Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-critique-7b-score
+  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. -->
+
+# zephyr-critique-7b-score
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5010
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4995        | 1.0   | 804  | 0.5010          |
+
+
+### Framework versions
+
+- Transformers 4.36.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.5010353326797485,
+    "eval_runtime": 535.6168,
+    "eval_samples": 25241,
+    "eval_samples_per_second": 10.666,
+    "eval_steps_per_second": 0.168,
+    "train_loss": 0.6083842945929191,
+    "train_runtime": 18940.7815,
+    "train_samples": 227177,
+    "train_samples_per_second": 2.718,
+    "train_steps_per_second": 0.042
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.5010353326797485,
+    "eval_runtime": 535.6168,
+    "eval_samples": 25241,
+    "eval_samples_per_second": 10.666,
+    "eval_steps_per_second": 0.168
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d877c3231e9ba051a70f84d5b894dea5b34e78cfd3e93f7867634211c1431c64
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c44e7522060c665364ffffd2bbe83f2ca6f5fc68dac4174b8c70b22fd284c20
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635407192f4c4ef484f022b6069085284e3bb773f1290bcdddfd39886162a6df
+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/Jan29_02-49-06_node01/events.out.tfevents.1706467766.node01.2335800.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e951bbd884a40e88c4dc0b60447f102e25d5e010ddd9d83b68fc745be23a0aa5
+size 30254

runs/Jan29_02-49-06_node01/events.out.tfevents.1706487242.node01.2335800.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d65182733976fcac9998fea259fe9cc0d0beacdecfdfd8ef27a4468b4a36c23
+size 359

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": true,
+  "model_max_length": 4096,
+  "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 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6083842945929191,
+    "train_runtime": 18940.7815,
+    "train_samples": 227177,
+    "train_samples_per_second": 2.718,
+    "train_steps_per_second": 0.042
+}

trainer_state.json

@@ -0,0 +1,1004 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993784959602238,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9999923659130937e-05,
+      "loss": 1.1511,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9998091536552034e-05,
+      "loss": 1.106,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9992366874654684e-05,
+      "loss": 0.9112,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.998282819936954e-05,
+      "loss": 0.8622,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.8476,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.995232482639774e-05,
+      "loss": 0.834,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9931371771625545e-05,
+      "loss": 0.8008,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9906627984850487e-05,
+      "loss": 0.7916,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.7707,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.984580743667168e-05,
+      "loss": 0.7505,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9809753890026543e-05,
+      "loss": 0.7624,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9769956032034873e-05,
+      "loss": 0.756,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.742,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9679189567595917e-05,
+      "loss": 0.7512,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9628255606044562e-05,
+      "loss": 0.7402,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.957364660971485e-05,
+      "loss": 0.725,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.7333,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.945348828291703e-05,
+      "loss": 0.7349,
+      "step": 85
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9387984816003868e-05,
+      "loss": 0.7327,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9318898023916416e-05,
+      "loss": 0.734,
+      "step": 95
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.7408,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9170081301576444e-05,
+      "loss": 0.7348,
+      "step": 105
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9090408173578923e-05,
+      "loss": 0.7194,
+      "step": 110
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9007265303236133e-05,
+      "loss": 0.7247,
+      "step": 115
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.7078,
+      "step": 120
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8830698587880195e-05,
+      "loss": 0.7146,
+      "step": 125
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8737342137091523e-05,
+      "loss": 0.6873,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.864065070668265e-05,
+      "loss": 0.7052,
+      "step": 135
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.7139,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8437411791503264e-05,
+      "loss": 0.6942,
+      "step": 145
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8330941881540917e-05,
+      "loss": 0.7058,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8221292111964958e-05,
+      "loss": 0.7059,
+      "step": 155
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.6936,
+      "step": 160
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.799262160178843e-05,
+      "loss": 0.7181,
+      "step": 165
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.787368814304992e-05,
+      "loss": 0.7021,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7751749355107073e-05,
+      "loss": 0.6991,
+      "step": 175
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.7092,
+      "step": 180
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7499043093531113e-05,
+      "loss": 0.6885,
+      "step": 185
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7368372076030654e-05,
+      "loss": 0.6892,
+      "step": 190
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7234888604774576e-05,
+      "loss": 0.6858,
+      "step": 195
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.6746,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.695968915370211e-05,
+      "loss": 0.6741,
+      "step": 205
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.681807821550438e-05,
+      "loss": 0.674,
+      "step": 210
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6673864866694714e-05,
+      "loss": 0.6656,
+      "step": 215
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.6657,
+      "step": 220
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6377852090274278e-05,
+      "loss": 0.6948,
+      "step": 225
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.622616564857629e-05,
+      "loss": 0.6631,
+      "step": 230
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6072102724966047e-05,
+      "loss": 0.6497,
+      "step": 235
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.657,
+      "step": 240
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.575708353541596e-05,
+      "loss": 0.6495,
+      "step": 245
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5596247509997843e-05,
+      "loss": 0.6475,
+      "step": 250
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5433275437816004e-05,
+      "loss": 0.6446,
+      "step": 255
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.6609,
+      "step": 260
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5101172765725555e-05,
+      "loss": 0.6385,
+      "step": 265
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4932168926979074e-05,
+      "loss": 0.6461,
+      "step": 270
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4761282515409326e-05,
+      "loss": 0.6395,
+      "step": 275
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.64,
+      "step": 280
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4414123571844178e-05,
+      "loss": 0.6448,
+      "step": 285
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4237983547879664e-05,
+      "loss": 0.6264,
+      "step": 290
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4060225916576307e-05,
+      "loss": 0.6346,
+      "step": 295
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.6232,
+      "step": 300
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3700129818638133e-05,
+      "loss": 0.619,
+      "step": 305
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3517928798051442e-05,
+      "loss": 0.6344,
+      "step": 310
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3334385009760032e-05,
+      "loss": 0.6331,
+      "step": 315
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.6304,
+      "step": 320
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.2963549845136123e-05,
+      "loss": 0.6226,
+      "step": 325
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2776400013875006e-05,
+      "loss": 0.622,
+      "step": 330
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.6149,
+      "step": 335
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.6169,
+      "step": 340
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.220887986048825e-05,
+      "loss": 0.6006,
+      "step": 345
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2017923612880579e-05,
+      "loss": 0.6051,
+      "step": 350
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.182619713858172e-05,
+      "loss": 0.5993,
+      "step": 355
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.5935,
+      "step": 360
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1440726498342376e-05,
+      "loss": 0.603,
+      "step": 365
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1247129463727329e-05,
+      "loss": 0.5972,
+      "step": 370
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1053056408913001e-05,
+      "loss": 0.5868,
+      "step": 375
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.595,
+      "step": 380
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0663778697170641e-05,
+      "loss": 0.5847,
+      "step": 385
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0468722624699401e-05,
+      "loss": 0.6046,
+      "step": 390
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0273487644228867e-05,
+      "loss": 0.6025,
+      "step": 395
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.5918,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.88277907819334e-06,
+      "loss": 0.5865,
+      "step": 405
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.68745462323176e-06,
+      "loss": 0.5937,
+      "step": 410
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.492249464555658e-06,
+      "loss": 0.5869,
+      "step": 415
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.5793,
+      "step": 420
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.102494995614217e-06,
+      "loss": 0.5606,
+      "step": 425
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.908094451780408e-06,
+      "loss": 0.5835,
+      "step": 430
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.714110680312082e-06,
+      "loss": 0.5674,
+      "step": 435
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.5638,
+      "step": 440
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.327689435881421e-06,
+      "loss": 0.5635,
+      "step": 445
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.13539945708319e-06,
+      "loss": 0.574,
+      "step": 450
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.943821182681204e-06,
+      "loss": 0.573,
+      "step": 455
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.5605,
+      "step": 460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.563091943609984e-06,
+      "loss": 0.5625,
+      "step": 465
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.374086300508019e-06,
+      "loss": 0.5686,
+      "step": 470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.1860829494686536e-06,
+      "loss": 0.5629,
+      "step": 475
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.5584,
+      "step": 480
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.813369751638927e-06,
+      "loss": 0.5556,
+      "step": 485
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.628802166751496e-06,
+      "loss": 0.5546,
+      "step": 490
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.445521343432189e-06,
+      "loss": 0.5474,
+      "step": 495
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.5602,
+      "step": 500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.083099291450012e-06,
+      "loss": 0.5611,
+      "step": 505
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.904096396634935e-06,
+      "loss": 0.5654,
+      "step": 510
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.726656878282546e-06,
+      "loss": 0.5508,
+      "step": 515
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.5526,
+      "step": 520
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.3767382578534e-06,
+      "loss": 0.5439,
+      "step": 525
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.204392717156021e-06,
+      "loss": 0.5425,
+      "step": 530
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.033877624700662e-06,
+      "loss": 0.5332,
+      "step": 535
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.5375,
+      "step": 540
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.6985983984620934e-06,
+      "loss": 0.5402,
+      "step": 545
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.5339622383085095e-06,
+      "loss": 0.5328,
+      "step": 550
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.371412424809607e-06,
+      "loss": 0.5293,
+      "step": 555
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.5289,
+      "step": 560
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.052819194052821e-06,
+      "loss": 0.5362,
+      "step": 565
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.896897381502081e-06,
+      "loss": 0.5299,
+      "step": 570
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.743305078604653e-06,
+      "loss": 0.5237,
+      "step": 575
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.5289,
+      "step": 580
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.44334259047297e-06,
+      "loss": 0.5249,
+      "step": 585
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.297086898727583e-06,
+      "loss": 0.5209,
+      "step": 590
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.1533896599119297e-06,
+      "loss": 0.5331,
+      "step": 595
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.5185,
+      "step": 600
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.8738889363341806e-06,
+      "loss": 0.5122,
+      "step": 605
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.73819213495501e-06,
+      "loss": 0.5082,
+      "step": 610
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.605267112551154e-06,
+      "loss": 0.5266,
+      "step": 615
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.5207,
+      "step": 620
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.347934273373138e-06,
+      "loss": 0.5238,
+      "step": 625
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.2236246786624794e-06,
+      "loss": 0.5102,
+      "step": 630
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1022832695635085e-06,
+      "loss": 0.5122,
+      "step": 635
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.5172,
+      "step": 640
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.868689118102931e-06,
+      "loss": 0.5218,
+      "step": 645
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7565255369212664e-06,
+      "loss": 0.5142,
+      "step": 650
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6475084296790056e-06,
+      "loss": 0.5092,
+      "step": 655
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.5105,
+      "step": 660
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.439078864275476e-06,
+      "loss": 0.5086,
+      "step": 665
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.5069,
+      "step": 670
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2437186156920167e-06,
+      "loss": 0.4965,
+      "step": 675
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.4952,
+      "step": 680
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0617259257816192e-06,
+      "loss": 0.5007,
+      "step": 685
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.75830047614117e-07,
+      "loss": 0.5157,
+      "step": 690
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.933786291470859e-07,
+      "loss": 0.5003,
+      "step": 695
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.5037,
+      "step": 700
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.389337289917653e-07,
+      "loss": 0.5079,
+      "step": 705
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.669991977928103e-07,
+      "loss": 0.4994,
+      "step": 710
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.986270047720244e-07,
+      "loss": 0.5035,
+      "step": 715
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.5137,
+      "step": 720
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.7267265225041883e-07,
+      "loss": 0.5061,
+      "step": 725
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1513856860517676e-07,
+      "loss": 0.4981,
+      "step": 730
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.612629564990622e-07,
+      "loss": 0.4999,
+      "step": 735
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.4889,
+      "step": 740
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.645679983524252e-07,
+      "loss": 0.5082,
+      "step": 745
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2178556007054876e-07,
+      "loss": 0.4924,
+      "step": 750
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.827353947576671e-07,
+      "loss": 0.5059,
+      "step": 755
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.4914,
+      "step": 760
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.158900734189039e-07,
+      "loss": 0.4934,
+      "step": 765
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.812043176351093e-08,
+      "loss": 0.5042,
+      "step": 770
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.413408207944005e-08,
+      "loss": 0.494,
+      "step": 775
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.5009,
+      "step": 780
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7546432733128737e-08,
+      "loss": 0.4886,
+      "step": 785
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.495909830917075e-08,
+      "loss": 0.4926,
+      "step": 790
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.182981002679223e-09,
+      "loss": 0.5008,
+      "step": 795
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.4995,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5010353326797485,
+      "eval_runtime": 537.3572,
+      "eval_samples_per_second": 10.632,
+      "eval_steps_per_second": 0.167,
+      "step": 804
+    },
+    {
+      "epoch": 1.0,
+      "step": 804,
+      "total_flos": 336473106677760.0,
+      "train_loss": 0.6083842945929191,
+      "train_runtime": 18940.7815,
+      "train_samples_per_second": 2.718,
+      "train_steps_per_second": 0.042
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 336473106677760.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b1f7cb88fafdd5058e3d506c727ab6969994ed2f1fd902aea04e0d9c9195c5
+size 5307