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-direct-0.1p-rare-seed42
+  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-direct-0.1p-rare-seed42
+
+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: 0.3326
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3303        | 0.9995 | 1024 | 0.3326          |
+
+
+### 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": 0.9995119570522206,
+    "total_flos": 214352422502400.0,
+    "train_loss": 0.4881494865985587,
+    "train_runtime": 23473.6027,
+    "train_samples": 108847,
+    "train_samples_per_second": 1.397,
+    "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:fab4b5711dd951be179c4497f1087937b5815d727b69b8530fc4b3f1030b9456
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf77131c433c8fadf7c0a13ee913d4c19e2a8d171142f226e36eeec33493321
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7597380754656845b829fe4a7ec6310adaaaf76e4e705c8d817f2cc1a5ee755
+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/Aug05_21-29-30_COE-CS-sv003/events.out.tfevents.1722893698.COE-CS-sv003.2094480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a2a11a97bb314c336a47bee57b503a385169c0dd63a37941c11b5fe609ee15
+size 5448

runs/Aug05_21-37-07_COE-CS-sv003/events.out.tfevents.1722893849.COE-CS-sv003.2098235.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350f77e46999383f6600cf0c55686c77cc2ea452f0db2523870b6e1abdeaf5f5
+size 49017

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": 0.9995119570522206,
+    "total_flos": 214352422502400.0,
+    "train_loss": 0.4881494865985587,
+    "train_runtime": 23473.6027,
+    "train_samples": 108847,
+    "train_samples_per_second": 1.397,
+    "train_steps_per_second": 0.044
+}

trainer_state.json

@@ -0,0 +1,1485 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9995119570522206,
+  "eval_steps": 500,
+  "global_step": 1024,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009760858955588092,
+      "grad_norm": 23.035247556232232,
+      "learning_rate": 9.70873786407767e-08,
+      "loss": 1.305,
+      "step": 1
+    },
+    {
+      "epoch": 0.004880429477794046,
+      "grad_norm": 20.719836042073574,
+      "learning_rate": 4.854368932038835e-07,
+      "loss": 1.3146,
+      "step": 5
+    },
+    {
+      "epoch": 0.009760858955588092,
+      "grad_norm": 9.316004282384458,
+      "learning_rate": 9.70873786407767e-07,
+      "loss": 1.2051,
+      "step": 10
+    },
+    {
+      "epoch": 0.014641288433382138,
+      "grad_norm": 8.495855354939422,
+      "learning_rate": 1.4563106796116506e-06,
+      "loss": 1.0417,
+      "step": 15
+    },
+    {
+      "epoch": 0.019521717911176184,
+      "grad_norm": 3.0384642525762553,
+      "learning_rate": 1.941747572815534e-06,
+      "loss": 0.9234,
+      "step": 20
+    },
+    {
+      "epoch": 0.02440214738897023,
+      "grad_norm": 2.435241261554877,
+      "learning_rate": 2.427184466019418e-06,
+      "loss": 0.873,
+      "step": 25
+    },
+    {
+      "epoch": 0.029282576866764276,
+      "grad_norm": 2.2514226333854612,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 0.8389,
+      "step": 30
+    },
+    {
+      "epoch": 0.03416300634455832,
+      "grad_norm": 2.2291597467335396,
+      "learning_rate": 3.398058252427185e-06,
+      "loss": 0.8266,
+      "step": 35
+    },
+    {
+      "epoch": 0.03904343582235237,
+      "grad_norm": 2.3180250181670745,
+      "learning_rate": 3.883495145631068e-06,
+      "loss": 0.8014,
+      "step": 40
+    },
+    {
+      "epoch": 0.043923865300146414,
+      "grad_norm": 2.242281011137039,
+      "learning_rate": 4.368932038834952e-06,
+      "loss": 0.7868,
+      "step": 45
+    },
+    {
+      "epoch": 0.04880429477794046,
+      "grad_norm": 2.265455274846197,
+      "learning_rate": 4.854368932038836e-06,
+      "loss": 0.7727,
+      "step": 50
+    },
+    {
+      "epoch": 0.053684724255734506,
+      "grad_norm": 2.513657587709498,
+      "learning_rate": 5.3398058252427185e-06,
+      "loss": 0.7657,
+      "step": 55
+    },
+    {
+      "epoch": 0.05856515373352855,
+      "grad_norm": 2.5260021282408194,
+      "learning_rate": 5.825242718446602e-06,
+      "loss": 0.7469,
+      "step": 60
+    },
+    {
+      "epoch": 0.0634455832113226,
+      "grad_norm": 2.37579367638948,
+      "learning_rate": 6.310679611650487e-06,
+      "loss": 0.7318,
+      "step": 65
+    },
+    {
+      "epoch": 0.06832601268911664,
+      "grad_norm": 2.3867971053464965,
+      "learning_rate": 6.79611650485437e-06,
+      "loss": 0.7206,
+      "step": 70
+    },
+    {
+      "epoch": 0.07320644216691069,
+      "grad_norm": 2.4935586404236156,
+      "learning_rate": 7.2815533980582534e-06,
+      "loss": 0.7054,
+      "step": 75
+    },
+    {
+      "epoch": 0.07808687164470474,
+      "grad_norm": 2.294194399695781,
+      "learning_rate": 7.766990291262136e-06,
+      "loss": 0.7024,
+      "step": 80
+    },
+    {
+      "epoch": 0.08296730112249878,
+      "grad_norm": 2.6104379893467917,
+      "learning_rate": 8.25242718446602e-06,
+      "loss": 0.6972,
+      "step": 85
+    },
+    {
+      "epoch": 0.08784773060029283,
+      "grad_norm": 2.279295024137011,
+      "learning_rate": 8.737864077669904e-06,
+      "loss": 0.6811,
+      "step": 90
+    },
+    {
+      "epoch": 0.09272816007808687,
+      "grad_norm": 2.1438545371438047,
+      "learning_rate": 9.223300970873788e-06,
+      "loss": 0.6929,
+      "step": 95
+    },
+    {
+      "epoch": 0.09760858955588092,
+      "grad_norm": 2.0963423668390213,
+      "learning_rate": 9.708737864077671e-06,
+      "loss": 0.684,
+      "step": 100
+    },
+    {
+      "epoch": 0.10248901903367497,
+      "grad_norm": 2.346237075039726,
+      "learning_rate": 9.999883646674445e-06,
+      "loss": 0.6836,
+      "step": 105
+    },
+    {
+      "epoch": 0.10736944851146901,
+      "grad_norm": 2.079088926479871,
+      "learning_rate": 9.998574733951775e-06,
+      "loss": 0.6777,
+      "step": 110
+    },
+    {
+      "epoch": 0.11224987798926306,
+      "grad_norm": 2.012614649795243,
+      "learning_rate": 9.995811848851807e-06,
+      "loss": 0.6796,
+      "step": 115
+    },
+    {
+      "epoch": 0.1171303074670571,
+      "grad_norm": 2.4597764317331383,
+      "learning_rate": 9.991595795035352e-06,
+      "loss": 0.6677,
+      "step": 120
+    },
+    {
+      "epoch": 0.12201073694485115,
+      "grad_norm": 2.0190253268907354,
+      "learning_rate": 9.985927798857143e-06,
+      "loss": 0.6604,
+      "step": 125
+    },
+    {
+      "epoch": 0.1268911664226452,
+      "grad_norm": 2.056019595630264,
+      "learning_rate": 9.978809509009121e-06,
+      "loss": 0.671,
+      "step": 130
+    },
+    {
+      "epoch": 0.13177159590043924,
+      "grad_norm": 1.9920289467971395,
+      "learning_rate": 9.970242996040865e-06,
+      "loss": 0.6619,
+      "step": 135
+    },
+    {
+      "epoch": 0.1366520253782333,
+      "grad_norm": 2.427476265620817,
+      "learning_rate": 9.960230751757318e-06,
+      "loss": 0.653,
+      "step": 140
+    },
+    {
+      "epoch": 0.14153245485602733,
+      "grad_norm": 2.138699924734492,
+      "learning_rate": 9.948775688493974e-06,
+      "loss": 0.6428,
+      "step": 145
+    },
+    {
+      "epoch": 0.14641288433382138,
+      "grad_norm": 2.2832062237916007,
+      "learning_rate": 9.93588113826975e-06,
+      "loss": 0.6556,
+      "step": 150
+    },
+    {
+      "epoch": 0.15129331381161543,
+      "grad_norm": 2.330757441488492,
+      "learning_rate": 9.921550851817774e-06,
+      "loss": 0.6597,
+      "step": 155
+    },
+    {
+      "epoch": 0.15617374328940947,
+      "grad_norm": 2.028862838643975,
+      "learning_rate": 9.905788997494377e-06,
+      "loss": 0.6449,
+      "step": 160
+    },
+    {
+      "epoch": 0.16105417276720352,
+      "grad_norm": 2.097525756087534,
+      "learning_rate": 9.888600160066627e-06,
+      "loss": 0.6469,
+      "step": 165
+    },
+    {
+      "epoch": 0.16593460224499756,
+      "grad_norm": 2.238936294256646,
+      "learning_rate": 9.869989339378706e-06,
+      "loss": 0.6345,
+      "step": 170
+    },
+    {
+      "epoch": 0.1708150317227916,
+      "grad_norm": 2.3275889632266225,
+      "learning_rate": 9.849961948897582e-06,
+      "loss": 0.6361,
+      "step": 175
+    },
+    {
+      "epoch": 0.17569546120058566,
+      "grad_norm": 2.1824511863577096,
+      "learning_rate": 9.828523814138344e-06,
+      "loss": 0.6286,
+      "step": 180
+    },
+    {
+      "epoch": 0.1805758906783797,
+      "grad_norm": 1.9316765699674343,
+      "learning_rate": 9.8056811709697e-06,
+      "loss": 0.6312,
+      "step": 185
+    },
+    {
+      "epoch": 0.18545632015617375,
+      "grad_norm": 1.913481112213078,
+      "learning_rate": 9.781440663800099e-06,
+      "loss": 0.6252,
+      "step": 190
+    },
+    {
+      "epoch": 0.1903367496339678,
+      "grad_norm": 2.126509994727766,
+      "learning_rate": 9.755809343645021e-06,
+      "loss": 0.6197,
+      "step": 195
+    },
+    {
+      "epoch": 0.19521717911176184,
+      "grad_norm": 2.0612294747506437,
+      "learning_rate": 9.728794666076004e-06,
+      "loss": 0.6095,
+      "step": 200
+    },
+    {
+      "epoch": 0.2000976085895559,
+      "grad_norm": 1.957338282859279,
+      "learning_rate": 9.700404489051974e-06,
+      "loss": 0.6161,
+      "step": 205
+    },
+    {
+      "epoch": 0.20497803806734993,
+      "grad_norm": 2.0078755538466955,
+      "learning_rate": 9.670647070633554e-06,
+      "loss": 0.6091,
+      "step": 210
+    },
+    {
+      "epoch": 0.20985846754514398,
+      "grad_norm": 2.023099319748942,
+      "learning_rate": 9.639531066580979e-06,
+      "loss": 0.6085,
+      "step": 215
+    },
+    {
+      "epoch": 0.21473889702293802,
+      "grad_norm": 2.0118211094195773,
+      "learning_rate": 9.607065527836324e-06,
+      "loss": 0.5993,
+      "step": 220
+    },
+    {
+      "epoch": 0.21961932650073207,
+      "grad_norm": 2.1563303821214626,
+      "learning_rate": 9.573259897890794e-06,
+      "loss": 0.5958,
+      "step": 225
+    },
+    {
+      "epoch": 0.22449975597852612,
+      "grad_norm": 2.0414228158229792,
+      "learning_rate": 9.538124010037832e-06,
+      "loss": 0.5886,
+      "step": 230
+    },
+    {
+      "epoch": 0.22938018545632016,
+      "grad_norm": 2.0788427448618,
+      "learning_rate": 9.501668084512827e-06,
+      "loss": 0.5985,
+      "step": 235
+    },
+    {
+      "epoch": 0.2342606149341142,
+      "grad_norm": 2.1797519504265885,
+      "learning_rate": 9.46390272552028e-06,
+      "loss": 0.5928,
+      "step": 240
+    },
+    {
+      "epoch": 0.23914104441190825,
+      "grad_norm": 2.0188184151034383,
+      "learning_rate": 9.424838918149285e-06,
+      "loss": 0.5938,
+      "step": 245
+    },
+    {
+      "epoch": 0.2440214738897023,
+      "grad_norm": 2.010370103702029,
+      "learning_rate": 9.384488025178214e-06,
+      "loss": 0.5916,
+      "step": 250
+    },
+    {
+      "epoch": 0.24890190336749635,
+      "grad_norm": 2.0376138426044377,
+      "learning_rate": 9.342861783769535e-06,
+      "loss": 0.5977,
+      "step": 255
+    },
+    {
+      "epoch": 0.2537823328452904,
+      "grad_norm": 1.97689791600861,
+      "learning_rate": 9.29997230205575e-06,
+      "loss": 0.585,
+      "step": 260
+    },
+    {
+      "epoch": 0.25866276232308444,
+      "grad_norm": 2.0361234487708573,
+      "learning_rate": 9.2558320556174e-06,
+      "loss": 0.5753,
+      "step": 265
+    },
+    {
+      "epoch": 0.2635431918008785,
+      "grad_norm": 1.979410664780559,
+      "learning_rate": 9.210453883854204e-06,
+      "loss": 0.5898,
+      "step": 270
+    },
+    {
+      "epoch": 0.26842362127867253,
+      "grad_norm": 1.9815660852967445,
+      "learning_rate": 9.163850986250375e-06,
+      "loss": 0.5836,
+      "step": 275
+    },
+    {
+      "epoch": 0.2733040507564666,
+      "grad_norm": 2.2880133483104625,
+      "learning_rate": 9.11603691853518e-06,
+      "loss": 0.5663,
+      "step": 280
+    },
+    {
+      "epoch": 0.2781844802342606,
+      "grad_norm": 1.9874397029111008,
+      "learning_rate": 9.067025588739889e-06,
+      "loss": 0.5658,
+      "step": 285
+    },
+    {
+      "epoch": 0.28306490971205467,
+      "grad_norm": 1.9026409986400121,
+      "learning_rate": 9.016831253152244e-06,
+      "loss": 0.5689,
+      "step": 290
+    },
+    {
+      "epoch": 0.2879453391898487,
+      "grad_norm": 2.241058211758017,
+      "learning_rate": 8.96546851216962e-06,
+      "loss": 0.5557,
+      "step": 295
+    },
+    {
+      "epoch": 0.29282576866764276,
+      "grad_norm": 1.9994798416425632,
+      "learning_rate": 8.912952306052109e-06,
+      "loss": 0.5628,
+      "step": 300
+    },
+    {
+      "epoch": 0.2977061981454368,
+      "grad_norm": 1.9657323697266753,
+      "learning_rate": 8.859297910576732e-06,
+      "loss": 0.5556,
+      "step": 305
+    },
+    {
+      "epoch": 0.30258662762323085,
+      "grad_norm": 2.275704776988123,
+      "learning_rate": 8.804520932594061e-06,
+      "loss": 0.547,
+      "step": 310
+    },
+    {
+      "epoch": 0.3074670571010249,
+      "grad_norm": 2.02689211581186,
+      "learning_rate": 8.748637305488537e-06,
+      "loss": 0.5481,
+      "step": 315
+    },
+    {
+      "epoch": 0.31234748657881894,
+      "grad_norm": 1.9315973089401948,
+      "learning_rate": 8.691663284543812e-06,
+      "loss": 0.5489,
+      "step": 320
+    },
+    {
+      "epoch": 0.317227916056613,
+      "grad_norm": 1.9190728935534196,
+      "learning_rate": 8.633615442214452e-06,
+      "loss": 0.5476,
+      "step": 325
+    },
+    {
+      "epoch": 0.32210834553440704,
+      "grad_norm": 2.326687095328215,
+      "learning_rate": 8.574510663305388e-06,
+      "loss": 0.535,
+      "step": 330
+    },
+    {
+      "epoch": 0.3269887750122011,
+      "grad_norm": 2.0644871195721652,
+      "learning_rate": 8.514366140060504e-06,
+      "loss": 0.5503,
+      "step": 335
+    },
+    {
+      "epoch": 0.33186920448999513,
+      "grad_norm": 2.1583645554795226,
+      "learning_rate": 8.453199367161804e-06,
+      "loss": 0.5323,
+      "step": 340
+    },
+    {
+      "epoch": 0.3367496339677892,
+      "grad_norm": 2.108056214865082,
+      "learning_rate": 8.391028136640604e-06,
+      "loss": 0.5268,
+      "step": 345
+    },
+    {
+      "epoch": 0.3416300634455832,
+      "grad_norm": 1.9847999461871777,
+      "learning_rate": 8.32787053270223e-06,
+      "loss": 0.5234,
+      "step": 350
+    },
+    {
+      "epoch": 0.34651049292337727,
+      "grad_norm": 2.032846767263459,
+      "learning_rate": 8.263744926465744e-06,
+      "loss": 0.5389,
+      "step": 355
+    },
+    {
+      "epoch": 0.3513909224011713,
+      "grad_norm": 2.066277009423882,
+      "learning_rate": 8.198669970620177e-06,
+      "loss": 0.5194,
+      "step": 360
+    },
+    {
+      "epoch": 0.35627135187896536,
+      "grad_norm": 2.4408622009476364,
+      "learning_rate": 8.13266459399891e-06,
+      "loss": 0.5279,
+      "step": 365
+    },
+    {
+      "epoch": 0.3611517813567594,
+      "grad_norm": 2.0939994519934997,
+      "learning_rate": 8.065747996073681e-06,
+      "loss": 0.5176,
+      "step": 370
+    },
+    {
+      "epoch": 0.36603221083455345,
+      "grad_norm": 2.1186198571951773,
+      "learning_rate": 7.997939641369909e-06,
+      "loss": 0.5132,
+      "step": 375
+    },
+    {
+      "epoch": 0.3709126403123475,
+      "grad_norm": 1.894201627794718,
+      "learning_rate": 7.929259253804903e-06,
+      "loss": 0.521,
+      "step": 380
+    },
+    {
+      "epoch": 0.37579306979014154,
+      "grad_norm": 2.083317144453098,
+      "learning_rate": 7.859726810950606e-06,
+      "loss": 0.5084,
+      "step": 385
+    },
+    {
+      "epoch": 0.3806734992679356,
+      "grad_norm": 1.8916170318680645,
+      "learning_rate": 7.789362538222585e-06,
+      "loss": 0.5127,
+      "step": 390
+    },
+    {
+      "epoch": 0.38555392874572963,
+      "grad_norm": 2.208287429807416,
+      "learning_rate": 7.718186902996912e-06,
+      "loss": 0.5082,
+      "step": 395
+    },
+    {
+      "epoch": 0.3904343582235237,
+      "grad_norm": 1.9376050467874282,
+      "learning_rate": 7.646220608656662e-06,
+      "loss": 0.5033,
+      "step": 400
+    },
+    {
+      "epoch": 0.3953147877013177,
+      "grad_norm": 1.9494765756044568,
+      "learning_rate": 7.573484588569775e-06,
+      "loss": 0.5083,
+      "step": 405
+    },
+    {
+      "epoch": 0.4001952171791118,
+      "grad_norm": 1.9102990648958087,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.5063,
+      "step": 410
+    },
+    {
+      "epoch": 0.4050756466569058,
+      "grad_norm": 1.997919784615126,
+      "learning_rate": 7.425788217952744e-06,
+      "loss": 0.494,
+      "step": 415
+    },
+    {
+      "epoch": 0.40995607613469986,
+      "grad_norm": 2.080884858986304,
+      "learning_rate": 7.350870828957547e-06,
+      "loss": 0.4985,
+      "step": 420
+    },
+    {
+      "epoch": 0.4148365056124939,
+      "grad_norm": 1.9539843013372942,
+      "learning_rate": 7.27526962478906e-06,
+      "loss": 0.4887,
+      "step": 425
+    },
+    {
+      "epoch": 0.41971693509028796,
+      "grad_norm": 2.072970721277029,
+      "learning_rate": 7.1990065961283075e-06,
+      "loss": 0.497,
+      "step": 430
+    },
+    {
+      "epoch": 0.424597364568082,
+      "grad_norm": 1.9942120864124357,
+      "learning_rate": 7.122103926166096e-06,
+      "loss": 0.4841,
+      "step": 435
+    },
+    {
+      "epoch": 0.42947779404587605,
+      "grad_norm": 1.9812280986457487,
+      "learning_rate": 7.044583984150425e-06,
+      "loss": 0.4762,
+      "step": 440
+    },
+    {
+      "epoch": 0.4343582235236701,
+      "grad_norm": 2.0123859041578678,
+      "learning_rate": 6.9664693188797776e-06,
+      "loss": 0.478,
+      "step": 445
+    },
+    {
+      "epoch": 0.43923865300146414,
+      "grad_norm": 1.8650862463799345,
+      "learning_rate": 6.887782652144186e-06,
+      "loss": 0.4784,
+      "step": 450
+    },
+    {
+      "epoch": 0.4441190824792582,
+      "grad_norm": 1.9432343558958571,
+      "learning_rate": 6.808546872115976e-06,
+      "loss": 0.4727,
+      "step": 455
+    },
+    {
+      "epoch": 0.44899951195705223,
+      "grad_norm": 1.9279715713548145,
+      "learning_rate": 6.728785026692113e-06,
+      "loss": 0.4753,
+      "step": 460
+    },
+    {
+      "epoch": 0.4538799414348463,
+      "grad_norm": 1.954814041702271,
+      "learning_rate": 6.648520316790102e-06,
+      "loss": 0.4561,
+      "step": 465
+    },
+    {
+      "epoch": 0.4587603709126403,
+      "grad_norm": 1.8912197483130344,
+      "learning_rate": 6.567776089599339e-06,
+      "loss": 0.4712,
+      "step": 470
+    },
+    {
+      "epoch": 0.46364080039043437,
+      "grad_norm": 1.8511135512437755,
+      "learning_rate": 6.486575831789974e-06,
+      "loss": 0.4564,
+      "step": 475
+    },
+    {
+      "epoch": 0.4685212298682284,
+      "grad_norm": 2.0169192033711063,
+      "learning_rate": 6.404943162681144e-06,
+      "loss": 0.4612,
+      "step": 480
+    },
+    {
+      "epoch": 0.47340165934602246,
+      "grad_norm": 1.9398646592145217,
+      "learning_rate": 6.322901827370659e-06,
+      "loss": 0.4622,
+      "step": 485
+    },
+    {
+      "epoch": 0.4782820888238165,
+      "grad_norm": 1.9832620948402848,
+      "learning_rate": 6.240475689828087e-06,
+      "loss": 0.4589,
+      "step": 490
+    },
+    {
+      "epoch": 0.48316251830161056,
+      "grad_norm": 2.0795997220341325,
+      "learning_rate": 6.1576887259532695e-06,
+      "loss": 0.447,
+      "step": 495
+    },
+    {
+      "epoch": 0.4880429477794046,
+      "grad_norm": 1.8116820288469397,
+      "learning_rate": 6.074565016602263e-06,
+      "loss": 0.4519,
+      "step": 500
+    },
+    {
+      "epoch": 0.49292337725719865,
+      "grad_norm": 1.943068708736876,
+      "learning_rate": 5.991128740582774e-06,
+      "loss": 0.453,
+      "step": 505
+    },
+    {
+      "epoch": 0.4978038067349927,
+      "grad_norm": 2.0127161873905948,
+      "learning_rate": 5.907404167621087e-06,
+      "loss": 0.4551,
+      "step": 510
+    },
+    {
+      "epoch": 0.5026842362127867,
+      "grad_norm": 1.9262937498205195,
+      "learning_rate": 5.823415651302545e-06,
+      "loss": 0.4526,
+      "step": 515
+    },
+    {
+      "epoch": 0.5075646656905808,
+      "grad_norm": 1.890004605269585,
+      "learning_rate": 5.739187621987649e-06,
+      "loss": 0.4471,
+      "step": 520
+    },
+    {
+      "epoch": 0.5124450951683748,
+      "grad_norm": 1.986812970174512,
+      "learning_rate": 5.654744579705815e-06,
+      "loss": 0.4318,
+      "step": 525
+    },
+    {
+      "epoch": 0.5173255246461689,
+      "grad_norm": 2.074431055050664,
+      "learning_rate": 5.570111087028868e-06,
+      "loss": 0.4449,
+      "step": 530
+    },
+    {
+      "epoch": 0.5222059541239629,
+      "grad_norm": 1.8815049244771753,
+      "learning_rate": 5.4853117619263496e-06,
+      "loss": 0.4407,
+      "step": 535
+    },
+    {
+      "epoch": 0.527086383601757,
+      "grad_norm": 1.9186809916757779,
+      "learning_rate": 5.4003712706047055e-06,
+      "loss": 0.4457,
+      "step": 540
+    },
+    {
+      "epoch": 0.531966813079551,
+      "grad_norm": 1.9444758137939766,
+      "learning_rate": 5.315314320332438e-06,
+      "loss": 0.4343,
+      "step": 545
+    },
+    {
+      "epoch": 0.5368472425573451,
+      "grad_norm": 2.1154813361539424,
+      "learning_rate": 5.230165652253329e-06,
+      "loss": 0.4301,
+      "step": 550
+    },
+    {
+      "epoch": 0.541727672035139,
+      "grad_norm": 1.8462242497921442,
+      "learning_rate": 5.144950034189798e-06,
+      "loss": 0.4348,
+      "step": 555
+    },
+    {
+      "epoch": 0.5466081015129332,
+      "grad_norm": 1.8891533773792688,
+      "learning_rate": 5.059692253438495e-06,
+      "loss": 0.4238,
+      "step": 560
+    },
+    {
+      "epoch": 0.5514885309907271,
+      "grad_norm": 1.8943839327223533,
+      "learning_rate": 4.97441710956025e-06,
+      "loss": 0.4278,
+      "step": 565
+    },
+    {
+      "epoch": 0.5563689604685212,
+      "grad_norm": 1.8842523650803675,
+      "learning_rate": 4.8891494071664315e-06,
+      "loss": 0.4381,
+      "step": 570
+    },
+    {
+      "epoch": 0.5612493899463152,
+      "grad_norm": 1.8611349476498642,
+      "learning_rate": 4.803913948703845e-06,
+      "loss": 0.4057,
+      "step": 575
+    },
+    {
+      "epoch": 0.5661298194241093,
+      "grad_norm": 2.250944612674544,
+      "learning_rate": 4.71873552724027e-06,
+      "loss": 0.4102,
+      "step": 580
+    },
+    {
+      "epoch": 0.5710102489019033,
+      "grad_norm": 1.846182706672498,
+      "learning_rate": 4.633638919252712e-06,
+      "loss": 0.4123,
+      "step": 585
+    },
+    {
+      "epoch": 0.5758906783796974,
+      "grad_norm": 1.9576170198699478,
+      "learning_rate": 4.548648877420481e-06,
+      "loss": 0.4126,
+      "step": 590
+    },
+    {
+      "epoch": 0.5807711078574914,
+      "grad_norm": 2.0956436020765166,
+      "learning_rate": 4.463790123425209e-06,
+      "loss": 0.4059,
+      "step": 595
+    },
+    {
+      "epoch": 0.5856515373352855,
+      "grad_norm": 1.957295844436941,
+      "learning_rate": 4.379087340759861e-06,
+      "loss": 0.416,
+      "step": 600
+    },
+    {
+      "epoch": 0.5905319668130795,
+      "grad_norm": 1.9288351907184336,
+      "learning_rate": 4.294565167548866e-06,
+      "loss": 0.4088,
+      "step": 605
+    },
+    {
+      "epoch": 0.5954123962908736,
+      "grad_norm": 1.8695034228231788,
+      "learning_rate": 4.2102481893814504e-06,
+      "loss": 0.4021,
+      "step": 610
+    },
+    {
+      "epoch": 0.6002928257686676,
+      "grad_norm": 1.932666429763739,
+      "learning_rate": 4.1261609321602406e-06,
+      "loss": 0.4066,
+      "step": 615
+    },
+    {
+      "epoch": 0.6051732552464617,
+      "grad_norm": 1.863599655356967,
+      "learning_rate": 4.042327854967231e-06,
+      "loss": 0.4029,
+      "step": 620
+    },
+    {
+      "epoch": 0.6100536847242557,
+      "grad_norm": 1.9017066401572869,
+      "learning_rate": 3.958773342949196e-06,
+      "loss": 0.4014,
+      "step": 625
+    },
+    {
+      "epoch": 0.6149341142020498,
+      "grad_norm": 1.8354296840477746,
+      "learning_rate": 3.875521700224598e-06,
+      "loss": 0.3996,
+      "step": 630
+    },
+    {
+      "epoch": 0.6198145436798438,
+      "grad_norm": 1.9012134040742121,
+      "learning_rate": 3.7925971428140655e-06,
+      "loss": 0.3963,
+      "step": 635
+    },
+    {
+      "epoch": 0.6246949731576379,
+      "grad_norm": 1.8307728966391115,
+      "learning_rate": 3.71002379159651e-06,
+      "loss": 0.3815,
+      "step": 640
+    },
+    {
+      "epoch": 0.6295754026354319,
+      "grad_norm": 1.8463068672322085,
+      "learning_rate": 3.627825665292899e-06,
+      "loss": 0.3866,
+      "step": 645
+    },
+    {
+      "epoch": 0.634455832113226,
+      "grad_norm": 1.8799977224296363,
+      "learning_rate": 3.546026673479755e-06,
+      "loss": 0.3862,
+      "step": 650
+    },
+    {
+      "epoch": 0.63933626159102,
+      "grad_norm": 1.9499227663945158,
+      "learning_rate": 3.464650609634403e-06,
+      "loss": 0.3834,
+      "step": 655
+    },
+    {
+      "epoch": 0.6442166910688141,
+      "grad_norm": 2.085562927435089,
+      "learning_rate": 3.383721144213985e-06,
+      "loss": 0.3885,
+      "step": 660
+    },
+    {
+      "epoch": 0.6490971205466081,
+      "grad_norm": 1.8062059990982582,
+      "learning_rate": 3.3032618177702546e-06,
+      "loss": 0.3882,
+      "step": 665
+    },
+    {
+      "epoch": 0.6539775500244022,
+      "grad_norm": 1.8689683106850827,
+      "learning_rate": 3.2232960341021703e-06,
+      "loss": 0.3836,
+      "step": 670
+    },
+    {
+      "epoch": 0.6588579795021962,
+      "grad_norm": 1.7607073017774915,
+      "learning_rate": 3.1438470534482547e-06,
+      "loss": 0.3864,
+      "step": 675
+    },
+    {
+      "epoch": 0.6637384089799903,
+      "grad_norm": 1.8221640618653892,
+      "learning_rate": 3.064937985720717e-06,
+      "loss": 0.3851,
+      "step": 680
+    },
+    {
+      "epoch": 0.6686188384577842,
+      "grad_norm": 1.7866065439568548,
+      "learning_rate": 2.9865917837833025e-06,
+      "loss": 0.3791,
+      "step": 685
+    },
+    {
+      "epoch": 0.6734992679355783,
+      "grad_norm": 1.854981360240035,
+      "learning_rate": 2.9088312367748257e-06,
+      "loss": 0.3767,
+      "step": 690
+    },
+    {
+      "epoch": 0.6783796974133723,
+      "grad_norm": 1.8356520705100887,
+      "learning_rate": 2.8316789634803223e-06,
+      "loss": 0.3791,
+      "step": 695
+    },
+    {
+      "epoch": 0.6832601268911664,
+      "grad_norm": 1.9624888900737716,
+      "learning_rate": 2.75515740575176e-06,
+      "loss": 0.3754,
+      "step": 700
+    },
+    {
+      "epoch": 0.6881405563689604,
+      "grad_norm": 1.8570794747458175,
+      "learning_rate": 2.6792888219802017e-06,
+      "loss": 0.3732,
+      "step": 705
+    },
+    {
+      "epoch": 0.6930209858467545,
+      "grad_norm": 1.8773607924105495,
+      "learning_rate": 2.604095280621354e-06,
+      "loss": 0.3641,
+      "step": 710
+    },
+    {
+      "epoch": 0.6979014153245485,
+      "grad_norm": 1.9091813518590455,
+      "learning_rate": 2.529598653776349e-06,
+      "loss": 0.3683,
+      "step": 715
+    },
+    {
+      "epoch": 0.7027818448023426,
+      "grad_norm": 1.8992343259387405,
+      "learning_rate": 2.4558206108296394e-06,
+      "loss": 0.3701,
+      "step": 720
+    },
+    {
+      "epoch": 0.7076622742801366,
+      "grad_norm": 1.8563794906563806,
+      "learning_rate": 2.3827826121458713e-06,
+      "loss": 0.3725,
+      "step": 725
+    },
+    {
+      "epoch": 0.7125427037579307,
+      "grad_norm": 1.7665178047594396,
+      "learning_rate": 2.3105059028275467e-06,
+      "loss": 0.3704,
+      "step": 730
+    },
+    {
+      "epoch": 0.7174231332357247,
+      "grad_norm": 1.8625985682622697,
+      "learning_rate": 2.2390115065352974e-06,
+      "loss": 0.3695,
+      "step": 735
+    },
+    {
+      "epoch": 0.7223035627135188,
+      "grad_norm": 1.9454683490909128,
+      "learning_rate": 2.16832021937259e-06,
+      "loss": 0.3728,
+      "step": 740
+    },
+    {
+      "epoch": 0.7271839921913128,
+      "grad_norm": 1.8998464205788768,
+      "learning_rate": 2.0984526038366005e-06,
+      "loss": 0.3584,
+      "step": 745
+    },
+    {
+      "epoch": 0.7320644216691069,
+      "grad_norm": 1.7833634293472909,
+      "learning_rate": 2.0294289828370506e-06,
+      "loss": 0.3655,
+      "step": 750
+    },
+    {
+      "epoch": 0.7369448511469009,
+      "grad_norm": 1.7357199941063493,
+      "learning_rate": 1.9612694337847334e-06,
+      "loss": 0.3607,
+      "step": 755
+    },
+    {
+      "epoch": 0.741825280624695,
+      "grad_norm": 1.822672774536763,
+      "learning_rate": 1.8939937827514509e-06,
+      "loss": 0.3558,
+      "step": 760
+    },
+    {
+      "epoch": 0.746705710102489,
+      "grad_norm": 1.8562189172640455,
+      "learning_rate": 1.8276215987030489e-06,
+      "loss": 0.3627,
+      "step": 765
+    },
+    {
+      "epoch": 0.7515861395802831,
+      "grad_norm": 1.778360536639837,
+      "learning_rate": 1.7621721878072601e-06,
+      "loss": 0.3565,
+      "step": 770
+    },
+    {
+      "epoch": 0.7564665690580771,
+      "grad_norm": 1.7353609171885467,
+      "learning_rate": 1.6976645878179677e-06,
+      "loss": 0.3564,
+      "step": 775
+    },
+    {
+      "epoch": 0.7613469985358712,
+      "grad_norm": 1.724352647878197,
+      "learning_rate": 1.6341175625375554e-06,
+      "loss": 0.3542,
+      "step": 780
+    },
+    {
+      "epoch": 0.7662274280136652,
+      "grad_norm": 1.702190896366777,
+      "learning_rate": 1.5715495963589434e-06,
+      "loss": 0.359,
+      "step": 785
+    },
+    {
+      "epoch": 0.7711078574914593,
+      "grad_norm": 1.791687835303583,
+      "learning_rate": 1.509978888888894e-06,
+      "loss": 0.3505,
+      "step": 790
+    },
+    {
+      "epoch": 0.7759882869692533,
+      "grad_norm": 1.9174372654606664,
+      "learning_rate": 1.4494233496541548e-06,
+      "loss": 0.3523,
+      "step": 795
+    },
+    {
+      "epoch": 0.7808687164470474,
+      "grad_norm": 1.90072457106355,
+      "learning_rate": 1.3899005928919901e-06,
+      "loss": 0.3546,
+      "step": 800
+    },
+    {
+      "epoch": 0.7857491459248414,
+      "grad_norm": 1.657112918762303,
+      "learning_rate": 1.3314279324265922e-06,
+      "loss": 0.3539,
+      "step": 805
+    },
+    {
+      "epoch": 0.7906295754026355,
+      "grad_norm": 1.749712238075224,
+      "learning_rate": 1.2740223766328813e-06,
+      "loss": 0.3414,
+      "step": 810
+    },
+    {
+      "epoch": 0.7955100048804294,
+      "grad_norm": 1.9679950016790901,
+      "learning_rate": 1.2177006234891548e-06,
+      "loss": 0.3506,
+      "step": 815
+    },
+    {
+      "epoch": 0.8003904343582235,
+      "grad_norm": 2.1432874187201594,
+      "learning_rate": 1.1624790557200255e-06,
+      "loss": 0.3444,
+      "step": 820
+    },
+    {
+      "epoch": 0.8052708638360175,
+      "grad_norm": 1.8338877374043903,
+      "learning_rate": 1.1083737360310487e-06,
+      "loss": 0.3451,
+      "step": 825
+    },
+    {
+      "epoch": 0.8101512933138116,
+      "grad_norm": 1.7170366478986214,
+      "learning_rate": 1.0554004024364573e-06,
+      "loss": 0.3399,
+      "step": 830
+    },
+    {
+      "epoch": 0.8150317227916056,
+      "grad_norm": 1.680152272001201,
+      "learning_rate": 1.0035744636813188e-06,
+      "loss": 0.3351,
+      "step": 835
+    },
+    {
+      "epoch": 0.8199121522693997,
+      "grad_norm": 1.9673664630690946,
+      "learning_rate": 9.529109947594834e-07,
+      "loss": 0.34,
+      "step": 840
+    },
+    {
+      "epoch": 0.8247925817471937,
+      "grad_norm": 1.7733447956263555,
+      "learning_rate": 9.034247325286122e-07,
+      "loss": 0.3334,
+      "step": 845
+    },
+    {
+      "epoch": 0.8296730112249878,
+      "grad_norm": 1.6571893614203954,
+      "learning_rate": 8.551300714235494e-07,
+      "loss": 0.3401,
+      "step": 850
+    },
+    {
+      "epoch": 0.8345534407027818,
+      "grad_norm": 1.6136229922890815,
+      "learning_rate": 8.080410592693183e-07,
+      "loss": 0.3342,
+      "step": 855
+    },
+    {
+      "epoch": 0.8394338701805759,
+      "grad_norm": 1.8811832308333971,
+      "learning_rate": 7.621713931949181e-07,
+      "loss": 0.3466,
+      "step": 860
+    },
+    {
+      "epoch": 0.8443142996583699,
+      "grad_norm": 1.690925430698955,
+      "learning_rate": 7.175344156491432e-07,
+      "loss": 0.3402,
+      "step": 865
+    },
+    {
+      "epoch": 0.849194729136164,
+      "grad_norm": 1.7672934144690045,
+      "learning_rate": 6.741431105195623e-07,
+      "loss": 0.3421,
+      "step": 870
+    },
+    {
+      "epoch": 0.854075158613958,
+      "grad_norm": 1.6317452879722867,
+      "learning_rate": 6.32010099355806e-07,
+      "loss": 0.3387,
+      "step": 875
+    },
+    {
+      "epoch": 0.8589555880917521,
+      "grad_norm": 1.6773249666989778,
+      "learning_rate": 5.911476376982333e-07,
+      "loss": 0.3291,
+      "step": 880
+    },
+    {
+      "epoch": 0.8638360175695461,
+      "grad_norm": 1.8539252747080448,
+      "learning_rate": 5.515676115130819e-07,
+      "loss": 0.3439,
+      "step": 885
+    },
+    {
+      "epoch": 0.8687164470473402,
+      "grad_norm": 1.6252654529292938,
+      "learning_rate": 5.132815337351038e-07,
+      "loss": 0.3333,
+      "step": 890
+    },
+    {
+      "epoch": 0.8735968765251342,
+      "grad_norm": 1.7572937209892616,
+      "learning_rate": 4.763005409187155e-07,
+      "loss": 0.3346,
+      "step": 895
+    },
+    {
+      "epoch": 0.8784773060029283,
+      "grad_norm": 1.6547399559546787,
+      "learning_rate": 4.406353899986221e-07,
+      "loss": 0.3293,
+      "step": 900
+    },
+    {
+      "epoch": 0.8833577354807223,
+      "grad_norm": 1.7444267110302711,
+      "learning_rate": 4.06296455160875e-07,
+      "loss": 0.3384,
+      "step": 905
+    },
+    {
+      "epoch": 0.8882381649585164,
+      "grad_norm": 1.6099424270875666,
+      "learning_rate": 3.732937248252472e-07,
+      "loss": 0.3335,
+      "step": 910
+    },
+    {
+      "epoch": 0.8931185944363104,
+      "grad_norm": 1.7062101914063132,
+      "learning_rate": 3.416367987398345e-07,
+      "loss": 0.3346,
+      "step": 915
+    },
+    {
+      "epoch": 0.8979990239141045,
+      "grad_norm": 1.611954806755092,
+      "learning_rate": 3.113348851887038e-07,
+      "loss": 0.3288,
+      "step": 920
+    },
+    {
+      "epoch": 0.9028794533918985,
+      "grad_norm": 1.7251802193314405,
+      "learning_rate": 2.8239679831341126e-07,
+      "loss": 0.3299,
+      "step": 925
+    },
+    {
+      "epoch": 0.9077598828696926,
+      "grad_norm": 1.6429002170577425,
+      "learning_rate": 2.548309555491674e-07,
+      "loss": 0.3381,
+      "step": 930
+    },
+    {
+      "epoch": 0.9126403123474865,
+      "grad_norm": 1.9456711393571784,
+      "learning_rate": 2.2864537517639618e-07,
+      "loss": 0.3336,
+      "step": 935
+    },
+    {
+      "epoch": 0.9175207418252807,
+      "grad_norm": 1.6656697539121814,
+      "learning_rate": 2.038476739883982e-07,
+      "loss": 0.3319,
+      "step": 940
+    },
+    {
+      "epoch": 0.9224011713030746,
+      "grad_norm": 1.6161650401186363,
+      "learning_rate": 1.804450650757972e-07,
+      "loss": 0.3268,
+      "step": 945
+    },
+    {
+      "epoch": 0.9272816007808687,
+      "grad_norm": 1.7642679481071266,
+      "learning_rate": 1.5844435572841544e-07,
+      "loss": 0.3325,
+      "step": 950
+    },
+    {
+      "epoch": 0.9321620302586627,
+      "grad_norm": 1.6788640143992795,
+      "learning_rate": 1.3785194545518965e-07,
+      "loss": 0.3209,
+      "step": 955
+    },
+    {
+      "epoch": 0.9370424597364568,
+      "grad_norm": 1.6412136858855984,
+      "learning_rate": 1.1867382412269257e-07,
+      "loss": 0.3279,
+      "step": 960
+    },
+    {
+      "epoch": 0.9419228892142508,
+      "grad_norm": 1.660638704825638,
+      "learning_rate": 1.0091557021282283e-07,
+      "loss": 0.3246,
+      "step": 965
+    },
+    {
+      "epoch": 0.9468033186920449,
+      "grad_norm": 1.676587421925541,
+      "learning_rate": 8.458234920014685e-08,
+      "loss": 0.3319,
+      "step": 970
+    },
+    {
+      "epoch": 0.9516837481698389,
+      "grad_norm": 1.6537486653683027,
+      "learning_rate": 6.967891204937737e-08,
+      "loss": 0.3358,
+      "step": 975
+    },
+    {
+      "epoch": 0.956564177647633,
+      "grad_norm": 1.6606920687073268,
+      "learning_rate": 5.620959383343061e-08,
+      "loss": 0.3252,
+      "step": 980
+    },
+    {
+      "epoch": 0.961444607125427,
+      "grad_norm": 1.6627144649185686,
+      "learning_rate": 4.417831247244819e-08,
+      "loss": 0.3277,
+      "step": 985
+    },
+    {
+      "epoch": 0.9663250366032211,
+      "grad_norm": 1.624001266110359,
+      "learning_rate": 3.3588567594161625e-08,
+      "loss": 0.3192,
+      "step": 990
+    },
+    {
+      "epoch": 0.9712054660810151,
+      "grad_norm": 1.672812217323314,
+      "learning_rate": 2.4443439515933754e-08,
+      "loss": 0.3281,
+      "step": 995
+    },
+    {
+      "epoch": 0.9760858955588092,
+      "grad_norm": 1.6582644783125504,
+      "learning_rate": 1.6745588348758836e-08,
+      "loss": 0.3276,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9809663250366032,
+      "grad_norm": 1.7011718232749053,
+      "learning_rate": 1.0497253223502035e-08,
+      "loss": 0.3202,
+      "step": 1005
+    },
+    {
+      "epoch": 0.9858467545143973,
+      "grad_norm": 1.6469486959612,
+      "learning_rate": 5.700251639581544e-09,
+      "loss": 0.3212,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9907271839921913,
+      "grad_norm": 1.6927823132524529,
+      "learning_rate": 2.355978936303127e-09,
+      "loss": 0.3298,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9956076134699854,
+      "grad_norm": 1.6684894053484163,
+      "learning_rate": 4.6540788698534735e-10,
+      "loss": 0.3303,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9995119570522206,
+      "eval_loss": 0.3325524628162384,
+      "eval_runtime": 96.5862,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 0.787,
+      "step": 1024
+    },
+    {
+      "epoch": 0.9995119570522206,
+      "step": 1024,
+      "total_flos": 214352422502400.0,
+      "train_loss": 0.4881494865985587,
+      "train_runtime": 23473.6027,
+      "train_samples_per_second": 1.397,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1024,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 214352422502400.0,
+  "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:ef4a78f35bc06f6fedeb47ccbbc51575f24238258b43c7df467a45ea177aab6d
+size 6584