, "total_steps": 1548, "loss": 0.458, "learning_rate": 2e-06, "epoch": 2.5387596899224807, "percentage": 84.63, "elapsed_time": "1:06:40", "remaining_time": "0:12:06"}
+{"current_steps": 1320, "total_steps": 1548, "loss": 0.4702, "learning_rate": 2e-06, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "1:09:03", "remaining_time": "0:11:55"}
+{"current_steps": 1330, "total_steps": 1548, "loss": 0.4622, "learning_rate": 2e-06, "epoch": 2.5775193798449614, "percentage": 85.92, "elapsed_time": "1:11:26", "remaining_time": "0:11:42"}
+{"current_steps": 1340, "total_steps": 1548, "loss": 0.4708, "learning_rate": 2e-06, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "1:13:48", "remaining_time": "0:11:27"}
+{"current_steps": 1350, "total_steps": 1548, "loss": 0.4622, "learning_rate": 2e-06, "epoch": 2.616279069767442, "percentage": 87.21, "elapsed_time": "1:16:11", "remaining_time": "0:11:10"}
+{"current_steps": 1360, "total_steps": 1548, "loss": 0.459, "learning_rate": 2e-06, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "1:18:34", "remaining_time": "0:10:51"}
+{"current_steps": 1370, "total_steps": 1548, "loss": 0.4597, "learning_rate": 2e-06, "epoch": 2.6550387596899228, "percentage": 88.5, "elapsed_time": "1:20:57", "remaining_time": "0:10:31"}
+{"current_steps": 1380, "total_steps": 1548, "loss": 0.468, "learning_rate": 2e-06, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "1:23:19", "remaining_time": "0:10:08"}
+{"current_steps": 1390, "total_steps": 1548, "loss": 0.4598, "learning_rate": 2e-06, "epoch": 2.693798449612403, "percentage": 89.79, "elapsed_time": "1:25:42", "remaining_time": "0:09:44"}
+{"current_steps": 1400, "total_steps": 1548, "loss": 0.4678, "learning_rate": 2e-06, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "1:28:05", "remaining_time": "0:09:18"}
+{"current_steps": 1410, "total_steps": 1548, "loss": 0.4594, "learning_rate": 2e-06, "epoch": 2.7325581395348837, "percentage": 91.09, "elapsed_time": "1:30:27", "remaining_time": "0:08:51"}
+{"current_steps": 1420, "total_steps": 1548, "loss": 0.4613, "learning_rate": 2e-06, "epoch": 2.751937984496124, "percentage": 91.73, "elapsed_time": "1:32:50", "remaining_time": "0:08:22"}
+{"current_steps": 1430, "total_steps": 1548, "loss": 0.4667, "learning_rate": 2e-06, "epoch": 2.7713178294573644, "percentage": 92.38, "elapsed_time": "1:35:13", "remaining_time": "0:07:51"}
+{"current_steps": 1440, "total_steps": 1548, "loss": 0.4656, "learning_rate": 2e-06, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "1:37:35", "remaining_time": "0:07:19"}
+{"current_steps": 1450, "total_steps": 1548, "loss": 0.463, "learning_rate": 2e-06, "epoch": 2.810077519379845, "percentage": 93.67, "elapsed_time": "1:39:58", "remaining_time": "0:06:45"}
+{"current_steps": 1460, "total_steps": 1548, "loss": 0.4703, "learning_rate": 2e-06, "epoch": 2.8294573643410854, "percentage": 94.32, "elapsed_time": "1:42:20", "remaining_time": "0:06:10"}
+{"current_steps": 1470, "total_steps": 1548, "loss": 0.4661, "learning_rate": 2e-06, "epoch": 2.8488372093023253, "percentage": 94.96, "elapsed_time": "1:44:43", "remaining_time": "0:05:33"}
+{"current_steps": 1480, "total_steps": 1548, "loss": 0.4667, "learning_rate": 2e-06, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "1:47:06", "remaining_time": "0:04:55"}
+{"current_steps": 1490, "total_steps": 1548, "loss": 0.4692, "learning_rate": 2e-06, "epoch": 2.887596899224806, "percentage": 96.25, "elapsed_time": "1:49:30", "remaining_time": "0:04:15"}
+{"current_steps": 1500, "total_steps": 1548, "loss": 0.4585, "learning_rate": 2e-06, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "1:51:53", "remaining_time": "0:03:34"}
+{"current_steps": 1510, "total_steps": 1548, "loss": 0.4627, "learning_rate": 2e-06, "epoch": 2.9263565891472867, "percentage": 97.55, "elapsed_time": "1:54:16", "remaining_time": "0:02:52"}
+{"current_steps": 1520, "total_steps": 1548, "loss": 0.4679, "learning_rate": 2e-06, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "1:56:39", "remaining_time": "0:02:08"}
+{"current_steps": 1530, "total_steps": 1548, "loss": 0.463, "learning_rate": 2e-06, "epoch": 2.9651162790697674, "percentage": 98.84, "elapsed_time": "1:59:02", "remaining_time": "0:01:24"}
+{"current_steps": 1540, "total_steps": 1548, "loss": 0.468, "learning_rate": 2e-06, "epoch": 2.9844961240310077, "percentage": 99.48, "elapsed_time": "2:01:25", "remaining_time": "0:00:37"}
+{"current_steps": 1548, "total_steps": 1548, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:04:08", "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": 3.1349940241372636,
+      "learning_rate": 2e-06,
+      "loss": 0.7225,
+      "step": 10
+    },
+    {
+      "epoch": 0.03875968992248062,
+      "grad_norm": 1.478554813389481,
+      "learning_rate": 2e-06,
+      "loss": 0.6518,
+      "step": 20
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "grad_norm": 1.40892259720196,
+      "learning_rate": 2e-06,
+      "loss": 0.6267,
+      "step": 30
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 1.6253951402557405,
+      "learning_rate": 2e-06,
+      "loss": 0.6193,
+      "step": 40
+    },
+    {
+      "epoch": 0.09689922480620156,
+      "grad_norm": 1.474392955252126,
+      "learning_rate": 2e-06,
+      "loss": 0.6139,
+      "step": 50
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 3.0751907911279477,
+      "learning_rate": 2e-06,
+      "loss": 0.6069,
+      "step": 60
+    },
+    {
+      "epoch": 0.13565891472868216,
+      "grad_norm": 2.9223888412970873,
+      "learning_rate": 2e-06,
+      "loss": 0.6024,
+      "step": 70
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 2.357095375310306,
+      "learning_rate": 2e-06,
+      "loss": 0.6052,
+      "step": 80
+    },
+    {
+      "epoch": 0.1744186046511628,
+      "grad_norm": 1.3933025656894271,
+      "learning_rate": 2e-06,
+      "loss": 0.5906,
+      "step": 90
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 1.820645926185548,
+      "learning_rate": 2e-06,
+      "loss": 0.5929,
+      "step": 100
+    },
+    {
+      "epoch": 0.2131782945736434,
+      "grad_norm": 1.7924399526821087,
+      "learning_rate": 2e-06,
+      "loss": 0.5958,
+      "step": 110
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.7736991192509453,
+      "learning_rate": 2e-06,
+      "loss": 0.587,
+      "step": 120
+    },
+    {
+      "epoch": 0.25193798449612403,
+      "grad_norm": 1.9201526538063434,
+      "learning_rate": 2e-06,
+      "loss": 0.5972,
+      "step": 130
+    },
+    {
+      "epoch": 0.2713178294573643,
+      "grad_norm": 1.9904730096438479,
+      "learning_rate": 2e-06,
+      "loss": 0.5837,
+      "step": 140
+    },
+    {
+      "epoch": 0.29069767441860467,
+      "grad_norm": 1.706489075036192,
+      "learning_rate": 2e-06,
+      "loss": 0.5837,
+      "step": 150
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.6008690300286739,
+      "learning_rate": 2e-06,
+      "loss": 0.5824,
+      "step": 160
+    },
+    {
+      "epoch": 0.32945736434108525,
+      "grad_norm": 1.7784490780851796,
+      "learning_rate": 2e-06,
+      "loss": 0.5776,
+      "step": 170
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 1.4254130054140608,
+      "learning_rate": 2e-06,
+      "loss": 0.5817,
+      "step": 180
+    },
+    {
+      "epoch": 0.3682170542635659,
+      "grad_norm": 1.4517537061348775,
+      "learning_rate": 2e-06,
+      "loss": 0.5745,
+      "step": 190
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 1.421098096153975,
+      "learning_rate": 2e-06,
+      "loss": 0.5822,
+      "step": 200
+    },
+    {
+      "epoch": 0.4069767441860465,
+      "grad_norm": 1.4340247949454419,
+      "learning_rate": 2e-06,
+      "loss": 0.5803,
+      "step": 210
+    },
+    {
+      "epoch": 0.4263565891472868,
+      "grad_norm": 1.2607995600168784,
+      "learning_rate": 2e-06,
+      "loss": 0.5683,
+      "step": 220
+    },
+    {
+      "epoch": 0.44573643410852715,
+      "grad_norm": 1.4088258448752224,
+      "learning_rate": 2e-06,
+      "loss": 0.5669,
+      "step": 230
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.4547922751942315,
+      "learning_rate": 2e-06,
+      "loss": 0.5711,
+      "step": 240
+    },
+    {
+      "epoch": 0.4844961240310077,
+      "grad_norm": 1.3166116102995473,
+      "learning_rate": 2e-06,
+      "loss": 0.5715,
+      "step": 250
+    },
+    {
+      "epoch": 0.5038759689922481,
+      "grad_norm": 1.2865076146935452,
+      "learning_rate": 2e-06,
+      "loss": 0.5706,
+      "step": 260
+    },
+    {
+      "epoch": 0.5232558139534884,
+      "grad_norm": 1.9514850118526776,
+      "learning_rate": 2e-06,
+      "loss": 0.5711,
+      "step": 270
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.3656201312041214,
+      "learning_rate": 2e-06,
+      "loss": 0.5665,
+      "step": 280
+    },
+    {
+      "epoch": 0.562015503875969,
+      "grad_norm": 1.2117280702790532,
+      "learning_rate": 2e-06,
+      "loss": 0.5685,
+      "step": 290
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 1.5936964457861214,
+      "learning_rate": 2e-06,
+      "loss": 0.5767,
+      "step": 300
+    },
+    {
+      "epoch": 0.6007751937984496,
+      "grad_norm": 1.262836540024248,
+      "learning_rate": 2e-06,
+      "loss": 0.5639,
+      "step": 310
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.5253983364542758,
+      "learning_rate": 2e-06,
+      "loss": 0.5613,
+      "step": 320
+    },
+    {
+      "epoch": 0.6395348837209303,
+      "grad_norm": 1.695119554349292,
+      "learning_rate": 2e-06,
+      "loss": 0.5629,
+      "step": 330
+    },
+    {
+      "epoch": 0.6589147286821705,
+      "grad_norm": 1.2779875033648296,
+      "learning_rate": 2e-06,
+      "loss": 0.5591,
+      "step": 340
+    },
+    {
+      "epoch": 0.6782945736434108,
+      "grad_norm": 1.6166948739589506,
+      "learning_rate": 2e-06,
+      "loss": 0.5561,
+      "step": 350
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.3469984241923647,
+      "learning_rate": 2e-06,
+      "loss": 0.561,
+      "step": 360
+    },
+    {
+      "epoch": 0.7170542635658915,
+      "grad_norm": 1.2982439077151307,
+      "learning_rate": 2e-06,
+      "loss": 0.5662,
+      "step": 370
+    },
+    {
+      "epoch": 0.7364341085271318,
+      "grad_norm": 1.3681013360427425,
+      "learning_rate": 2e-06,
+      "loss": 0.5671,
+      "step": 380
+    },
+    {
+      "epoch": 0.7558139534883721,
+      "grad_norm": 1.2116770625468472,
+      "learning_rate": 2e-06,
+      "loss": 0.5568,
+      "step": 390
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.433614262268133,
+      "learning_rate": 2e-06,
+      "loss": 0.5581,
+      "step": 400
+    },
+    {
+      "epoch": 0.7945736434108527,
+      "grad_norm": 1.1848821794193687,
+      "learning_rate": 2e-06,
+      "loss": 0.5637,
+      "step": 410
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.3158386135055107,
+      "learning_rate": 2e-06,
+      "loss": 0.5582,
+      "step": 420
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.3927036985893504,
+      "learning_rate": 2e-06,
+      "loss": 0.5612,
+      "step": 430
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.1806090504426345,
+      "learning_rate": 2e-06,
+      "loss": 0.5588,
+      "step": 440
+    },
+    {
+      "epoch": 0.872093023255814,
+      "grad_norm": 1.2223208556627352,
+      "learning_rate": 2e-06,
+      "loss": 0.5621,
+      "step": 450
+    },
+    {
+      "epoch": 0.8914728682170543,
+      "grad_norm": 1.1512657163820463,
+      "learning_rate": 2e-06,
+      "loss": 0.5513,
+      "step": 460
+    },
+    {
+      "epoch": 0.9108527131782945,
+      "grad_norm": 1.1826527683444463,
+      "learning_rate": 2e-06,
+      "loss": 0.5577,
+      "step": 470
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.578741070129489,
+      "learning_rate": 2e-06,
+      "loss": 0.5584,
+      "step": 480
+    },
+    {
+      "epoch": 0.9496124031007752,
+      "grad_norm": 1.364010417258464,
+      "learning_rate": 2e-06,
+      "loss": 0.5517,
+      "step": 490
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 1.564561079833014,
+      "learning_rate": 2e-06,
+      "loss": 0.5528,
+      "step": 500
+    },
+    {
+      "epoch": 0.9883720930232558,
+      "grad_norm": 1.1934813597924194,
+      "learning_rate": 2e-06,
+      "loss": 0.5573,
+      "step": 510
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 2.2183985963794735,
+      "learning_rate": 2e-06,
+      "loss": 0.5359,
+      "step": 520
+    },
+    {
+      "epoch": 1.0271317829457365,
+      "grad_norm": 1.444929607797708,
+      "learning_rate": 2e-06,
+      "loss": 0.5096,
+      "step": 530
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 1.3333146357476189,
+      "learning_rate": 2e-06,
+      "loss": 0.5072,
+      "step": 540
+    },
+    {
+      "epoch": 1.0658914728682172,
+      "grad_norm": 1.1259644665340547,
+      "learning_rate": 2e-06,
+      "loss": 0.5052,
+      "step": 550
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.4403172490091567,
+      "learning_rate": 2e-06,
+      "loss": 0.5169,
+      "step": 560
+    },
+    {
+      "epoch": 1.1046511627906976,
+      "grad_norm": 1.157835174296272,
+      "learning_rate": 2e-06,
+      "loss": 0.5102,
+      "step": 570
+    },
+    {
+      "epoch": 1.124031007751938,
+      "grad_norm": 1.1960407146223624,
+      "learning_rate": 2e-06,
+      "loss": 0.5038,
+      "step": 580
+    },
+    {
+      "epoch": 1.1434108527131783,
+      "grad_norm": 1.253507090792846,
+      "learning_rate": 2e-06,
+      "loss": 0.5034,
+      "step": 590
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.2979047842512628,
+      "learning_rate": 2e-06,
+      "loss": 0.5038,
+      "step": 600
+    },
+    {
+      "epoch": 1.1821705426356588,
+      "grad_norm": 1.2576281990523717,
+      "learning_rate": 2e-06,
+      "loss": 0.5137,
+      "step": 610
+    },
+    {
+      "epoch": 1.2015503875968991,
+      "grad_norm": 1.2748802075166439,
+      "learning_rate": 2e-06,
+      "loss": 0.5076,
+      "step": 620
+    },
+    {
+      "epoch": 1.2209302325581395,
+      "grad_norm": 1.5223812042187916,
+      "learning_rate": 2e-06,
+      "loss": 0.5077,
+      "step": 630
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.3632540604107077,
+      "learning_rate": 2e-06,
+      "loss": 0.5083,
+      "step": 640
+    },
+    {
+      "epoch": 1.2596899224806202,
+      "grad_norm": 1.2321831811826818,
+      "learning_rate": 2e-06,
+      "loss": 0.5096,
+      "step": 650
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.3323190632353188,
+      "learning_rate": 2e-06,
+      "loss": 0.5063,
+      "step": 660
+    },
+    {
+      "epoch": 1.2984496124031009,
+      "grad_norm": 1.2066604050023704,
+      "learning_rate": 2e-06,
+      "loss": 0.5122,
+      "step": 670
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 1.186727847270962,
+      "learning_rate": 2e-06,
+      "loss": 0.5121,
+      "step": 680
+    },
+    {
+      "epoch": 1.3372093023255813,
+      "grad_norm": 1.397263671569467,
+      "learning_rate": 2e-06,
+      "loss": 0.5089,
+      "step": 690
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 1.573664700028339,
+      "learning_rate": 2e-06,
+      "loss": 0.5099,
+      "step": 700
+    },
+    {
+      "epoch": 1.375968992248062,
+      "grad_norm": 1.4467914138897073,
+      "learning_rate": 2e-06,
+      "loss": 0.5134,
+      "step": 710
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.3706902755992394,
+      "learning_rate": 2e-06,
+      "loss": 0.5123,
+      "step": 720
+    },
+    {
+      "epoch": 1.4147286821705427,
+      "grad_norm": 1.2411084475779852,
+      "learning_rate": 2e-06,
+      "loss": 0.5078,
+      "step": 730
+    },
+    {
+      "epoch": 1.4341085271317828,
+      "grad_norm": 1.5902510539142722,
+      "learning_rate": 2e-06,
+      "loss": 0.5137,
+      "step": 740
+    },
+    {
+      "epoch": 1.4534883720930232,
+      "grad_norm": 1.7787034613442634,
+      "learning_rate": 2e-06,
+      "loss": 0.5094,
+      "step": 750
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 1.2787619752439543,
+      "learning_rate": 2e-06,
+      "loss": 0.5063,
+      "step": 760
+    },
+    {
+      "epoch": 1.4922480620155039,
+      "grad_norm": 1.2898677794347344,
+      "learning_rate": 2e-06,
+      "loss": 0.5097,
+      "step": 770
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.2320340010541546,
+      "learning_rate": 2e-06,
+      "loss": 0.5127,
+      "step": 780
+    },
+    {
+      "epoch": 1.5310077519379846,
+      "grad_norm": 1.1998558863263413,
+      "learning_rate": 2e-06,
+      "loss": 0.5097,
+      "step": 790
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 1.2491228211939762,
+      "learning_rate": 2e-06,
+      "loss": 0.507,
+      "step": 800
+    },
+    {
+      "epoch": 1.5697674418604652,
+      "grad_norm": 1.2235970378609549,
+      "learning_rate": 2e-06,
+      "loss": 0.5052,
+      "step": 810
+    },
+    {
+      "epoch": 1.5891472868217056,
+      "grad_norm": 1.4176990973616905,
+      "learning_rate": 2e-06,
+      "loss": 0.5039,
+      "step": 820
+    },
+    {
+      "epoch": 1.6085271317829457,
+      "grad_norm": 1.3149977315253063,
+      "learning_rate": 2e-06,
+      "loss": 0.512,
+      "step": 830
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.2333272112594988,
+      "learning_rate": 2e-06,
+      "loss": 0.5066,
+      "step": 840
+    },
+    {
+      "epoch": 1.6472868217054264,
+      "grad_norm": 1.1574106550887124,
+      "learning_rate": 2e-06,
+      "loss": 0.5113,
+      "step": 850
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.418576038122765,
+      "learning_rate": 2e-06,
+      "loss": 0.5137,
+      "step": 860
+    },
+    {
+      "epoch": 1.6860465116279069,
+      "grad_norm": 1.187391106828372,
+      "learning_rate": 2e-06,
+      "loss": 0.506,
+      "step": 870
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 1.170649147011855,
+      "learning_rate": 2e-06,
+      "loss": 0.5107,
+      "step": 880
+    },
+    {
+      "epoch": 1.7248062015503876,
+      "grad_norm": 1.3798145976951228,
+      "learning_rate": 2e-06,
+      "loss": 0.5099,
+      "step": 890
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 1.725987629268818,
+      "learning_rate": 2e-06,
+      "loss": 0.5139,
+      "step": 900
+    },
+    {
+      "epoch": 1.7635658914728682,
+      "grad_norm": 1.8813904948358928,
+      "learning_rate": 2e-06,
+      "loss": 0.5059,
+      "step": 910
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.8516754910417244,
+      "learning_rate": 2e-06,
+      "loss": 0.5088,
+      "step": 920
+    },
+    {
+      "epoch": 1.802325581395349,
+      "grad_norm": 1.2095051182172416,
+      "learning_rate": 2e-06,
+      "loss": 0.5096,
+      "step": 930
+    },
+    {
+      "epoch": 1.8217054263565893,
+      "grad_norm": 1.2435069711568396,
+      "learning_rate": 2e-06,
+      "loss": 0.5077,
+      "step": 940
+    },
+    {
+      "epoch": 1.8410852713178296,
+      "grad_norm": 1.3586556706802664,
+      "learning_rate": 2e-06,
+      "loss": 0.5102,
+      "step": 950
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.1979327298252027,
+      "learning_rate": 2e-06,
+      "loss": 0.512,
+      "step": 960
+    },
+    {
+      "epoch": 1.87984496124031,
+      "grad_norm": 1.7904993765105046,
+      "learning_rate": 2e-06,
+      "loss": 0.5096,
+      "step": 970
+    },
+    {
+      "epoch": 1.8992248062015504,
+      "grad_norm": 1.377601184927356,
+      "learning_rate": 2e-06,
+      "loss": 0.5057,
+      "step": 980
+    },
+    {
+      "epoch": 1.9186046511627906,
+      "grad_norm": 1.1816932854326225,
+      "learning_rate": 2e-06,
+      "loss": 0.5118,
+      "step": 990
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 1.235638000745403,
+      "learning_rate": 2e-06,
+      "loss": 0.5092,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9573643410852712,
+      "grad_norm": 1.2730535171048605,
+      "learning_rate": 2e-06,
+      "loss": 0.5104,
+      "step": 1010
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 1.2382473568182877,
+      "learning_rate": 2e-06,
+      "loss": 0.5059,
+      "step": 1020
+    },
+    {
+      "epoch": 1.996124031007752,
+      "grad_norm": 1.2856863827108878,
+      "learning_rate": 2e-06,
+      "loss": 0.51,
+      "step": 1030
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 1.6836529854231972,
+      "learning_rate": 2e-06,
+      "loss": 0.4603,
+      "step": 1040
+    },
+    {
+      "epoch": 2.0348837209302326,
+      "grad_norm": 1.4922089047807388,
+      "learning_rate": 2e-06,
+      "loss": 0.4585,
+      "step": 1050
+    },
+    {
+      "epoch": 2.054263565891473,
+      "grad_norm": 1.3990249605527378,
+      "learning_rate": 2e-06,
+      "loss": 0.4571,
+      "step": 1060
+    },
+    {
+      "epoch": 2.0736434108527133,
+      "grad_norm": 1.5500783972286114,
+      "learning_rate": 2e-06,
+      "loss": 0.4591,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.4063766317234851,
+      "learning_rate": 2e-06,
+      "loss": 0.4537,
+      "step": 1080
+    },
+    {
+      "epoch": 2.112403100775194,
+      "grad_norm": 1.4498154054826256,
+      "learning_rate": 2e-06,
+      "loss": 0.4567,
+      "step": 1090
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 1.4659238804284036,
+      "learning_rate": 2e-06,
+      "loss": 0.4564,
+      "step": 1100
+    },
+    {
+      "epoch": 2.1511627906976742,
+      "grad_norm": 1.4331071288445956,
+      "learning_rate": 2e-06,
+      "loss": 0.4597,
+      "step": 1110
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 1.2265580968692957,
+      "learning_rate": 2e-06,
+      "loss": 0.4613,
+      "step": 1120
+    },
+    {
+      "epoch": 2.189922480620155,
+      "grad_norm": 1.430430093258902,
+      "learning_rate": 2e-06,
+      "loss": 0.4582,
+      "step": 1130
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 1.3191685780949374,
+      "learning_rate": 2e-06,
+      "loss": 0.4567,
+      "step": 1140
+    },
+    {
+      "epoch": 2.2286821705426356,
+      "grad_norm": 1.4143557981830728,
+      "learning_rate": 2e-06,
+      "loss": 0.4593,
+      "step": 1150
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 1.2038927572265354,
+      "learning_rate": 2e-06,
+      "loss": 0.4571,
+      "step": 1160
+    },
+    {
+      "epoch": 2.2674418604651163,
+      "grad_norm": 1.5101700084835745,
+      "learning_rate": 2e-06,
+      "loss": 0.4576,
+      "step": 1170
+    },
+    {
+      "epoch": 2.2868217054263567,
+      "grad_norm": 1.3238249446175274,
+      "learning_rate": 2e-06,
+      "loss": 0.4648,
+      "step": 1180
+    },
+    {
+      "epoch": 2.306201550387597,
+      "grad_norm": 1.4453440150118313,
+      "learning_rate": 2e-06,
+      "loss": 0.46,
+      "step": 1190
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 1.291302766406732,
+      "learning_rate": 2e-06,
+      "loss": 0.4564,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3449612403100777,
+      "grad_norm": 1.3371668345858843,
+      "learning_rate": 2e-06,
+      "loss": 0.4605,
+      "step": 1210
+    },
+    {
+      "epoch": 2.3643410852713176,
+      "grad_norm": 1.4583613955952517,
+      "learning_rate": 2e-06,
+      "loss": 0.4639,
+      "step": 1220
+    },
+    {
+      "epoch": 2.383720930232558,
+      "grad_norm": 1.3603243092911215,
+      "learning_rate": 2e-06,
+      "loss": 0.4591,
+      "step": 1230
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 1.4381588797038276,
+      "learning_rate": 2e-06,
+      "loss": 0.4654,
+      "step": 1240
+    },
+    {
+      "epoch": 2.4224806201550386,
+      "grad_norm": 1.2897514442264095,
+      "learning_rate": 2e-06,
+      "loss": 0.46,
+      "step": 1250
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 1.4149740934308317,
+      "learning_rate": 2e-06,
+      "loss": 0.462,
+      "step": 1260
+    },
+    {
+      "epoch": 2.4612403100775193,
+      "grad_norm": 1.2334708007117,
+      "learning_rate": 2e-06,
+      "loss": 0.4636,
+      "step": 1270
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 1.3277525646372448,
+      "learning_rate": 2e-06,
+      "loss": 0.4637,
+      "step": 1280
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.341129908785728,
+      "learning_rate": 2e-06,
+      "loss": 0.4572,
+      "step": 1290
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 1.2028868010871578,
+      "learning_rate": 2e-06,
+      "loss": 0.4643,
+      "step": 1300
+    },
+    {
+      "epoch": 2.5387596899224807,
+      "grad_norm": 1.2788628805207698,
+      "learning_rate": 2e-06,
+      "loss": 0.458,
+      "step": 1310
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.1964555955603347,
+      "learning_rate": 2e-06,
+      "loss": 0.4702,
+      "step": 1320
+    },
+    {
+      "epoch": 2.5775193798449614,
+      "grad_norm": 1.2630513178641603,
+      "learning_rate": 2e-06,
+      "loss": 0.4622,
+      "step": 1330
+    },
+    {
+      "epoch": 2.5968992248062017,
+      "grad_norm": 1.4987867600057845,
+      "learning_rate": 2e-06,
+      "loss": 0.4708,
+      "step": 1340
+    },
+    {
+      "epoch": 2.616279069767442,
+      "grad_norm": 1.328908367081974,
+      "learning_rate": 2e-06,
+      "loss": 0.4622,
+      "step": 1350
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 1.572958887182858,
+      "learning_rate": 2e-06,
+      "loss": 0.459,
+      "step": 1360
+    },
+    {
+      "epoch": 2.6550387596899228,
+      "grad_norm": 1.2305373948782317,
+      "learning_rate": 2e-06,
+      "loss": 0.4597,
+      "step": 1370
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 1.231294042248163,
+      "learning_rate": 2e-06,
+      "loss": 0.468,
+      "step": 1380
+    },
+    {
+      "epoch": 2.693798449612403,
+      "grad_norm": 1.2696874963913714,
+      "learning_rate": 2e-06,
+      "loss": 0.4598,
+      "step": 1390
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 1.2272319783021322,
+      "learning_rate": 2e-06,
+      "loss": 0.4678,
+      "step": 1400
+    },
+    {
+      "epoch": 2.7325581395348837,
+      "grad_norm": 1.3352293934792803,
+      "learning_rate": 2e-06,
+      "loss": 0.4594,
+      "step": 1410
+    },
+    {
+      "epoch": 2.751937984496124,
+      "grad_norm": 1.306891032131746,
+      "learning_rate": 2e-06,
+      "loss": 0.4613,
+      "step": 1420
+    },
+    {
+      "epoch": 2.7713178294573644,
+      "grad_norm": 1.2665315216624808,
+      "learning_rate": 2e-06,
+      "loss": 0.4667,
+      "step": 1430
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 1.3240308251203166,
+      "learning_rate": 2e-06,
+      "loss": 0.4656,
+      "step": 1440
+    },
+    {
+      "epoch": 2.810077519379845,
+      "grad_norm": 1.4793024854316217,
+      "learning_rate": 2e-06,
+      "loss": 0.463,
+      "step": 1450
+    },
+    {
+      "epoch": 2.8294573643410854,
+      "grad_norm": 1.4217782757634918,
+      "learning_rate": 2e-06,
+      "loss": 0.4703,
+      "step": 1460
+    },
+    {
+      "epoch": 2.8488372093023253,
+      "grad_norm": 1.2290713413876615,
+      "learning_rate": 2e-06,
+      "loss": 0.4661,
+      "step": 1470
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 1.4408298205910421,
+      "learning_rate": 2e-06,
+      "loss": 0.4667,
+      "step": 1480
+    },
+    {
+      "epoch": 2.887596899224806,
+      "grad_norm": 1.4463509582697884,
+      "learning_rate": 2e-06,
+      "loss": 0.4692,
+      "step": 1490
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 1.3757313989698736,
+      "learning_rate": 2e-06,
+      "loss": 0.4585,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9263565891472867,
+      "grad_norm": 1.3950705796217753,
+      "learning_rate": 2e-06,
+      "loss": 0.4627,
+      "step": 1510
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 1.269632815277089,
+      "learning_rate": 2e-06,
+      "loss": 0.4679,
+      "step": 1520
+    },
+    {
+      "epoch": 2.9651162790697674,
+      "grad_norm": 1.3792098795510677,
+      "learning_rate": 2e-06,
+      "loss": 0.463,
+      "step": 1530
+    },
+    {
+      "epoch": 2.9844961240310077,
+      "grad_norm": 1.2723166198917764,
+      "learning_rate": 2e-06,
+      "loss": 0.468,
+      "step": 1540
+    },
+    {
+      "epoch": 3.0,
+      "step": 1548,
+      "total_flos": 2591282618695680.0,
+      "train_loss": 0.1541580106552873,
+      "train_runtime": 7454.5076,
+      "train_samples_per_second": 106.232,
+      "train_steps_per_second": 0.208
+    }
+  ],
+  "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": 2591282618695680.0,
+  "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 sha256:754d186d3c4123eed47f7cd05bda52bb4cf9e1021406a6181f16329dd48a6458
+size 7672