Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+license: cc-by-nc-4.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+model-index:
+- name: meow
+  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. -->
+
+# meow
+
+This model is a fine-tuned version of [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) on HuggingFaceH4/no_robots dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3831
+
+## 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: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.3864        | 0.11  | 2    | 2.3831          |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.0
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.11,
+    "eval_loss": 2.3830578327178955,
+    "eval_runtime": 21.8336,
+    "eval_samples": 500,
+    "eval_samples_per_second": 22.9,
+    "eval_steps_per_second": 2.885,
+    "train_loss": 3.4910590648651123,
+    "train_runtime": 1414.3444,
+    "train_samples": 9500,
+    "train_samples_per_second": 6.717,
+    "train_steps_per_second": 0.013
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.11,
+    "eval_loss": 2.3830578327178955,
+    "eval_runtime": 21.8336,
+    "eval_samples": 500,
+    "eval_samples_per_second": 22.9,
+    "eval_steps_per_second": 2.885
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false
+}

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 21463048192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeff49c036ee77b19e626cf494bdc0b2a4e15866401235029f9998437c791d64
+size 4300082336

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.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 %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.11,
+    "train_loss": 3.4910590648651123,
+    "train_runtime": 1414.3444,
+    "train_samples": 9500,
+    "train_samples_per_second": 6.717,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.10778947368421053,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 2.3864,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 2.3830578327178955,
+      "eval_runtime": 22.0897,
+      "eval_samples_per_second": 22.635,
+      "eval_steps_per_second": 2.852,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "step": 2,
+      "total_flos": 1.9781391004729344e+17,
+      "train_loss": 3.4910590648651123,
+      "train_runtime": 1414.3444,
+      "train_samples_per_second": 6.717,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.9781391004729344e+17,
+  "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:a74325f8b8748877c9362cfadd0e5aa940fd12a5c20f182cf3978aeb70c119ec
+size 4728