Model save

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: BioMistral/BioMistral-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: bio_mistral_channel_targeter_new_prompt
+  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. -->
+
+# bio_mistral_channel_targeter_new_prompt
+
+This model is a fine-tuned version of [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0644
+
+## 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
+- total_train_batch_size: 12
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0524        | 1.0   | 317  | 0.0502          |
+| 0.0466        | 2.0   | 634  | 0.0421          |
+| 0.0158        | 3.0   | 951  | 0.0503          |
+| 0.0047        | 4.0   | 1268 | 0.0644          |
+
+
+### 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": 4.0,
+    "eval_loss": 0.06437445431947708,
+    "eval_runtime": 21.298,
+    "eval_samples": 206,
+    "eval_samples_per_second": 9.672,
+    "eval_steps_per_second": 0.845,
+    "train_loss": 0.16973004465752314,
+    "train_runtime": 6166.9886,
+    "train_samples": 3798,
+    "train_samples_per_second": 2.463,
+    "train_steps_per_second": 0.206
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "BioMistral/BioMistral-7B",
+  "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": "4.36.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.06437445431947708,
+    "eval_runtime": 21.298,
+    "eval_samples": 206,
+    "eval_samples_per_second": 9.672,
+    "eval_steps_per_second": 0.845
+}

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:cf479a53737a7cd61adc3b38a3c9ee9f97dc61ea40dbf7852e713633cfa3852e
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2aaf64596ba49552eb964370290b9cd1d7032399b1ddaffcb7b473fcef61f25
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074b76269a1df62b05368525c4a6426c3d73b567842741d4e20f239541c4179d
+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": 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": 4.0,
+    "train_loss": 0.16973004465752314,
+    "train_runtime": 6166.9886,
+    "train_samples": 3798,
+    "train_samples_per_second": 2.463,
+    "train_steps_per_second": 0.206
+}

trainer_state.json

@@ -0,0 +1,818 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.937007874015748e-08,
+      "loss": 5.1243,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.874015748031496e-08,
+      "loss": 4.9463,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.1811023622047243e-07,
+      "loss": 4.0023,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.5748031496062992e-07,
+      "loss": 2.1698,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.968503937007874e-07,
+      "loss": 0.7212,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.3622047244094486e-07,
+      "loss": 0.2513,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.7559055118110235e-07,
+      "loss": 0.1898,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.1496062992125984e-07,
+      "loss": 0.1545,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.5433070866141727e-07,
+      "loss": 0.1172,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.937007874015748e-07,
+      "loss": 0.0956,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.330708661417323e-07,
+      "loss": 0.1053,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.7244094488188973e-07,
+      "loss": 0.0706,
+      "step": 120
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.999914713850033e-07,
+      "loss": 0.0664,
+      "step": 130
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.998398677500815e-07,
+      "loss": 0.0616,
+      "step": 140
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.994988716220417e-07,
+      "loss": 0.0576,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.989687414948845e-07,
+      "loss": 0.0568,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.982498792366836e-07,
+      "loss": 0.058,
+      "step": 170
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.973428297849485e-07,
+      "loss": 0.0586,
+      "step": 180
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.962482807335314e-07,
+      "loss": 0.0677,
+      "step": 190
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.949670618113922e-07,
+      "loss": 0.0617,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.935001442536189e-07,
+      "loss": 0.0571,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.918486400651768e-07,
+      "loss": 0.0584,
+      "step": 220
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.90013801177947e-07,
+      "loss": 0.0596,
+      "step": 230
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.87997018501693e-07,
+      "loss": 0.0536,
+      "step": 240
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.857998208696731e-07,
+      "loss": 0.0569,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.83423873879701e-07,
+      "loss": 0.0594,
+      "step": 260
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.808709786315288e-07,
+      "loss": 0.0572,
+      "step": 270
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.781430703615145e-07,
+      "loss": 0.0522,
+      "step": 280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.752422169756047e-07,
+      "loss": 0.057,
+      "step": 290
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.721706174817478e-07,
+      "loss": 0.0544,
+      "step": 300
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.6893060032292275e-07,
+      "loss": 0.0524,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.050160180777311325,
+      "eval_runtime": 21.3363,
+      "eval_samples_per_second": 9.655,
+      "eval_steps_per_second": 0.844,
+      "step": 317
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.6552462161205106e-07,
+      "loss": 0.0482,
+      "step": 320
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.6195526327012623e-07,
+      "loss": 0.041,
+      "step": 330
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.582252310689744e-07,
+      "loss": 0.0498,
+      "step": 340
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.5433735258012895e-07,
+      "loss": 0.0522,
+      "step": 350
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.502945750313747e-07,
+      "loss": 0.0469,
+      "step": 360
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.4609996307258503e-07,
+      "loss": 0.0454,
+      "step": 370
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.417566964525473e-07,
+      "loss": 0.0617,
+      "step": 380
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 4.37268067608537e-07,
+      "loss": 0.0438,
+      "step": 390
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.3263747917046697e-07,
+      "loss": 0.0507,
+      "step": 400
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 4.278684413815052e-07,
+      "loss": 0.0453,
+      "step": 410
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.22964569437116e-07,
+      "loss": 0.0401,
+      "step": 420
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.179295807445402e-07,
+      "loss": 0.0452,
+      "step": 430
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.127672921047948e-07,
+      "loss": 0.0448,
+      "step": 440
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.074816168193256e-07,
+      "loss": 0.0459,
+      "step": 450
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 4.0207656172350736e-07,
+      "loss": 0.04,
+      "step": 460
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.9655622414924007e-07,
+      "loss": 0.0531,
+      "step": 470
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.90924788818944e-07,
+      "loss": 0.048,
+      "step": 480
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.851865246733077e-07,
+      "loss": 0.0423,
+      "step": 490
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.793457816351937e-07,
+      "loss": 0.039,
+      "step": 500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.734069873121555e-07,
+      "loss": 0.045,
+      "step": 510
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.673746436400655e-07,
+      "loss": 0.0425,
+      "step": 520
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.6125332347039733e-07,
+      "loss": 0.0451,
+      "step": 530
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.5504766710375047e-07,
+      "loss": 0.0496,
+      "step": 540
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.487623787722448e-07,
+      "loss": 0.0435,
+      "step": 550
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.424022230734516e-07,
+      "loss": 0.0375,
+      "step": 560
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.3597202135856375e-07,
+      "loss": 0.0279,
+      "step": 570
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.2947664807754393e-07,
+      "loss": 0.0512,
+      "step": 580
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.2292102708402085e-07,
+      "loss": 0.0386,
+      "step": 590
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.1631012790273483e-07,
+      "loss": 0.0461,
+      "step": 600
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.096489619623621e-07,
+      "loss": 0.0417,
+      "step": 610
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.0294257879657347e-07,
+      "loss": 0.0376,
+      "step": 620
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.9619606221620736e-07,
+      "loss": 0.0466,
+      "step": 630
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.04205736145377159,
+      "eval_runtime": 21.3091,
+      "eval_samples_per_second": 9.667,
+      "eval_steps_per_second": 0.845,
+      "step": 634
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.894145264554593e-07,
+      "loss": 0.0378,
+      "step": 640
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.82603112295008e-07,
+      "loss": 0.0223,
+      "step": 650
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.757669831650181e-07,
+      "loss": 0.0323,
+      "step": 660
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.6891132123097383e-07,
+      "loss": 0.0326,
+      "step": 670
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 2.620413234653093e-07,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 2.551621977078152e-07,
+      "loss": 0.0217,
+      "step": 690
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 2.4827915871780665e-07,
+      "loss": 0.0236,
+      "step": 700
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.413974242210468e-07,
+      "loss": 0.0211,
+      "step": 710
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.3452221095441987e-07,
+      "loss": 0.0246,
+      "step": 720
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.2765873071135604e-07,
+      "loss": 0.0284,
+      "step": 730
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.2081218639100186e-07,
+      "loss": 0.0239,
+      "step": 740
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.1398776805413398e-07,
+      "loss": 0.0226,
+      "step": 750
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0719064898880494e-07,
+      "loss": 0.0279,
+      "step": 760
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.0042598178870386e-07,
+      "loss": 0.0276,
+      "step": 770
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.936988944472036e-07,
+      "loss": 0.0255,
+      "step": 780
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.8701448647005768e-07,
+      "loss": 0.0251,
+      "step": 790
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.8037782500969133e-07,
+      "loss": 0.0302,
+      "step": 800
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.7379394102401884e-07,
+      "loss": 0.0193,
+      "step": 810
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.672678254626979e-07,
+      "loss": 0.0212,
+      "step": 820
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.60804425483713e-07,
+      "loss": 0.0284,
+      "step": 830
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 1.5440864070315438e-07,
+      "loss": 0.025,
+      "step": 840
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.480853194810373e-07,
+      "loss": 0.0188,
+      "step": 850
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.4183925524597612e-07,
+      "loss": 0.0266,
+      "step": 860
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.356751828614987e-07,
+      "loss": 0.0243,
+      "step": 870
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.2959777503675736e-07,
+      "loss": 0.0216,
+      "step": 880
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.2361163878435594e-07,
+      "loss": 0.0219,
+      "step": 890
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.177213119279779e-07,
+      "loss": 0.0232,
+      "step": 900
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.1193125966246453e-07,
+      "loss": 0.019,
+      "step": 910
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.0624587116894887e-07,
+      "loss": 0.0182,
+      "step": 920
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.006694562876133e-07,
+      "loss": 0.0248,
+      "step": 930
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 9.52062422505906e-08,
+      "loss": 0.0207,
+      "step": 940
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.986037047748768e-08,
+      "loss": 0.0158,
+      "step": 950
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.050269413739442825,
+      "eval_runtime": 21.2804,
+      "eval_samples_per_second": 9.68,
+      "eval_steps_per_second": 0.846,
+      "step": 951
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 8.463589343595976e-08,
+      "loss": 0.0099,
+      "step": 960
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 7.953677156971433e-08,
+      "loss": 0.0086,
+      "step": 970
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.456687029627526e-08,
+      "loss": 0.0075,
+      "step": 980
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 6.972995707678153e-08,
+      "loss": 0.0064,
+      "step": 990
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 6.502969856004251e-08,
+      "loss": 0.0073,
+      "step": 1000
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 6.046965780301483e-08,
+      "loss": 0.0114,
+      "step": 1010
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 5.605329156980679e-08,
+      "loss": 0.0099,
+      "step": 1020
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 5.178394771125968e-08,
+      "loss": 0.0052,
+      "step": 1030
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 4.7664862627090744e-08,
+      "loss": 0.0138,
+      "step": 1040
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 4.369915881252259e-08,
+      "loss": 0.0046,
+      "step": 1050
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.988984249125821e-08,
+      "loss": 0.0021,
+      "step": 1060
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.623980133659685e-08,
+      "loss": 0.009,
+      "step": 1070
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 3.2751802282416915e-08,
+      "loss": 0.0032,
+      "step": 1080
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.9428489425686626e-08,
+      "loss": 0.0074,
+      "step": 1090
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.62723820220917e-08,
+      "loss": 0.0035,
+      "step": 1100
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.3285872576299604e-08,
+      "loss": 0.0069,
+      "step": 1110
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 2.0471225028308226e-08,
+      "loss": 0.0034,
+      "step": 1120
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.783057303725355e-08,
+      "loss": 0.0171,
+      "step": 1130
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.536591836397763e-08,
+      "loss": 0.0068,
+      "step": 1140
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.3079129353582658e-08,
+      "loss": 0.0121,
+      "step": 1150
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.0971939519121648e-08,
+      "loss": 0.0122,
+      "step": 1160
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 9.045946227499297e-09,
+      "loss": 0.0079,
+      "step": 1170
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 7.302609488579248e-09,
+      "loss": 0.0103,
+      "step": 1180
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 5.743250848415343e-09,
+      "loss": 0.0051,
+      "step": 1190
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 4.369052387446476e-09,
+      "loss": 0.0066,
+      "step": 1200
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 3.1810558244139695e-09,
+      "loss": 0.0051,
+      "step": 1210
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 2.1801617266808957e-09,
+      "loss": 0.0064,
+      "step": 1220
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.3671288275519666e-09,
+      "loss": 0.0085,
+      "step": 1230
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 7.425734511116998e-10,
+      "loss": 0.0056,
+      "step": 1240
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 3.06969045016342e-10,
+      "loss": 0.0072,
+      "step": 1250
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 6.064582159442944e-11,
+      "loss": 0.0047,
+      "step": 1260
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.06437445431947708,
+      "eval_runtime": 21.3091,
+      "eval_samples_per_second": 9.667,
+      "eval_steps_per_second": 0.845,
+      "step": 1268
+    },
+    {
+      "epoch": 4.0,
+      "step": 1268,
+      "total_flos": 72924899573760.0,
+      "train_loss": 0.16973004465752314,
+      "train_runtime": 6166.9886,
+      "train_samples_per_second": 2.463,
+      "train_steps_per_second": 0.206
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 72924899573760.0,
+  "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 sha256:1e73681fa3b9fd1ab38d1aab60e3926416bb52ea5a00a35581665a5f508849c6
+size 5371