Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: prometheus-7b-preference
+  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. -->
+
+# prometheus-7b-preference
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3400
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3466        | 0.9996 | 1207 | 0.3400          |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9995859213250518,
+    "total_flos": 252668899491840.0,
+    "train_loss": 0.5242949779505758,
+    "train_runtime": 27497.765,
+    "train_samples": 98881,
+    "train_samples_per_second": 1.405,
+    "train_steps_per_second": 0.044
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.4"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b42df83fd3b590bbb123b2f9a65060c953d60b75b9038aec9a2b66f3563856
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99e61e3f73ecd97c3ba9f772fd993a53946cff863f7949739e32dfa2b2de594
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515ec614e6ef05b83a1b47612f4fa014413fd47c082485a60e570588e630f1ec
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "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"
+  }
+}

runs/Aug09_21-36-59_COE-CS-sv003/events.out.tfevents.1723239816.COE-CS-sv003.3443478.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca82792798d58cfc3447f91a2ca8e69bf16529278bf6a422aab201381254b011
+size 56771

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9995859213250518,
+    "total_flos": 252668899491840.0,
+    "train_loss": 0.5242949779505758,
+    "train_runtime": 27497.765,
+    "train_samples": 98881,
+    "train_samples_per_second": 1.405,
+    "train_steps_per_second": 0.044
+}

trainer_state.json

@@ -0,0 +1,1744 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9995859213250518,
+  "eval_steps": 500,
+  "global_step": 1207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008281573498964803,
+      "grad_norm": 23.327525151011056,
+      "learning_rate": 8.264462809917357e-08,
+      "loss": 1.4005,
+      "step": 1
+    },
+    {
+      "epoch": 0.004140786749482402,
+      "grad_norm": 23.258943369441326,
+      "learning_rate": 4.132231404958678e-07,
+      "loss": 1.4149,
+      "step": 5
+    },
+    {
+      "epoch": 0.008281573498964804,
+      "grad_norm": 8.596486068396079,
+      "learning_rate": 8.264462809917356e-07,
+      "loss": 1.3035,
+      "step": 10
+    },
+    {
+      "epoch": 0.012422360248447204,
+      "grad_norm": 10.471425792727166,
+      "learning_rate": 1.2396694214876035e-06,
+      "loss": 1.1551,
+      "step": 15
+    },
+    {
+      "epoch": 0.016563146997929608,
+      "grad_norm": 2.949608539181658,
+      "learning_rate": 1.6528925619834712e-06,
+      "loss": 1.01,
+      "step": 20
+    },
+    {
+      "epoch": 0.020703933747412008,
+      "grad_norm": 2.8135801377147867,
+      "learning_rate": 2.066115702479339e-06,
+      "loss": 0.9591,
+      "step": 25
+    },
+    {
+      "epoch": 0.024844720496894408,
+      "grad_norm": 2.5182522183092853,
+      "learning_rate": 2.479338842975207e-06,
+      "loss": 0.9186,
+      "step": 30
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 2.2568295476930262,
+      "learning_rate": 2.8925619834710743e-06,
+      "loss": 0.9096,
+      "step": 35
+    },
+    {
+      "epoch": 0.033126293995859216,
+      "grad_norm": 2.5218798187172196,
+      "learning_rate": 3.3057851239669424e-06,
+      "loss": 0.8779,
+      "step": 40
+    },
+    {
+      "epoch": 0.037267080745341616,
+      "grad_norm": 2.527152447671948,
+      "learning_rate": 3.71900826446281e-06,
+      "loss": 0.8818,
+      "step": 45
+    },
+    {
+      "epoch": 0.041407867494824016,
+      "grad_norm": 2.3809263568393617,
+      "learning_rate": 4.132231404958678e-06,
+      "loss": 0.8688,
+      "step": 50
+    },
+    {
+      "epoch": 0.045548654244306416,
+      "grad_norm": 2.511225291546822,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.8611,
+      "step": 55
+    },
+    {
+      "epoch": 0.049689440993788817,
+      "grad_norm": 2.3182185684474317,
+      "learning_rate": 4.958677685950414e-06,
+      "loss": 0.8508,
+      "step": 60
+    },
+    {
+      "epoch": 0.053830227743271224,
+      "grad_norm": 2.3756730633774494,
+      "learning_rate": 5.371900826446281e-06,
+      "loss": 0.855,
+      "step": 65
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 2.501349708861314,
+      "learning_rate": 5.785123966942149e-06,
+      "loss": 0.8408,
+      "step": 70
+    },
+    {
+      "epoch": 0.062111801242236024,
+      "grad_norm": 2.7274716294485617,
+      "learning_rate": 6.198347107438017e-06,
+      "loss": 0.8311,
+      "step": 75
+    },
+    {
+      "epoch": 0.06625258799171843,
+      "grad_norm": 2.473386291311923,
+      "learning_rate": 6.611570247933885e-06,
+      "loss": 0.8383,
+      "step": 80
+    },
+    {
+      "epoch": 0.07039337474120083,
+      "grad_norm": 2.366326788697712,
+      "learning_rate": 7.0247933884297525e-06,
+      "loss": 0.8309,
+      "step": 85
+    },
+    {
+      "epoch": 0.07453416149068323,
+      "grad_norm": 2.5315630281263335,
+      "learning_rate": 7.43801652892562e-06,
+      "loss": 0.8209,
+      "step": 90
+    },
+    {
+      "epoch": 0.07867494824016563,
+      "grad_norm": 2.589584428395013,
+      "learning_rate": 7.851239669421489e-06,
+      "loss": 0.8161,
+      "step": 95
+    },
+    {
+      "epoch": 0.08281573498964803,
+      "grad_norm": 2.9536546546217264,
+      "learning_rate": 8.264462809917356e-06,
+      "loss": 0.819,
+      "step": 100
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 2.44404519233414,
+      "learning_rate": 8.677685950413224e-06,
+      "loss": 0.8124,
+      "step": 105
+    },
+    {
+      "epoch": 0.09109730848861283,
+      "grad_norm": 2.487953243973851,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.8114,
+      "step": 110
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 2.6020731071259124,
+      "learning_rate": 9.50413223140496e-06,
+      "loss": 0.7995,
+      "step": 115
+    },
+    {
+      "epoch": 0.09937888198757763,
+      "grad_norm": 2.3960060410854966,
+      "learning_rate": 9.917355371900828e-06,
+      "loss": 0.795,
+      "step": 120
+    },
+    {
+      "epoch": 0.10351966873706005,
+      "grad_norm": 2.4423780661726817,
+      "learning_rate": 9.999665269535307e-06,
+      "loss": 0.7988,
+      "step": 125
+    },
+    {
+      "epoch": 0.10766045548654245,
+      "grad_norm": 2.570173600121692,
+      "learning_rate": 9.998305503833872e-06,
+      "loss": 0.7761,
+      "step": 130
+    },
+    {
+      "epoch": 0.11180124223602485,
+      "grad_norm": 2.3986936359278,
+      "learning_rate": 9.995900066492902e-06,
+      "loss": 0.7839,
+      "step": 135
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 2.487706091670238,
+      "learning_rate": 9.992449460742464e-06,
+      "loss": 0.7864,
+      "step": 140
+    },
+    {
+      "epoch": 0.12008281573498965,
+      "grad_norm": 2.2343649680910596,
+      "learning_rate": 9.98795440846732e-06,
+      "loss": 0.7654,
+      "step": 145
+    },
+    {
+      "epoch": 0.12422360248447205,
+      "grad_norm": 2.4156685822084785,
+      "learning_rate": 9.982415850055902e-06,
+      "loss": 0.7686,
+      "step": 150
+    },
+    {
+      "epoch": 0.12836438923395446,
+      "grad_norm": 2.5259231738748356,
+      "learning_rate": 9.975834944203581e-06,
+      "loss": 0.7751,
+      "step": 155
+    },
+    {
+      "epoch": 0.13250517598343686,
+      "grad_norm": 2.3772530672985326,
+      "learning_rate": 9.968213067670265e-06,
+      "loss": 0.7445,
+      "step": 160
+    },
+    {
+      "epoch": 0.13664596273291926,
+      "grad_norm": 2.2859422135364107,
+      "learning_rate": 9.959551814992364e-06,
+      "loss": 0.7547,
+      "step": 165
+    },
+    {
+      "epoch": 0.14078674948240166,
+      "grad_norm": 2.5122248077169984,
+      "learning_rate": 9.949852998149217e-06,
+      "loss": 0.7585,
+      "step": 170
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 2.4905596534144268,
+      "learning_rate": 9.939118646184007e-06,
+      "loss": 0.7467,
+      "step": 175
+    },
+    {
+      "epoch": 0.14906832298136646,
+      "grad_norm": 2.486536604984542,
+      "learning_rate": 9.927351004779275e-06,
+      "loss": 0.7388,
+      "step": 180
+    },
+    {
+      "epoch": 0.15320910973084886,
+      "grad_norm": 2.9785597879261174,
+      "learning_rate": 9.914552535787122e-06,
+      "loss": 0.7302,
+      "step": 185
+    },
+    {
+      "epoch": 0.15734989648033126,
+      "grad_norm": 2.3058286602799427,
+      "learning_rate": 9.900725916714157e-06,
+      "loss": 0.7314,
+      "step": 190
+    },
+    {
+      "epoch": 0.16149068322981366,
+      "grad_norm": 2.5472246179561737,
+      "learning_rate": 9.885874040161373e-06,
+      "loss": 0.7286,
+      "step": 195
+    },
+    {
+      "epoch": 0.16563146997929606,
+      "grad_norm": 2.279293729274078,
+      "learning_rate": 9.87000001321898e-06,
+      "loss": 0.7183,
+      "step": 200
+    },
+    {
+      "epoch": 0.16977225672877846,
+      "grad_norm": 2.3921354483270445,
+      "learning_rate": 9.853107156816393e-06,
+      "loss": 0.7134,
+      "step": 205
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 2.3525551445639024,
+      "learning_rate": 9.835199005027477e-06,
+      "loss": 0.7221,
+      "step": 210
+    },
+    {
+      "epoch": 0.17805383022774326,
+      "grad_norm": 2.3800199876143884,
+      "learning_rate": 9.816279304331202e-06,
+      "loss": 0.7183,
+      "step": 215
+    },
+    {
+      "epoch": 0.18219461697722567,
+      "grad_norm": 2.229750773842239,
+      "learning_rate": 9.79635201282785e-06,
+      "loss": 0.7194,
+      "step": 220
+    },
+    {
+      "epoch": 0.18633540372670807,
+      "grad_norm": 2.299300141984987,
+      "learning_rate": 9.775421299410977e-06,
+      "loss": 0.7068,
+      "step": 225
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 2.4470455330242022,
+      "learning_rate": 9.753491542895237e-06,
+      "loss": 0.6965,
+      "step": 230
+    },
+    {
+      "epoch": 0.19461697722567287,
+      "grad_norm": 2.4108850288342416,
+      "learning_rate": 9.730567331100333e-06,
+      "loss": 0.6961,
+      "step": 235
+    },
+    {
+      "epoch": 0.19875776397515527,
+      "grad_norm": 2.2444903738856166,
+      "learning_rate": 9.706653459891207e-06,
+      "loss": 0.695,
+      "step": 240
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 2.3716649705516613,
+      "learning_rate": 9.681754932174719e-06,
+      "loss": 0.6851,
+      "step": 245
+    },
+    {
+      "epoch": 0.2070393374741201,
+      "grad_norm": 2.3143450163448374,
+      "learning_rate": 9.655876956853025e-06,
+      "loss": 0.6876,
+      "step": 250
+    },
+    {
+      "epoch": 0.2111801242236025,
+      "grad_norm": 2.409260444364719,
+      "learning_rate": 9.629024947733836e-06,
+      "loss": 0.6788,
+      "step": 255
+    },
+    {
+      "epoch": 0.2153209109730849,
+      "grad_norm": 2.2610337983169657,
+      "learning_rate": 9.601204522397826e-06,
+      "loss": 0.6754,
+      "step": 260
+    },
+    {
+      "epoch": 0.2194616977225673,
+      "grad_norm": 2.340354580101845,
+      "learning_rate": 9.572421501023403e-06,
+      "loss": 0.6875,
+      "step": 265
+    },
+    {
+      "epoch": 0.2236024844720497,
+      "grad_norm": 2.367203272779439,
+      "learning_rate": 9.5426819051691e-06,
+      "loss": 0.6698,
+      "step": 270
+    },
+    {
+      "epoch": 0.2277432712215321,
+      "grad_norm": 2.4354443343778356,
+      "learning_rate": 9.511991956513828e-06,
+      "loss": 0.6737,
+      "step": 275
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 2.3653987155446528,
+      "learning_rate": 9.480358075555278e-06,
+      "loss": 0.6534,
+      "step": 280
+    },
+    {
+      "epoch": 0.2360248447204969,
+      "grad_norm": 2.463110193099795,
+      "learning_rate": 9.447786880266706e-06,
+      "loss": 0.6793,
+      "step": 285
+    },
+    {
+      "epoch": 0.2401656314699793,
+      "grad_norm": 2.356291601187774,
+      "learning_rate": 9.414285184712432e-06,
+      "loss": 0.6482,
+      "step": 290
+    },
+    {
+      "epoch": 0.2443064182194617,
+      "grad_norm": 2.448482745822932,
+      "learning_rate": 9.37985999762229e-06,
+      "loss": 0.6537,
+      "step": 295
+    },
+    {
+      "epoch": 0.2484472049689441,
+      "grad_norm": 2.167053624005552,
+      "learning_rate": 9.344518520925377e-06,
+      "loss": 0.6395,
+      "step": 300
+    },
+    {
+      "epoch": 0.2525879917184265,
+      "grad_norm": 2.224339535064626,
+      "learning_rate": 9.308268148243355e-06,
+      "loss": 0.6293,
+      "step": 305
+    },
+    {
+      "epoch": 0.2567287784679089,
+      "grad_norm": 2.214031822614262,
+      "learning_rate": 9.271116463343692e-06,
+      "loss": 0.6374,
+      "step": 310
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 2.8051942047743235,
+      "learning_rate": 9.23307123855307e-06,
+      "loss": 0.6313,
+      "step": 315
+    },
+    {
+      "epoch": 0.2650103519668737,
+      "grad_norm": 2.363326927922635,
+      "learning_rate": 9.194140433131397e-06,
+      "loss": 0.6324,
+      "step": 320
+    },
+    {
+      "epoch": 0.2691511387163561,
+      "grad_norm": 2.5833993381945124,
+      "learning_rate": 9.154332191606671e-06,
+      "loss": 0.6096,
+      "step": 325
+    },
+    {
+      "epoch": 0.2732919254658385,
+      "grad_norm": 2.5023763345607244,
+      "learning_rate": 9.113654842071114e-06,
+      "loss": 0.6331,
+      "step": 330
+    },
+    {
+      "epoch": 0.2774327122153209,
+      "grad_norm": 2.2756476411928954,
+      "learning_rate": 9.072116894438885e-06,
+      "loss": 0.6102,
+      "step": 335
+    },
+    {
+      "epoch": 0.2815734989648033,
+      "grad_norm": 2.2883976811600886,
+      "learning_rate": 9.029727038665765e-06,
+      "loss": 0.6196,
+      "step": 340
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 2.4045467670456024,
+      "learning_rate": 8.986494142931168e-06,
+      "loss": 0.6053,
+      "step": 345
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 2.411121438317645,
+      "learning_rate": 8.94242725178288e-06,
+      "loss": 0.6191,
+      "step": 350
+    },
+    {
+      "epoch": 0.2939958592132505,
+      "grad_norm": 2.2437917822304505,
+      "learning_rate": 8.89753558424488e-06,
+      "loss": 0.5877,
+      "step": 355
+    },
+    {
+      "epoch": 0.2981366459627329,
+      "grad_norm": 2.594060420622693,
+      "learning_rate": 8.851828531888692e-06,
+      "loss": 0.6023,
+      "step": 360
+    },
+    {
+      "epoch": 0.3022774327122153,
+      "grad_norm": 2.671644595885512,
+      "learning_rate": 8.805315656868587e-06,
+      "loss": 0.6078,
+      "step": 365
+    },
+    {
+      "epoch": 0.3064182194616977,
+      "grad_norm": 2.2680229592309695,
+      "learning_rate": 8.75800668992117e-06,
+      "loss": 0.59,
+      "step": 370
+    },
+    {
+      "epoch": 0.3105590062111801,
+      "grad_norm": 2.197781067793621,
+      "learning_rate": 8.709911528329623e-06,
+      "loss": 0.5923,
+      "step": 375
+    },
+    {
+      "epoch": 0.3146997929606625,
+      "grad_norm": 2.0913374258858495,
+      "learning_rate": 8.661040233853166e-06,
+      "loss": 0.589,
+      "step": 380
+    },
+    {
+      "epoch": 0.3188405797101449,
+      "grad_norm": 2.2014541423571043,
+      "learning_rate": 8.611403030622074e-06,
+      "loss": 0.5822,
+      "step": 385
+    },
+    {
+      "epoch": 0.32298136645962733,
+      "grad_norm": 2.261196085234065,
+      "learning_rate": 8.561010302998734e-06,
+      "loss": 0.564,
+      "step": 390
+    },
+    {
+      "epoch": 0.32712215320910976,
+      "grad_norm": 2.23730484550207,
+      "learning_rate": 8.509872593405189e-06,
+      "loss": 0.5645,
+      "step": 395
+    },
+    {
+      "epoch": 0.33126293995859213,
+      "grad_norm": 2.2692143055291063,
+      "learning_rate": 8.458000600117604e-06,
+      "loss": 0.5776,
+      "step": 400
+    },
+    {
+      "epoch": 0.33540372670807456,
+      "grad_norm": 2.3234912814206226,
+      "learning_rate": 8.40540517502813e-06,
+      "loss": 0.5827,
+      "step": 405
+    },
+    {
+      "epoch": 0.33954451345755693,
+      "grad_norm": 2.6596848933224146,
+      "learning_rate": 8.35209732137463e-06,
+      "loss": 0.5669,
+      "step": 410
+    },
+    {
+      "epoch": 0.34368530020703936,
+      "grad_norm": 2.170663333128378,
+      "learning_rate": 8.298088191438753e-06,
+      "loss": 0.5707,
+      "step": 415
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 2.3379705431469815,
+      "learning_rate": 8.243389084212808e-06,
+      "loss": 0.5633,
+      "step": 420
+    },
+    {
+      "epoch": 0.35196687370600416,
+      "grad_norm": 2.2304485025883194,
+      "learning_rate": 8.188011443035962e-06,
+      "loss": 0.5528,
+      "step": 425
+    },
+    {
+      "epoch": 0.35610766045548653,
+      "grad_norm": 2.190979894629082,
+      "learning_rate": 8.131966853200226e-06,
+      "loss": 0.56,
+      "step": 430
+    },
+    {
+      "epoch": 0.36024844720496896,
+      "grad_norm": 2.4413883194284915,
+      "learning_rate": 8.075267039526764e-06,
+      "loss": 0.5563,
+      "step": 435
+    },
+    {
+      "epoch": 0.36438923395445133,
+      "grad_norm": 2.14891058793579,
+      "learning_rate": 8.017923863912989e-06,
+      "loss": 0.5516,
+      "step": 440
+    },
+    {
+      "epoch": 0.36853002070393376,
+      "grad_norm": 2.193120721619817,
+      "learning_rate": 7.959949322850994e-06,
+      "loss": 0.5504,
+      "step": 445
+    },
+    {
+      "epoch": 0.37267080745341613,
+      "grad_norm": 2.2245149668941595,
+      "learning_rate": 7.901355544917827e-06,
+      "loss": 0.5464,
+      "step": 450
+    },
+    {
+      "epoch": 0.37681159420289856,
+      "grad_norm": 2.3390482615587356,
+      "learning_rate": 7.842154788238124e-06,
+      "loss": 0.5464,
+      "step": 455
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 2.106177697179644,
+      "learning_rate": 7.782359437919644e-06,
+      "loss": 0.5399,
+      "step": 460
+    },
+    {
+      "epoch": 0.38509316770186336,
+      "grad_norm": 2.122296342328107,
+      "learning_rate": 7.721982003462255e-06,
+      "loss": 0.5189,
+      "step": 465
+    },
+    {
+      "epoch": 0.38923395445134573,
+      "grad_norm": 2.2344930887284944,
+      "learning_rate": 7.661035116140856e-06,
+      "loss": 0.5317,
+      "step": 470
+    },
+    {
+      "epoch": 0.39337474120082816,
+      "grad_norm": 3.733462702610377,
+      "learning_rate": 7.599531526362873e-06,
+      "loss": 0.5362,
+      "step": 475
+    },
+    {
+      "epoch": 0.39751552795031053,
+      "grad_norm": 2.2217276329657607,
+      "learning_rate": 7.537484101000787e-06,
+      "loss": 0.5145,
+      "step": 480
+    },
+    {
+      "epoch": 0.40165631469979296,
+      "grad_norm": 2.317355987149082,
+      "learning_rate": 7.474905820700334e-06,
+      "loss": 0.5235,
+      "step": 485
+    },
+    {
+      "epoch": 0.4057971014492754,
+      "grad_norm": 2.2831077300833007,
+      "learning_rate": 7.411809777164873e-06,
+      "loss": 0.5194,
+      "step": 490
+    },
+    {
+      "epoch": 0.40993788819875776,
+      "grad_norm": 2.1848755725332873,
+      "learning_rate": 7.3482091704165405e-06,
+      "loss": 0.5177,
+      "step": 495
+    },
+    {
+      "epoch": 0.4140786749482402,
+      "grad_norm": 2.156631269209744,
+      "learning_rate": 7.284117306034733e-06,
+      "loss": 0.5202,
+      "step": 500
+    },
+    {
+      "epoch": 0.41821946169772256,
+      "grad_norm": 2.1755447650720283,
+      "learning_rate": 7.219547592372512e-06,
+      "loss": 0.5128,
+      "step": 505
+    },
+    {
+      "epoch": 0.422360248447205,
+      "grad_norm": 2.08598669974358,
+      "learning_rate": 7.15451353775151e-06,
+      "loss": 0.5172,
+      "step": 510
+    },
+    {
+      "epoch": 0.42650103519668736,
+      "grad_norm": 2.16833234073926,
+      "learning_rate": 7.089028747635908e-06,
+      "loss": 0.5126,
+      "step": 515
+    },
+    {
+      "epoch": 0.4306418219461698,
+      "grad_norm": 2.1117513557765486,
+      "learning_rate": 7.023106921786118e-06,
+      "loss": 0.5084,
+      "step": 520
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 2.1996894090923096,
+      "learning_rate": 6.956761851392706e-06,
+      "loss": 0.5066,
+      "step": 525
+    },
+    {
+      "epoch": 0.4389233954451346,
+      "grad_norm": 2.19899240264073,
+      "learning_rate": 6.890007416191209e-06,
+      "loss": 0.506,
+      "step": 530
+    },
+    {
+      "epoch": 0.44306418219461696,
+      "grad_norm": 2.162714599010301,
+      "learning_rate": 6.822857581558423e-06,
+      "loss": 0.4976,
+      "step": 535
+    },
+    {
+      "epoch": 0.4472049689440994,
+      "grad_norm": 2.1084852870864914,
+      "learning_rate": 6.7553263955907755e-06,
+      "loss": 0.4918,
+      "step": 540
+    },
+    {
+      "epoch": 0.45134575569358176,
+      "grad_norm": 2.094525435495713,
+      "learning_rate": 6.687427986165379e-06,
+      "loss": 0.4889,
+      "step": 545
+    },
+    {
+      "epoch": 0.4554865424430642,
+      "grad_norm": 2.2871720115590226,
+      "learning_rate": 6.6191765579844205e-06,
+      "loss": 0.4883,
+      "step": 550
+    },
+    {
+      "epoch": 0.45962732919254656,
+      "grad_norm": 2.2666748333234157,
+      "learning_rate": 6.550586389603451e-06,
+      "loss": 0.5001,
+      "step": 555
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 2.1704201350055756,
+      "learning_rate": 6.481671830444243e-06,
+      "loss": 0.489,
+      "step": 560
+    },
+    {
+      "epoch": 0.46790890269151136,
+      "grad_norm": 2.462881842902182,
+      "learning_rate": 6.412447297792818e-06,
+      "loss": 0.4925,
+      "step": 565
+    },
+    {
+      "epoch": 0.4720496894409938,
+      "grad_norm": 2.2118284938147994,
+      "learning_rate": 6.3429272737832726e-06,
+      "loss": 0.4797,
+      "step": 570
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.271594346562813,
+      "learning_rate": 6.273126302368037e-06,
+      "loss": 0.4838,
+      "step": 575
+    },
+    {
+      "epoch": 0.4803312629399586,
+      "grad_norm": 2.031397121849161,
+      "learning_rate": 6.203058986275207e-06,
+      "loss": 0.4804,
+      "step": 580
+    },
+    {
+      "epoch": 0.484472049689441,
+      "grad_norm": 2.1980808821259012,
+      "learning_rate": 6.132739983953579e-06,
+      "loss": 0.4717,
+      "step": 585
+    },
+    {
+      "epoch": 0.4886128364389234,
+      "grad_norm": 2.1375563048782023,
+      "learning_rate": 6.062184006506027e-06,
+      "loss": 0.4755,
+      "step": 590
+    },
+    {
+      "epoch": 0.4927536231884058,
+      "grad_norm": 2.227143810312422,
+      "learning_rate": 5.991405814611855e-06,
+      "loss": 0.473,
+      "step": 595
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 2.1657589451163783,
+      "learning_rate": 5.920420215438794e-06,
+      "loss": 0.4689,
+      "step": 600
+    },
+    {
+      "epoch": 0.5010351966873706,
+      "grad_norm": 2.0699845464241298,
+      "learning_rate": 5.849242059545259e-06,
+      "loss": 0.459,
+      "step": 605
+    },
+    {
+      "epoch": 0.505175983436853,
+      "grad_norm": 2.070180087891007,
+      "learning_rate": 5.777886237773542e-06,
+      "loss": 0.4639,
+      "step": 610
+    },
+    {
+      "epoch": 0.5093167701863354,
+      "grad_norm": 2.141330722860632,
+      "learning_rate": 5.706367678134562e-06,
+      "loss": 0.451,
+      "step": 615
+    },
+    {
+      "epoch": 0.5134575569358178,
+      "grad_norm": 2.1761626984660825,
+      "learning_rate": 5.634701342684852e-06,
+      "loss": 0.467,
+      "step": 620
+    },
+    {
+      "epoch": 0.5175983436853002,
+      "grad_norm": 2.066437574044899,
+      "learning_rate": 5.562902224396416e-06,
+      "loss": 0.4511,
+      "step": 625
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 2.11017439615472,
+      "learning_rate": 5.49098534402012e-06,
+      "loss": 0.4613,
+      "step": 630
+    },
+    {
+      "epoch": 0.525879917184265,
+      "grad_norm": 2.0667579107692973,
+      "learning_rate": 5.418965746943281e-06,
+      "loss": 0.4552,
+      "step": 635
+    },
+    {
+      "epoch": 0.5300207039337475,
+      "grad_norm": 2.1203564953642684,
+      "learning_rate": 5.34685850004208e-06,
+      "loss": 0.4515,
+      "step": 640
+    },
+    {
+      "epoch": 0.5341614906832298,
+      "grad_norm": 2.1839775513140802,
+      "learning_rate": 5.2746786885295034e-06,
+      "loss": 0.4517,
+      "step": 645
+    },
+    {
+      "epoch": 0.5383022774327122,
+      "grad_norm": 2.0625277001105657,
+      "learning_rate": 5.2024414127994325e-06,
+      "loss": 0.448,
+      "step": 650
+    },
+    {
+      "epoch": 0.5424430641821946,
+      "grad_norm": 2.206189353998323,
+      "learning_rate": 5.13016178526756e-06,
+      "loss": 0.4526,
+      "step": 655
+    },
+    {
+      "epoch": 0.546583850931677,
+      "grad_norm": 2.095803088261813,
+      "learning_rate": 5.057854927209804e-06,
+      "loss": 0.4493,
+      "step": 660
+    },
+    {
+      "epoch": 0.5507246376811594,
+      "grad_norm": 2.02519967151739,
+      "learning_rate": 4.985535965598843e-06,
+      "loss": 0.4454,
+      "step": 665
+    },
+    {
+      "epoch": 0.5548654244306418,
+      "grad_norm": 2.0296722021624567,
+      "learning_rate": 4.913220029939491e-06,
+      "loss": 0.4358,
+      "step": 670
+    },
+    {
+      "epoch": 0.5590062111801242,
+      "grad_norm": 2.3083437897418473,
+      "learning_rate": 4.840922249103506e-06,
+      "loss": 0.4456,
+      "step": 675
+    },
+    {
+      "epoch": 0.5631469979296067,
+      "grad_norm": 2.0519867202746407,
+      "learning_rate": 4.7686577481645745e-06,
+      "loss": 0.431,
+      "step": 680
+    },
+    {
+      "epoch": 0.567287784679089,
+      "grad_norm": 2.1470126174135924,
+      "learning_rate": 4.696441645234042e-06,
+      "loss": 0.4379,
+      "step": 685
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2.0560745378867846,
+      "learning_rate": 4.624289048298147e-06,
+      "loss": 0.443,
+      "step": 690
+    },
+    {
+      "epoch": 0.5755693581780539,
+      "grad_norm": 1.9569113027558405,
+      "learning_rate": 4.55221505205734e-06,
+      "loss": 0.4351,
+      "step": 695
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 2.0869788254714154,
+      "learning_rate": 4.480234734768393e-06,
+      "loss": 0.4263,
+      "step": 700
+    },
+    {
+      "epoch": 0.5838509316770186,
+      "grad_norm": 2.0909397682742883,
+      "learning_rate": 4.408363155089952e-06,
+      "loss": 0.4267,
+      "step": 705
+    },
+    {
+      "epoch": 0.587991718426501,
+      "grad_norm": 2.035030817366214,
+      "learning_rate": 4.3366153489321855e-06,
+      "loss": 0.4262,
+      "step": 710
+    },
+    {
+      "epoch": 0.5921325051759835,
+      "grad_norm": 2.081280914303008,
+      "learning_rate": 4.265006326311199e-06,
+      "loss": 0.4276,
+      "step": 715
+    },
+    {
+      "epoch": 0.5962732919254659,
+      "grad_norm": 2.2311910170648637,
+      "learning_rate": 4.1935510682088545e-06,
+      "loss": 0.4239,
+      "step": 720
+    },
+    {
+      "epoch": 0.6004140786749482,
+      "grad_norm": 2.089278016051515,
+      "learning_rate": 4.122264523438668e-06,
+      "loss": 0.4224,
+      "step": 725
+    },
+    {
+      "epoch": 0.6045548654244306,
+      "grad_norm": 1.924768903143278,
+      "learning_rate": 4.051161605518453e-06,
+      "loss": 0.4135,
+      "step": 730
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 2.1572030671513325,
+      "learning_rate": 3.980257189550316e-06,
+      "loss": 0.4162,
+      "step": 735
+    },
+    {
+      "epoch": 0.6128364389233955,
+      "grad_norm": 1.994411998332086,
+      "learning_rate": 3.909566109108727e-06,
+      "loss": 0.4133,
+      "step": 740
+    },
+    {
+      "epoch": 0.6169772256728778,
+      "grad_norm": 2.0520593778378626,
+      "learning_rate": 3.839103153137247e-06,
+      "loss": 0.4187,
+      "step": 745
+    },
+    {
+      "epoch": 0.6211180124223602,
+      "grad_norm": 2.091242798091324,
+      "learning_rate": 3.768883062854598e-06,
+      "loss": 0.4123,
+      "step": 750
+    },
+    {
+      "epoch": 0.6252587991718427,
+      "grad_norm": 2.0083055108666996,
+      "learning_rate": 3.6989205286707398e-06,
+      "loss": 0.4095,
+      "step": 755
+    },
+    {
+      "epoch": 0.629399585921325,
+      "grad_norm": 2.027716271226035,
+      "learning_rate": 3.6292301871135425e-06,
+      "loss": 0.4122,
+      "step": 760
+    },
+    {
+      "epoch": 0.6335403726708074,
+      "grad_norm": 2.187794954017901,
+      "learning_rate": 3.55982661776676e-06,
+      "loss": 0.3989,
+      "step": 765
+    },
+    {
+      "epoch": 0.6376811594202898,
+      "grad_norm": 2.063462092371761,
+      "learning_rate": 3.4907243402199013e-06,
+      "loss": 0.4085,
+      "step": 770
+    },
+    {
+      "epoch": 0.6418219461697723,
+      "grad_norm": 1.9854773033540876,
+      "learning_rate": 3.4219378110306523e-06,
+      "loss": 0.4073,
+      "step": 775
+    },
+    {
+      "epoch": 0.6459627329192547,
+      "grad_norm": 1.992830135581226,
+      "learning_rate": 3.353481420700495e-06,
+      "loss": 0.4016,
+      "step": 780
+    },
+    {
+      "epoch": 0.650103519668737,
+      "grad_norm": 2.0747311476669847,
+      "learning_rate": 3.285369490664133e-06,
+      "loss": 0.4021,
+      "step": 785
+    },
+    {
+      "epoch": 0.6542443064182195,
+      "grad_norm": 2.0479726659986803,
+      "learning_rate": 3.2176162702933816e-06,
+      "loss": 0.3988,
+      "step": 790
+    },
+    {
+      "epoch": 0.6583850931677019,
+      "grad_norm": 2.1244924225668793,
+      "learning_rate": 3.150235933916115e-06,
+      "loss": 0.391,
+      "step": 795
+    },
+    {
+      "epoch": 0.6625258799171843,
+      "grad_norm": 2.026867017023864,
+      "learning_rate": 3.0832425778509235e-06,
+      "loss": 0.3942,
+      "step": 800
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.0721889345390156,
+      "learning_rate": 3.0166502174581012e-06,
+      "loss": 0.3932,
+      "step": 805
+    },
+    {
+      "epoch": 0.6708074534161491,
+      "grad_norm": 2.076264432304557,
+      "learning_rate": 2.950472784207544e-06,
+      "loss": 0.3914,
+      "step": 810
+    },
+    {
+      "epoch": 0.6749482401656315,
+      "grad_norm": 1.9834852441387247,
+      "learning_rate": 2.8847241227642255e-06,
+      "loss": 0.3965,
+      "step": 815
+    },
+    {
+      "epoch": 0.6790890269151139,
+      "grad_norm": 2.1270225026333525,
+      "learning_rate": 2.819417988091814e-06,
+      "loss": 0.3955,
+      "step": 820
+    },
+    {
+      "epoch": 0.6832298136645962,
+      "grad_norm": 2.1736828836911117,
+      "learning_rate": 2.754568042575061e-06,
+      "loss": 0.3896,
+      "step": 825
+    },
+    {
+      "epoch": 0.6873706004140787,
+      "grad_norm": 2.0644181259123817,
+      "learning_rate": 2.6901878531615677e-06,
+      "loss": 0.3841,
+      "step": 830
+    },
+    {
+      "epoch": 0.6915113871635611,
+      "grad_norm": 2.0687716790652693,
+      "learning_rate": 2.6262908885235046e-06,
+      "loss": 0.3831,
+      "step": 835
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 2.0019086355999565,
+      "learning_rate": 2.5628905162398797e-06,
+      "loss": 0.3852,
+      "step": 840
+    },
+    {
+      "epoch": 0.6997929606625258,
+      "grad_norm": 2.092418141138653,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.3919,
+      "step": 845
+    },
+    {
+      "epoch": 0.7039337474120083,
+      "grad_norm": 1.9851562014074176,
+      "learning_rate": 2.4376324968286154e-06,
+      "loss": 0.3833,
+      "step": 850
+    },
+    {
+      "epoch": 0.7080745341614907,
+      "grad_norm": 2.0158181753004976,
+      "learning_rate": 2.375801054333409e-06,
+      "loss": 0.3818,
+      "step": 855
+    },
+    {
+      "epoch": 0.7122153209109731,
+      "grad_norm": 2.033514347950001,
+      "learning_rate": 2.3145186079753685e-06,
+      "loss": 0.3813,
+      "step": 860
+    },
+    {
+      "epoch": 0.7163561076604554,
+      "grad_norm": 2.18271145418854,
+      "learning_rate": 2.253797978362617e-06,
+      "loss": 0.3878,
+      "step": 865
+    },
+    {
+      "epoch": 0.7204968944099379,
+      "grad_norm": 2.0192627128869525,
+      "learning_rate": 2.193651868568285e-06,
+      "loss": 0.3846,
+      "step": 870
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 2.0678978350650024,
+      "learning_rate": 2.1340928614729445e-06,
+      "loss": 0.372,
+      "step": 875
+    },
+    {
+      "epoch": 0.7287784679089027,
+      "grad_norm": 1.9906640969676856,
+      "learning_rate": 2.075133417132223e-06,
+      "loss": 0.3736,
+      "step": 880
+    },
+    {
+      "epoch": 0.7329192546583851,
+      "grad_norm": 1.9462665473651348,
+      "learning_rate": 2.016785870170079e-06,
+      "loss": 0.3693,
+      "step": 885
+    },
+    {
+      "epoch": 0.7370600414078675,
+      "grad_norm": 2.010463061512907,
+      "learning_rate": 1.9590624271983406e-06,
+      "loss": 0.3692,
+      "step": 890
+    },
+    {
+      "epoch": 0.7412008281573499,
+      "grad_norm": 2.0531402948964432,
+      "learning_rate": 1.9019751642630252e-06,
+      "loss": 0.37,
+      "step": 895
+    },
+    {
+      "epoch": 0.7453416149068323,
+      "grad_norm": 2.2018575972936723,
+      "learning_rate": 1.8455360243179537e-06,
+      "loss": 0.3748,
+      "step": 900
+    },
+    {
+      "epoch": 0.7494824016563147,
+      "grad_norm": 2.0239016138022468,
+      "learning_rate": 1.7897568147262323e-06,
+      "loss": 0.3663,
+      "step": 905
+    },
+    {
+      "epoch": 0.7536231884057971,
+      "grad_norm": 2.101223919549933,
+      "learning_rate": 1.7346492047900897e-06,
+      "loss": 0.363,
+      "step": 910
+    },
+    {
+      "epoch": 0.7577639751552795,
+      "grad_norm": 2.0063562256177945,
+      "learning_rate": 1.6802247233095914e-06,
+      "loss": 0.3656,
+      "step": 915
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 2.0140033980586334,
+      "learning_rate": 1.626494756170765e-06,
+      "loss": 0.3613,
+      "step": 920
+    },
+    {
+      "epoch": 0.7660455486542443,
+      "grad_norm": 2.0970932926638883,
+      "learning_rate": 1.5734705439636017e-06,
+      "loss": 0.3636,
+      "step": 925
+    },
+    {
+      "epoch": 0.7701863354037267,
+      "grad_norm": 2.0036334089923176,
+      "learning_rate": 1.5211631796304721e-06,
+      "loss": 0.3646,
+      "step": 930
+    },
+    {
+      "epoch": 0.7743271221532091,
+      "grad_norm": 1.9781895967841074,
+      "learning_rate": 1.46958360614543e-06,
+      "loss": 0.3664,
+      "step": 935
+    },
+    {
+      "epoch": 0.7784679089026915,
+      "grad_norm": 1.9568011172776334,
+      "learning_rate": 1.4187426142248723e-06,
+      "loss": 0.3591,
+      "step": 940
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 2.0688381865589096,
+      "learning_rate": 1.3686508400700787e-06,
+      "loss": 0.3647,
+      "step": 945
+    },
+    {
+      "epoch": 0.7867494824016563,
+      "grad_norm": 2.0663898407393844,
+      "learning_rate": 1.3193187631420462e-06,
+      "loss": 0.3492,
+      "step": 950
+    },
+    {
+      "epoch": 0.7908902691511387,
+      "grad_norm": 2.055621288270255,
+      "learning_rate": 1.2707567039691505e-06,
+      "loss": 0.3527,
+      "step": 955
+    },
+    {
+      "epoch": 0.7950310559006211,
+      "grad_norm": 1.9925441732484688,
+      "learning_rate": 1.222974821988024e-06,
+      "loss": 0.3573,
+      "step": 960
+    },
+    {
+      "epoch": 0.7991718426501035,
+      "grad_norm": 2.062467657748088,
+      "learning_rate": 1.1759831134181504e-06,
+      "loss": 0.3601,
+      "step": 965
+    },
+    {
+      "epoch": 0.8033126293995859,
+      "grad_norm": 2.011075463880814,
+      "learning_rate": 1.1297914091706086e-06,
+      "loss": 0.3536,
+      "step": 970
+    },
+    {
+      "epoch": 0.8074534161490683,
+      "grad_norm": 2.0637149859980264,
+      "learning_rate": 1.0844093727913868e-06,
+      "loss": 0.3595,
+      "step": 975
+    },
+    {
+      "epoch": 0.8115942028985508,
+      "grad_norm": 1.9523568935411413,
+      "learning_rate": 1.039846498439727e-06,
+      "loss": 0.3563,
+      "step": 980
+    },
+    {
+      "epoch": 0.8157349896480331,
+      "grad_norm": 2.061998469109606,
+      "learning_rate": 9.961121089018933e-07,
+      "loss": 0.3523,
+      "step": 985
+    },
+    {
+      "epoch": 0.8198757763975155,
+      "grad_norm": 2.0466038173212633,
+      "learning_rate": 9.532153536407923e-07,
+      "loss": 0.3525,
+      "step": 990
+    },
+    {
+      "epoch": 0.8240165631469979,
+      "grad_norm": 2.051264847475936,
+      "learning_rate": 9.111652068818621e-07,
+      "loss": 0.3455,
+      "step": 995
+    },
+    {
+      "epoch": 0.8281573498964804,
+      "grad_norm": 2.110221360013133,
+      "learning_rate": 8.699704657356195e-07,
+      "loss": 0.3369,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8322981366459627,
+      "grad_norm": 1.974268048949072,
+      "learning_rate": 8.296397483572515e-07,
+      "loss": 0.3473,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8364389233954451,
+      "grad_norm": 2.1102185973268663,
+      "learning_rate": 7.901814921436624e-07,
+      "loss": 0.349,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8405797101449275,
+      "grad_norm": 2.088942249307371,
+      "learning_rate": 7.516039519683105e-07,
+      "loss": 0.3506,
+      "step": 1015
+    },
+    {
+      "epoch": 0.84472049689441,
+      "grad_norm": 2.0172621716492385,
+      "learning_rate": 7.139151984542636e-07,
+      "loss": 0.3479,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8488612836438924,
+      "grad_norm": 2.061272723188888,
+      "learning_rate": 6.771231162857722e-07,
+      "loss": 0.35,
+      "step": 1025
+    },
+    {
+      "epoch": 0.8530020703933747,
+      "grad_norm": 2.042641769558922,
+      "learning_rate": 6.412354025587509e-07,
+      "loss": 0.3419,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 2.107999860141605,
+      "learning_rate": 6.062595651705111e-07,
+      "loss": 0.3455,
+      "step": 1035
+    },
+    {
+      "epoch": 0.8612836438923396,
+      "grad_norm": 2.0760294798992507,
+      "learning_rate": 5.722029212490666e-07,
+      "loss": 0.3521,
+      "step": 1040
+    },
+    {
+      "epoch": 0.865424430641822,
+      "grad_norm": 2.0428220870108116,
+      "learning_rate": 5.390725956223531e-07,
+      "loss": 0.3422,
+      "step": 1045
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 2.001246350332589,
+      "learning_rate": 5.068755193276798e-07,
+      "loss": 0.3455,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8737060041407867,
+      "grad_norm": 2.099442444548102,
+      "learning_rate": 4.756184281617121e-07,
+      "loss": 0.3405,
+      "step": 1055
+    },
+    {
+      "epoch": 0.8778467908902692,
+      "grad_norm": 2.13132891801723,
+      "learning_rate": 4.4530786127131575e-07,
+      "loss": 0.334,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8819875776397516,
+      "grad_norm": 2.0329484032440766,
+      "learning_rate": 4.159501597855287e-07,
+      "loss": 0.3419,
+      "step": 1065
+    },
+    {
+      "epoch": 0.8861283643892339,
+      "grad_norm": 2.159379949424514,
+      "learning_rate": 3.8755146548896784e-07,
+      "loss": 0.3418,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8902691511387164,
+      "grad_norm": 2.040568384317151,
+      "learning_rate": 3.6011771953693044e-07,
+      "loss": 0.3395,
+      "step": 1075
+    },
+    {
+      "epoch": 0.8944099378881988,
+      "grad_norm": 2.120632936565463,
+      "learning_rate": 3.336546612124758e-07,
+      "loss": 0.3401,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8985507246376812,
+      "grad_norm": 2.09791384766389,
+      "learning_rate": 3.081678267257404e-07,
+      "loss": 0.3468,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9026915113871635,
+      "grad_norm": 2.0437408757508924,
+      "learning_rate": 2.836625480557265e-07,
+      "loss": 0.3368,
+      "step": 1090
+    },
+    {
+      "epoch": 0.906832298136646,
+      "grad_norm": 2.083527928278351,
+      "learning_rate": 2.601439518348331e-07,
+      "loss": 0.3466,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9109730848861284,
+      "grad_norm": 2.150766971163671,
+      "learning_rate": 2.376169582763288e-07,
+      "loss": 0.3433,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9151138716356108,
+      "grad_norm": 1.9684937329053864,
+      "learning_rate": 2.1608628014502364e-07,
+      "loss": 0.3417,
+      "step": 1105
+    },
+    {
+      "epoch": 0.9192546583850931,
+      "grad_norm": 2.0342367177559817,
+      "learning_rate": 1.955564217713335e-07,
+      "loss": 0.3435,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9233954451345756,
+      "grad_norm": 2.0540139915838815,
+      "learning_rate": 1.7603167810894662e-07,
+      "loss": 0.337,
+      "step": 1115
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 2.006652780971983,
+      "learning_rate": 1.5751613383630128e-07,
+      "loss": 0.3322,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9316770186335404,
+      "grad_norm": 2.0124326674054562,
+      "learning_rate": 1.4001366250204762e-07,
+      "loss": 0.3334,
+      "step": 1125
+    },
+    {
+      "epoch": 0.9358178053830227,
+      "grad_norm": 2.1136467451791168,
+      "learning_rate": 1.235279257146804e-07,
+      "loss": 0.3343,
+      "step": 1130
+    },
+    {
+      "epoch": 0.9399585921325052,
+      "grad_norm": 2.0186906193155782,
+      "learning_rate": 1.080623723765134e-07,
+      "loss": 0.3362,
+      "step": 1135
+    },
+    {
+      "epoch": 0.9440993788819876,
+      "grad_norm": 2.0844444504570165,
+      "learning_rate": 9.362023796215036e-08,
+      "loss": 0.3365,
+      "step": 1140
+    },
+    {
+      "epoch": 0.94824016563147,
+      "grad_norm": 2.073306988937045,
+      "learning_rate": 8.020454384160437e-08,
+      "loss": 0.3294,
+      "step": 1145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 2.0748770702565755,
+      "learning_rate": 6.78180966482156e-08,
+      "loss": 0.3399,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 1.9873613320972088,
+      "learning_rate": 5.646348769148491e-08,
+      "loss": 0.331,
+      "step": 1155
+    },
+    {
+      "epoch": 0.9606625258799172,
+      "grad_norm": 2.0532519601789194,
+      "learning_rate": 4.6143092414961396e-08,
+      "loss": 0.3359,
+      "step": 1160
+    },
+    {
+      "epoch": 0.9648033126293996,
+      "grad_norm": 2.294030777096881,
+      "learning_rate": 3.685906989928656e-08,
+      "loss": 0.3305,
+      "step": 1165
+    },
+    {
+      "epoch": 0.968944099378882,
+      "grad_norm": 2.292130787520844,
+      "learning_rate": 2.861336241050061e-08,
+      "loss": 0.3419,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9730848861283644,
+      "grad_norm": 2.057089249921181,
+      "learning_rate": 2.1407694993714755e-08,
+      "loss": 0.3321,
+      "step": 1175
+    },
+    {
+      "epoch": 0.9772256728778468,
+      "grad_norm": 2.0761794810893375,
+      "learning_rate": 1.5243575112218744e-08,
+      "loss": 0.336,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9813664596273292,
+      "grad_norm": 2.054973660726792,
+      "learning_rate": 1.0122292332114814e-08,
+      "loss": 0.3386,
+      "step": 1185
+    },
+    {
+      "epoch": 0.9855072463768116,
+      "grad_norm": 2.0266934387654163,
+      "learning_rate": 6.044918052531268e-09,
+      "loss": 0.3347,
+      "step": 1190
+    },
+    {
+      "epoch": 0.989648033126294,
+      "grad_norm": 2.0133284950403927,
+      "learning_rate": 3.0123052814812203e-09,
+      "loss": 0.3356,
+      "step": 1195
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 2.106679276632288,
+      "learning_rate": 1.025088457409229e-09,
+      "loss": 0.3369,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9979296066252588,
+      "grad_norm": 1.9986369917882558,
+      "learning_rate": 8.368331646302353e-11,
+      "loss": 0.3466,
+      "step": 1205
+    },
+    {
+      "epoch": 0.9995859213250518,
+      "eval_loss": 0.33997195959091187,
+      "eval_runtime": 125.5313,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 0.781,
+      "step": 1207
+    },
+    {
+      "epoch": 0.9995859213250518,
+      "step": 1207,
+      "total_flos": 252668899491840.0,
+      "train_loss": 0.5242949779505758,
+      "train_runtime": 27497.765,
+      "train_samples_per_second": 1.405,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 252668899491840.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47544fc9eff7625b9460c8c148652da7df09908398c6a351a27f36896fb9d7d
+size 6520