Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: mistral-7b-mmlu-v1
+  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-7b-mmlu-v1
+
+This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the medical_meadow_mmmlu dataset.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f14ef0d4184b9571f6f07846611e3e385767af3cfec335a3c84ede56f818ae
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6184843576560586,
+    "train_runtime": 481.5585,
+    "train_samples_per_second": 7.864,
+    "train_steps_per_second": 0.49
+}

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 +1,44 @@
+{
+  "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>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6184843576560586,
+    "train_runtime": 481.5585,
+    "train_samples_per_second": 7.864,
+    "train_steps_per_second": 0.49
+}

trainer_log.jsonl

@@ -0,0 +1,24 @@
+{"current_steps": 10, "total_steps": 236, "loss": 3.8893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.04, "percentage": 4.24, "elapsed_time": "0:00:19", "remaining_time": "0:07:23"}
+{"current_steps": 20, "total_steps": 236, "loss": 0.6272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045000000000000004, "epoch": 0.08, "percentage": 8.47, "elapsed_time": "0:00:39", "remaining_time": "0:07:06"}
+{"current_steps": 30, "total_steps": 236, "loss": 0.5738, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004983095894354857, "epoch": 0.13, "percentage": 12.71, "elapsed_time": "0:00:59", "remaining_time": "0:06:46"}
+{"current_steps": 40, "total_steps": 236, "loss": 0.5952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004914814565722671, "epoch": 0.17, "percentage": 16.95, "elapsed_time": "0:01:20", "remaining_time": "0:06:36"}
+{"current_steps": 50, "total_steps": 236, "loss": 0.5288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004795540267200685, "epoch": 0.21, "percentage": 21.19, "elapsed_time": "0:01:40", "remaining_time": "0:06:15"}
+{"current_steps": 60, "total_steps": 236, "loss": 0.5324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004627791681092499, "epoch": 0.25, "percentage": 25.42, "elapsed_time": "0:02:03", "remaining_time": "0:06:02"}
+{"current_steps": 70, "total_steps": 236, "loss": 0.4889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004415111107797445, "epoch": 0.3, "percentage": 29.66, "elapsed_time": "0:02:23", "remaining_time": "0:05:39"}
+{"current_steps": 80, "total_steps": 236, "loss": 0.563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004161989664034844, "epoch": 0.34, "percentage": 33.9, "elapsed_time": "0:02:46", "remaining_time": "0:05:24"}
+{"current_steps": 90, "total_steps": 236, "loss": 0.5221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003873772445177015, "epoch": 0.38, "percentage": 38.14, "elapsed_time": "0:03:07", "remaining_time": "0:05:04"}
+{"current_steps": 100, "total_steps": 236, "loss": 0.5077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00035565456543517487, "epoch": 0.42, "percentage": 42.37, "elapsed_time": "0:03:28", "remaining_time": "0:04:43"}
+{"current_steps": 110, "total_steps": 236, "loss": 0.4716, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003217008081777726, "epoch": 0.46, "percentage": 46.61, "elapsed_time": "0:03:48", "remaining_time": "0:04:21"}
+{"current_steps": 120, "total_steps": 236, "loss": 0.4604, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002862329648268117, "epoch": 0.51, "percentage": 50.85, "elapsed_time": "0:04:05", "remaining_time": "0:03:57"}
+{"current_steps": 130, "total_steps": 236, "loss": 0.4369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.55, "percentage": 55.08, "elapsed_time": "0:04:25", "remaining_time": "0:03:36"}
+{"current_steps": 140, "total_steps": 236, "loss": 0.4037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021376703517318835, "epoch": 0.59, "percentage": 59.32, "elapsed_time": "0:04:45", "remaining_time": "0:03:15"}
+{"current_steps": 150, "total_steps": 236, "loss": 0.4352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017829919182222752, "epoch": 0.63, "percentage": 63.56, "elapsed_time": "0:05:07", "remaining_time": "0:02:56"}
+{"current_steps": 160, "total_steps": 236, "loss": 0.4786, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001443454345648252, "epoch": 0.68, "percentage": 67.8, "elapsed_time": "0:05:28", "remaining_time": "0:02:35"}
+{"current_steps": 170, "total_steps": 236, "loss": 0.3898, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001126227554822985, "epoch": 0.72, "percentage": 72.03, "elapsed_time": "0:05:47", "remaining_time": "0:02:15"}
+{"current_steps": 180, "total_steps": 236, "loss": 0.4148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.380103359651554e-05, "epoch": 0.76, "percentage": 76.27, "elapsed_time": "0:06:09", "remaining_time": "0:01:54"}
+{"current_steps": 190, "total_steps": 236, "loss": 0.4038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.848888922025553e-05, "epoch": 0.8, "percentage": 80.51, "elapsed_time": "0:06:28", "remaining_time": "0:01:34"}
+{"current_steps": 200, "total_steps": 236, "loss": 0.3832, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7220831890750065e-05, "epoch": 0.84, "percentage": 84.75, "elapsed_time": "0:06:47", "remaining_time": "0:01:13"}
+{"current_steps": 210, "total_steps": 236, "loss": 0.4246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0445973279931528e-05, "epoch": 0.89, "percentage": 88.98, "elapsed_time": "0:07:07", "remaining_time": "0:00:52"}
+{"current_steps": 220, "total_steps": 236, "loss": 0.3939, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.51854342773295e-06, "epoch": 0.93, "percentage": 93.22, "elapsed_time": "0:07:28", "remaining_time": "0:00:32"}
+{"current_steps": 230, "total_steps": 236, "loss": 0.4482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6904105645142442e-06, "epoch": 0.97, "percentage": 97.46, "elapsed_time": "0:07:49", "remaining_time": "0:00:12"}
+{"current_steps": 236, "total_steps": 236, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:08:01", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.996832101372756,
+  "eval_steps": 500,
+  "global_step": 236,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025,
+      "loss": 3.8893,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 0.6272,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004983095894354857,
+      "loss": 0.5738,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0004914814565722671,
+      "loss": 0.5952,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0004795540267200685,
+      "loss": 0.5288,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0004627791681092499,
+      "loss": 0.5324,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0004415111107797445,
+      "loss": 0.4889,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004161989664034844,
+      "loss": 0.563,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003873772445177015,
+      "loss": 0.5221,
+      "step": 90
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00035565456543517487,
+      "loss": 0.5077,
+      "step": 100
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003217008081777726,
+      "loss": 0.4716,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002862329648268117,
+      "loss": 0.4604,
+      "step": 120
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00025,
+      "loss": 0.4369,
+      "step": 130
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00021376703517318835,
+      "loss": 0.4037,
+      "step": 140
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017829919182222752,
+      "loss": 0.4352,
+      "step": 150
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001443454345648252,
+      "loss": 0.4786,
+      "step": 160
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001126227554822985,
+      "loss": 0.3898,
+      "step": 170
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.380103359651554e-05,
+      "loss": 0.4148,
+      "step": 180
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.848888922025553e-05,
+      "loss": 0.4038,
+      "step": 190
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.7220831890750065e-05,
+      "loss": 0.3832,
+      "step": 200
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.0445973279931528e-05,
+      "loss": 0.4246,
+      "step": 210
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.51854342773295e-06,
+      "loss": 0.3939,
+      "step": 220
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6904105645142442e-06,
+      "loss": 0.4482,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "step": 236,
+      "total_flos": 2.7203285308932096e+16,
+      "train_loss": 0.6184843576560586,
+      "train_runtime": 481.5585,
+      "train_samples_per_second": 7.864,
+      "train_steps_per_second": 0.49
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 2.7203285308932096e+16,
+  "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 sha256:683d22d0058ae610e287452c3c3c541abe0555687c78569ebdde860cfdc7686a
+size 4920