Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: mistral_gsm8k_sft
+  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. -->
+
+# mistral_gsm8k_sft
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3771
+
+## 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: 4
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3753        | 1.0   | 455  | 0.3771          |
+
+
+### 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": 0.377094566822052,
+    "eval_runtime": 8.9964,
+    "eval_samples": 200,
+    "eval_samples_per_second": 22.231,
+    "eval_steps_per_second": 0.445,
+    "train_loss": 0.5052832438395574,
+    "train_runtime": 3169.7819,
+    "train_samples": 7273,
+    "train_samples_per_second": 2.294,
+    "train_steps_per_second": 0.144
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.377094566822052,
+    "eval_runtime": 8.9964,
+    "eval_samples": 200,
+    "eval_samples_per_second": 22.231,
+    "eval_steps_per_second": 0.445
+}

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 sha256:3dc3de2564d5b0ab0978ff24bfc148b0b5c079abf0f791dae273d870f63e0c6b
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7b6fd3b070f22088b79faff513c283e3be9db9ac623d23e140415591dbe8ba
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bc942743edf1b708e2dc8a6b790709c1a4d5054a25cf68e75a98495d62bd35
+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/Feb08_12-42-26_node01/events.out.tfevents.1707367471.node01.309557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70360eccf5b007830f11a65caa753933088ac0fbd7ebc2398393fdc36412e308
+size 6854

runs/Feb08_13-02-04_node01/events.out.tfevents.1707368647.node01.312921.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1cf1966d4edda66c8a33d7a1f4455c07c5b2d716ef893f350ef5bd704cbf95
+size 5314

runs/Feb08_13-18-58_node01/events.out.tfevents.1707369683.node01.316096.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fbbcb14b7bdd0c4cb47a9619e605c77c0b123cd417b5ed20900cf030b52bda
+size 4544

runs/Feb08_13-24-40_node01/events.out.tfevents.1707369944.node01.318234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cc2a932da860934131e11f46bd9838c9019db6b1d03fc01dbf471dbdfba29d
+size 19067

runs/Feb08_13-24-40_node01/events.out.tfevents.1707373106.node01.318234.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f858c08eae125ed5d561dfdb8941224900f17e1cce507d1e99cb0376e626c0
+size 359

runs/Feb09_11-38-39_node01/events.out.tfevents.1707450048.node01.469454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45fb23fe17188589f89a2c91aaca375a338b025069ab200bae54c5670aadc34
+size 19381

runs/Feb09_11-38-39_node01/events.out.tfevents.1707453227.node01.469454.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6ced4927e23b56e8f37545622849ee3ae07d22c9f4b26bcd603ac67616a342
+size 359

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 +1,43 @@
+{
+  "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": 0.5052832438395574,
+    "train_runtime": 3169.7819,
+    "train_samples": 7273,
+    "train_samples_per_second": 2.294,
+    "train_steps_per_second": 0.144
+}

trainer_state.json

@@ -0,0 +1,590 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 455,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9999761633493754e-05,
+      "loss": 1.0423,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9994041405510705e-05,
+      "loss": 2.4374,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.997617272301248e-05,
+      "loss": 0.8502,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9946415246951928e-05,
+      "loss": 0.646,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9904804439875635e-05,
+      "loss": 0.6536,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9851389890168738e-05,
+      "loss": 0.5722,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9786235252959555e-05,
+      "loss": 0.6106,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.6526,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9621030198436007e-05,
+      "loss": 0.6348,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.952117665910714e-05,
+      "loss": 0.5979,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9409976553623767e-05,
+      "loss": 0.5756,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9287562401253023e-05,
+      "loss": 0.5432,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9154080085253665e-05,
+      "loss": 0.5857,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.5409,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.5595,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8688879687250067e-05,
+      "loss": 0.5723,
+      "step": 75
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8512844415843514e-05,
+      "loss": 0.5951,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8326664226872063e-05,
+      "loss": 0.558,
+      "step": 85
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8130560994785325e-05,
+      "loss": 0.5562,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7924768419510906e-05,
+      "loss": 0.5595,
+      "step": 95
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7709531747949796e-05,
+      "loss": 0.5818,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.5446,
+      "step": 105
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7251763071433767e-05,
+      "loss": 0.5287,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7009776598061496e-05,
+      "loss": 0.5039,
+      "step": 115
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6759436441447544e-05,
+      "loss": 0.5484,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6501040936687444e-05,
+      "loss": 0.5968,
+      "step": 125
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.514,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5961324854692254e-05,
+      "loss": 0.5413,
+      "step": 135
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.497,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5393200344991993e-05,
+      "loss": 0.4721,
+      "step": 145
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5099326043901361e-05,
+      "loss": 0.5212,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4799374779597866e-05,
+      "loss": 0.5039,
+      "step": 155
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4493704009671614e-05,
+      "loss": 0.5297,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4182678007755653e-05,
+      "loss": 0.5203,
+      "step": 165
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.3866667429414188e-05,
+      "loss": 0.5279,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.5102,
+      "step": 175
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3221204417984907e-05,
+      "loss": 0.5044,
+      "step": 180
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2892521195365679e-05,
+      "loss": 0.5134,
+      "step": 185
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2560390900575472e-05,
+      "loss": 0.463,
+      "step": 190
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.4506,
+      "step": 195
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1887375954529167e-05,
+      "loss": 0.5345,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1547293347902813e-05,
+      "loss": 0.4631,
+      "step": 205
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 0.5217,
+      "step": 210
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.0862003798806195e-05,
+      "loss": 0.4843,
+      "step": 215
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0517613528842096e-05,
+      "loss": 0.4694,
+      "step": 220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0172606409053887e-05,
+      "loss": 0.4658,
+      "step": 225
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.827393590946116e-06,
+      "loss": 0.5038,
+      "step": 230
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.482386471157905e-06,
+      "loss": 0.4652,
+      "step": 235
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.137996201193807e-06,
+      "loss": 0.4731,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 0.4803,
+      "step": 245
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.452706652097187e-06,
+      "loss": 0.4798,
+      "step": 250
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.112624045470834e-06,
+      "loss": 0.4305,
+      "step": 255
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.4479,
+      "step": 260
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.4396090994245295e-06,
+      "loss": 0.4585,
+      "step": 265
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.107478804634324e-06,
+      "loss": 0.4788,
+      "step": 270
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.778795582015096e-06,
+      "loss": 0.4784,
+      "step": 275
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.4377,
+      "step": 280
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.133332570585813e-06,
+      "loss": 0.4303,
+      "step": 285
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.8173219922443516e-06,
+      "loss": 0.4167,
+      "step": 290
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.5062959903283855e-06,
+      "loss": 0.4651,
+      "step": 295
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.200625220402139e-06,
+      "loss": 0.45,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.900673956098644e-06,
+      "loss": 0.436,
+      "step": 305
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.606799655008009e-06,
+      "loss": 0.445,
+      "step": 310
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 0.4008,
+      "step": 315
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.038675145307747e-06,
+      "loss": 0.432,
+      "step": 320
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.4396,
+      "step": 325
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4989590633125583e-06,
+      "loss": 0.4207,
+      "step": 330
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2405635585524566e-06,
+      "loss": 0.4439,
+      "step": 335
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9902234019385056e-06,
+      "loss": 0.4375,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.748236928566238e-06,
+      "loss": 0.423,
+      "step": 345
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.3762,
+      "step": 350
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.290468252050204e-06,
+      "loss": 0.4148,
+      "step": 355
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.075231580489098e-06,
+      "loss": 0.4162,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8694390052146737e-06,
+      "loss": 0.376,
+      "step": 365
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6733357731279375e-06,
+      "loss": 0.4164,
+      "step": 370
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.4871555841564889e-06,
+      "loss": 0.4212,
+      "step": 375
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.311120312749935e-06,
+      "loss": 0.4117,
+      "step": 380
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 0.3915,
+      "step": 385
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.4401,
+      "step": 390
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.459199147463371e-07,
+      "loss": 0.4279,
+      "step": 395
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.124375987469767e-07,
+      "loss": 0.4203,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.900234463762367e-07,
+      "loss": 0.4094,
+      "step": 405
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.788233408928588e-07,
+      "loss": 0.4232,
+      "step": 410
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.7896980156399533e-07,
+      "loss": 0.3935,
+      "step": 415
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 0.3882,
+      "step": 420
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.1376474704044693e-07,
+      "loss": 0.3723,
+      "step": 425
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4861010983126202e-07,
+      "loss": 0.445,
+      "step": 430
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.519556012436815e-08,
+      "loss": 0.3977,
+      "step": 435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.3584753048073756e-08,
+      "loss": 0.3754,
+      "step": 440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.3827276987524738e-08,
+      "loss": 0.3606,
+      "step": 445
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.958594489295921e-09,
+      "loss": 0.4188,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.3753,
+      "step": 455
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.377094566822052,
+      "eval_runtime": 10.8473,
+      "eval_samples_per_second": 18.438,
+      "eval_steps_per_second": 0.369,
+      "step": 455
+    },
+    {
+      "epoch": 1.0,
+      "step": 455,
+      "total_flos": 3232394280960.0,
+      "train_loss": 0.5052832438395574,
+      "train_runtime": 3169.7819,
+      "train_samples_per_second": 2.294,
+      "train_steps_per_second": 0.144
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 455,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 3232394280960.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ad38fa1fd5326251f448cb5e477218462a717c0dc07cbab7c2c056cb4a0dd4
+size 5307