Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral_channel_targeter_0_1_5120
+  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_channel_targeter_0_1_5120
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0415
+
+## 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: 5e-07
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 24
+- total_eval_batch_size: 12
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0511        | 1.0   | 273  | 0.0516          |
+| 0.0412        | 2.0   | 547  | 0.0408          |
+| 0.032         | 3.0   | 820  | 0.0394          |
+| 0.0258        | 3.99  | 1092 | 0.0415          |
+
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.99,
+    "eval_loss": 0.04152332618832588,
+    "eval_runtime": 48.5998,
+    "eval_samples": 347,
+    "eval_samples_per_second": 7.14,
+    "eval_steps_per_second": 0.597,
+    "train_loss": 0.20003320886702328,
+    "train_runtime": 14516.5669,
+    "train_samples": 6555,
+    "train_samples_per_second": 1.806,
+    "train_steps_per_second": 0.075
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.99,
+    "eval_loss": 0.04152332618832588,
+    "eval_runtime": 48.5998,
+    "eval_samples": 347,
+    "eval_samples_per_second": 7.14,
+    "eval_steps_per_second": 0.597
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6cc5f9a5f81b170b73047a870dd6ad16e51dd1566e00e4714fa891566bd2863
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ef22a25b19b584f569762623ca5bc44cd9527edc764c404da6ddca2ec1f732
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5f4a3388cca857661480f6d9cb4aefd3ab96baaff9ec90e42ac9b06dad9a79
+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"
+  }
+}

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{{ message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '\n###Response :\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '###Response :\n' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 5120,
+  "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": 3.99,
+    "train_loss": 0.20003320886702328,
+    "train_runtime": 14516.5669,
+    "train_samples": 6555,
+    "train_samples_per_second": 1.806,
+    "train_steps_per_second": 0.075
+}

trainer_state.json

@@ -0,0 +1,716 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9926873857404024,
+  "eval_steps": 500,
+  "global_step": 1092,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.545454545454545e-08,
+      "loss": 6.3231,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.09090909090909e-08,
+      "loss": 5.5694,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.3636363636363635e-07,
+      "loss": 3.253,
+      "step": 30
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.818181818181818e-07,
+      "loss": 1.3696,
+      "step": 40
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.2727272727272726e-07,
+      "loss": 0.5924,
+      "step": 50
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.727272727272727e-07,
+      "loss": 0.2712,
+      "step": 60
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.1818181818181815e-07,
+      "loss": 0.1977,
+      "step": 70
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.636363636363636e-07,
+      "loss": 0.1782,
+      "step": 80
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.090909090909091e-07,
+      "loss": 0.1586,
+      "step": 90
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.545454545454545e-07,
+      "loss": 0.1282,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 5e-07,
+      "loss": 0.083,
+      "step": 110
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.998720766742264e-07,
+      "loss": 0.0686,
+      "step": 120
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.994884376119235e-07,
+      "loss": 0.0636,
+      "step": 130
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.988494754241696e-07,
+      "loss": 0.0618,
+      "step": 140
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.979558440163095e-07,
+      "loss": 0.0609,
+      "step": 150
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.968084579187565e-07,
+      "loss": 0.0572,
+      "step": 160
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.954084913510755e-07,
+      "loss": 0.0576,
+      "step": 170
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.937573770203005e-07,
+      "loss": 0.0616,
+      "step": 180
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.918568046547231e-07,
+      "loss": 0.058,
+      "step": 190
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.897087192746464e-07,
+      "loss": 0.0581,
+      "step": 200
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.873153192018773e-07,
+      "loss": 0.0561,
+      "step": 210
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.846790538099934e-07,
+      "loss": 0.0527,
+      "step": 220
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.818026210176872e-07,
+      "loss": 0.0527,
+      "step": 230
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.786889645277519e-07,
+      "loss": 0.0546,
+      "step": 240
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.7534127081453554e-07,
+      "loss": 0.0513,
+      "step": 250
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.71762965862946e-07,
+      "loss": 0.0489,
+      "step": 260
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.679577116623435e-07,
+      "loss": 0.0511,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.051615118980407715,
+      "eval_runtime": 48.6349,
+      "eval_samples_per_second": 7.135,
+      "eval_steps_per_second": 0.596,
+      "step": 273
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 4.639294024589101e-07,
+      "loss": 0.0476,
+      "step": 280
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.596821607703302e-07,
+      "loss": 0.0486,
+      "step": 290
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.5522033316686106e-07,
+      "loss": 0.0473,
+      "step": 300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 4.5054848582311134e-07,
+      "loss": 0.0501,
+      "step": 310
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.456713998450786e-07,
+      "loss": 0.0435,
+      "step": 320
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 4.405940663772302e-07,
+      "loss": 0.0393,
+      "step": 330
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.353216814946321e-07,
+      "loss": 0.0489,
+      "step": 340
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.2985964088535603e-07,
+      "loss": 0.039,
+      "step": 350
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.2421353432860386e-07,
+      "loss": 0.045,
+      "step": 360
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.1838913997420285e-07,
+      "loss": 0.0389,
+      "step": 370
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.1239241842932446e-07,
+      "loss": 0.0407,
+      "step": 380
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.0622950665847893e-07,
+      "loss": 0.0442,
+      "step": 390
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.9990671170302747e-07,
+      "loss": 0.04,
+      "step": 400
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.934305042266413e-07,
+      "loss": 0.0398,
+      "step": 410
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 3.868075118933106e-07,
+      "loss": 0.0478,
+      "step": 420
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 3.8004451258468224e-07,
+      "loss": 0.0426,
+      "step": 430
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.7314842746366625e-07,
+      "loss": 0.0398,
+      "step": 440
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.6612631389141073e-07,
+      "loss": 0.0407,
+      "step": 450
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.5898535820489257e-07,
+      "loss": 0.0418,
+      "step": 460
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.5173286836251683e-07,
+      "loss": 0.0411,
+      "step": 470
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.4437626646524965e-07,
+      "loss": 0.0363,
+      "step": 480
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.369230811609397e-07,
+      "loss": 0.0397,
+      "step": 490
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.2938093993960107e-07,
+      "loss": 0.0439,
+      "step": 500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.217575613275414e-07,
+      "loss": 0.0437,
+      "step": 510
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.1406074698832646e-07,
+      "loss": 0.0445,
+      "step": 520
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.0629837373866113e-07,
+      "loss": 0.0401,
+      "step": 530
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.984783854873614e-07,
+      "loss": 0.0412,
+      "step": 540
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.04081326350569725,
+      "eval_runtime": 48.5536,
+      "eval_samples_per_second": 7.147,
+      "eval_steps_per_second": 0.597,
+      "step": 547
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.9060878510566426e-07,
+      "loss": 0.0354,
+      "step": 550
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.8269762623719636e-07,
+      "loss": 0.0325,
+      "step": 560
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.747530050559831e-07,
+      "loss": 0.0327,
+      "step": 570
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.6678305198093267e-07,
+      "loss": 0.0373,
+      "step": 580
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2.587959233552739e-07,
+      "loss": 0.0377,
+      "step": 590
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 2.507997930994643e-07,
+      "loss": 0.0328,
+      "step": 600
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.42802844346109e-07,
+      "loss": 0.0357,
+      "step": 610
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.3481326106545248e-07,
+      "loss": 0.0334,
+      "step": 620
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.2683921969001343e-07,
+      "loss": 0.0318,
+      "step": 630
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.1888888074693235e-07,
+      "loss": 0.0324,
+      "step": 640
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.109703805065985e-07,
+      "loss": 0.0321,
+      "step": 650
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.0309182265609888e-07,
+      "loss": 0.0328,
+      "step": 660
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.952612700060137e-07,
+      "loss": 0.0332,
+      "step": 670
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.874867362390442e-07,
+      "loss": 0.0329,
+      "step": 680
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.7977617770891678e-07,
+      "loss": 0.0328,
+      "step": 690
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.7213748529795756e-07,
+      "loss": 0.0272,
+      "step": 700
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.645784763416686e-07,
+      "loss": 0.0373,
+      "step": 710
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.5710688662857186e-07,
+      "loss": 0.031,
+      "step": 720
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.4973036248350665e-07,
+      "loss": 0.0342,
+      "step": 730
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.4245645294248333e-07,
+      "loss": 0.037,
+      "step": 740
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.352926020271006e-07,
+      "loss": 0.0334,
+      "step": 750
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.2824614112643428e-07,
+      "loss": 0.034,
+      "step": 760
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.2132428149419105e-07,
+      "loss": 0.036,
+      "step": 770
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.1453410686880843e-07,
+      "loss": 0.0383,
+      "step": 780
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.0788256622405165e-07,
+      "loss": 0.0266,
+      "step": 790
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.0137646665752717e-07,
+      "loss": 0.0318,
+      "step": 800
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 9.502246642438996e-08,
+      "loss": 0.0336,
+      "step": 810
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.882706812337432e-08,
+      "loss": 0.032,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.03941405192017555,
+      "eval_runtime": 48.6039,
+      "eval_samples_per_second": 7.139,
+      "eval_steps_per_second": 0.597,
+      "step": 820
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 8.279661204212143e-08,
+      "loss": 0.0254,
+      "step": 830
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 7.693726966861405e-08,
+      "loss": 0.0328,
+      "step": 840
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 7.125503737535843e-08,
+      "loss": 0.0231,
+      "step": 850
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 6.575573028277659e-08,
+      "loss": 0.0276,
+      "step": 860
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 6.044497630809053e-08,
+      "loss": 0.0239,
+      "step": 870
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 5.5328210405786696e-08,
+      "loss": 0.0251,
+      "step": 880
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 5.041066900555646e-08,
+      "loss": 0.025,
+      "step": 890
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 4.569738465340414e-08,
+      "loss": 0.0281,
+      "step": 900
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 4.1193180861406965e-08,
+      "loss": 0.0246,
+      "step": 910
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.690266717139728e-08,
+      "loss": 0.0252,
+      "step": 920
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 3.2830234437619035e-08,
+      "loss": 0.0293,
+      "step": 930
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.8980050333186595e-08,
+      "loss": 0.027,
+      "step": 940
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.5356055084943763e-08,
+      "loss": 0.025,
+      "step": 950
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.1961957441088557e-08,
+      "loss": 0.0255,
+      "step": 960
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.8801230875689688e-08,
+      "loss": 0.0273,
+      "step": 970
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 1.5877110033980152e-08,
+      "loss": 0.0291,
+      "step": 980
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.3192587422064166e-08,
+      "loss": 0.0273,
+      "step": 990
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.0750410344426781e-08,
+      "loss": 0.0303,
+      "step": 1000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 8.553078092379123e-09,
+      "loss": 0.0302,
+      "step": 1010
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 6.6028393863173935e-09,
+      "loss": 0.024,
+      "step": 1020
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 4.901690074412185e-09,
+      "loss": 0.0245,
+      "step": 1030
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 3.451371090084476e-09,
+      "loss": 0.0211,
+      "step": 1040
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 2.2533666703574983e-09,
+      "loss": 0.0224,
+      "step": 1050
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.308902836908543e-09,
+      "loss": 0.0201,
+      "step": 1060
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 6.189461413748098e-10,
+      "loss": 0.0242,
+      "step": 1070
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 1.842026761973703e-10,
+      "loss": 0.0301,
+      "step": 1080
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 5.117352015610033e-12,
+      "loss": 0.0258,
+      "step": 1090
+    },
+    {
+      "epoch": 3.99,
+      "eval_loss": 0.04152332618832588,
+      "eval_runtime": 48.6503,
+      "eval_samples_per_second": 7.133,
+      "eval_steps_per_second": 0.596,
+      "step": 1092
+    },
+    {
+      "epoch": 3.99,
+      "step": 1092,
+      "total_flos": 193702916259840.0,
+      "train_loss": 0.20003320886702328,
+      "train_runtime": 14516.5669,
+      "train_samples_per_second": 1.806,
+      "train_steps_per_second": 0.075
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1092,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 193702916259840.0,
+  "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 sha256:82d71d798abe99a39938a65e4fbe6e791075178e4bd603783911ad9c8eaf39db
+size 5371