mistral models

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+datasets:
+- customized
+model-index:
+- name: ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0
+  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. -->
+
+# ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the customized dataset.
+
+## 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: 1e-06
+- train_batch_size: 50
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 400
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.1302242176873343,
+    "train_runtime": 3134.3058,
+    "train_samples": 41637,
+    "train_samples_per_second": 13.284,
+    "train_steps_per_second": 0.034
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a0b1d32a057465c18df318f95d768f4dd11892349986d95d074b165476e284
+size 4943162336

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e037fcb7e40792941f98da28e6cbfa49e30d5ae6fdd0094ebff688eb0fc094
+size 4999819336

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46535ef34af9355e468d5295c5e8b070eb189374b3907b03dc263bf2bfc0b66b
+size 4540516344

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/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"
+  }
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/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
+  }
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.1302242176873343,
+    "train_runtime": 3134.3058,
+    "train_samples": 41637,
+    "train_samples_per_second": 13.284,
+    "train_steps_per_second": 0.034
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/trainer_state.json

@@ -0,0 +1,660 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50.0,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 1.428,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.995349917899734e-07,
+      "loss": 1.4481,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-06,
+      "loss": 1.4566,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.997762161417517e-07,
+      "loss": 1.4433,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.991050648838675e-07,
+      "loss": 1.4204,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.979871469976195e-07,
+      "loss": 1.3546,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.964234631709185e-07,
+      "loss": 1.3626,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.944154131125642e-07,
+      "loss": 1.3421,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.919647942993147e-07,
+      "loss": 1.323,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.890738003669027e-07,
+      "loss": 1.2718,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.857450191464337e-07,
+      "loss": 1.301,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.819814303479267e-07,
+      "loss": 1.2781,
+      "step": 12
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.777864028930702e-07,
+      "loss": 1.2419,
+      "step": 13
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.73163691899582e-07,
+      "loss": 1.2574,
+      "step": 14
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.681174353198686e-07,
+      "loss": 1.2205,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.626521502369983e-07,
+      "loss": 1.2113,
+      "step": 16
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.567727288213004e-07,
+      "loss": 1.2278,
+      "step": 17
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.504844339512094e-07,
+      "loss": 1.1911,
+      "step": 18
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.43792894502277e-07,
+      "loss": 1.1681,
+      "step": 19
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.367041003085648e-07,
+      "loss": 1.1458,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.29224396800933e-07,
+      "loss": 1.1442,
+      "step": 21
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.213604793270196e-07,
+      "loss": 1.1617,
+      "step": 22
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.131193871579974e-07,
+      "loss": 1.1357,
+      "step": 23
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.045084971874737e-07,
+      "loss": 1.1367,
+      "step": 24
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.955355173281707e-07,
+      "loss": 1.1346,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.862084796122997e-07,
+      "loss": 1.134,
+      "step": 26
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.765357330018055e-07,
+      "loss": 1.1241,
+      "step": 27
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.66525935914913e-07,
+      "loss": 1.1166,
+      "step": 28
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.561880484756724e-07,
+      "loss": 1.1157,
+      "step": 29
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.455313244934324e-07,
+      "loss": 1.1261,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.34565303179429e-07,
+      "loss": 1.1345,
+      "step": 31
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.232998006078997e-07,
+      "loss": 1.1066,
+      "step": 32
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.117449009293668e-07,
+      "loss": 1.1193,
+      "step": 33
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.999109473439569e-07,
+      "loss": 1.1046,
+      "step": 34
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.878085328428368e-07,
+      "loss": 1.1182,
+      "step": 35
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.754484907260512e-07,
+      "loss": 1.0941,
+      "step": 36
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.628418849052523e-07,
+      "loss": 1.1064,
+      "step": 37
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.5e-07,
+      "loss": 1.1275,
+      "step": 38
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.369343312364993e-07,
+      "loss": 1.1149,
+      "step": 39
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.236565741578162e-07,
+      "loss": 1.0986,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.101786141547828e-07,
+      "loss": 1.0968,
+      "step": 41
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.965125158269618e-07,
+      "loss": 1.094,
+      "step": 42
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.826705121831975e-07,
+      "loss": 1.089,
+      "step": 43
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.68664993691415e-07,
+      "loss": 1.088,
+      "step": 44
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.545084971874736e-07,
+      "loss": 1.0822,
+      "step": 45
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.402136946530014e-07,
+      "loss": 1.0965,
+      "step": 46
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.257933818722542e-07,
+      "loss": 1.094,
+      "step": 47
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 6.112604669781572e-07,
+      "loss": 1.0889,
+      "step": 48
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.966279588977767e-07,
+      "loss": 1.0705,
+      "step": 49
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.819089557075688e-07,
+      "loss": 1.0862,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.671166329088277e-07,
+      "loss": 1.0888,
+      "step": 51
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.522642316338269e-07,
+      "loss": 1.0931,
+      "step": 52
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.37365046793212e-07,
+      "loss": 1.0945,
+      "step": 53
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.224324151752575e-07,
+      "loss": 1.083,
+      "step": 54
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.074797035076318e-07,
+      "loss": 1.0775,
+      "step": 55
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.925202964923683e-07,
+      "loss": 1.0924,
+      "step": 56
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.775675848247426e-07,
+      "loss": 1.0922,
+      "step": 57
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.626349532067879e-07,
+      "loss": 1.0829,
+      "step": 58
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.477357683661733e-07,
+      "loss": 1.0741,
+      "step": 59
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.328833670911723e-07,
+      "loss": 1.0664,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.180910442924311e-07,
+      "loss": 1.0742,
+      "step": 61
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.0337204110222347e-07,
+      "loss": 1.0686,
+      "step": 62
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.8873953302184294e-07,
+      "loss": 1.0737,
+      "step": 63
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.742066181277457e-07,
+      "loss": 1.0786,
+      "step": 64
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.5978630534699865e-07,
+      "loss": 1.1105,
+      "step": 65
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.454915028125263e-07,
+      "loss": 1.0778,
+      "step": 66
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.31335006308585e-07,
+      "loss": 1.094,
+      "step": 67
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.173294878168026e-07,
+      "loss": 1.0694,
+      "step": 68
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.034874841730382e-07,
+      "loss": 1.0891,
+      "step": 69
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.898213858452173e-07,
+      "loss": 1.0585,
+      "step": 70
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.763434258421836e-07,
+      "loss": 1.0887,
+      "step": 71
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.6306566876350067e-07,
+      "loss": 1.0754,
+      "step": 72
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.500000000000001e-07,
+      "loss": 1.0693,
+      "step": 73
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.371581150947476e-07,
+      "loss": 1.0614,
+      "step": 74
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.2455150927394878e-07,
+      "loss": 1.0834,
+      "step": 75
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.121914671571633e-07,
+      "loss": 1.0722,
+      "step": 76
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.0008905265604315e-07,
+      "loss": 1.0733,
+      "step": 77
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.8825509907063326e-07,
+      "loss": 1.073,
+      "step": 78
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7670019939210023e-07,
+      "loss": 1.0713,
+      "step": 79
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6543469682057088e-07,
+      "loss": 1.0737,
+      "step": 80
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.5446867550656767e-07,
+      "loss": 1.0863,
+      "step": 81
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.438119515243275e-07,
+      "loss": 1.0691,
+      "step": 82
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3347406408508683e-07,
+      "loss": 1.0764,
+      "step": 83
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2346426699819456e-07,
+      "loss": 1.0847,
+      "step": 84
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1379152038770029e-07,
+      "loss": 1.0778,
+      "step": 85
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0446448267182933e-07,
+      "loss": 1.066,
+      "step": 86
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.549150281252632e-08,
+      "loss": 1.0622,
+      "step": 87
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.688061284200265e-08,
+      "loss": 1.0707,
+      "step": 88
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.863952067298041e-08,
+      "loss": 1.0754,
+      "step": 89
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.077560319906694e-08,
+      "loss": 1.0799,
+      "step": 90
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.329589969143517e-08,
+      "loss": 1.0814,
+      "step": 91
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.620710549772295e-08,
+      "loss": 1.0817,
+      "step": 92
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.951556604879048e-08,
+      "loss": 1.0724,
+      "step": 93
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.322727117869962e-08,
+      "loss": 1.0736,
+      "step": 94
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.7347849763001706e-08,
+      "loss": 1.0752,
+      "step": 95
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.1882564680131506e-08,
+      "loss": 1.0607,
+      "step": 96
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.6836308100417872e-08,
+      "loss": 1.0662,
+      "step": 97
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2213597106929605e-08,
+      "loss": 1.0919,
+      "step": 98
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8018569652073378e-08,
+      "loss": 1.0681,
+      "step": 99
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.42549808535663e-08,
+      "loss": 1.069,
+      "step": 100
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.092619963309721e-08,
+      "loss": 1.0713,
+      "step": 101
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.035205700685165e-09,
+      "loss": 1.0607,
+      "step": 102
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.5845868874357385e-09,
+      "loss": 1.0648,
+      "step": 103
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.5765368290813223e-09,
+      "loss": 1.095,
+      "step": 104
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.0128530023804656e-09,
+      "loss": 1.0783,
+      "step": 105
+    },
+    {
+      "epoch": 1.0,
+      "step": 105,
+      "total_flos": 9.174457870870118e+17,
+      "train_loss": 1.1302242176873343,
+      "train_runtime": 3134.3058,
+      "train_samples_per_second": 13.284,
+      "train_steps_per_second": 0.034
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 9.174457870870118e+17,
+  "train_batch_size": 50,
+  "trial_name": null,
+  "trial_params": null
+}

ft_mistral-7B_adamw_gpt4_v2_1e-6_base_0/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999181fd45123880a24a5bedaae6ad03b5a1d8a25d4fc4a561a8aac7b126b7be
+size 6456