Model save

Browse files

Files changed (8) hide show

README.md +60 -0
adapter_config.json +26 -0
adapter_model.safetensors +3 -0
special_tokens_map.json +24 -0
tokenizer.model +3 -0
tokenizer_config.json +44 -0
trainer_state.json +492 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,60 @@

+---
+license: apache-2.0
+base_model: microsoft/llava-med-v1.5-mistral-7b
+tags:
+- generated_from_trainer
+model-index:
+- name: llava-med-spect-persona-ffr-report-20250410
+  results: []
+library_name: peft
+---
+<!-- 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. -->
+# llava-med-spect-persona-ffr-report-20250410
+This model is a fine-tuned version of [microsoft/llava-med-v1.5-mistral-7b](https://huggingface.co/microsoft/llava-med-v1.5-mistral-7b) on an unknown 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.02
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+### Training results
+### Framework versions
+- PEFT 0.4.0
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Tokenizers 0.15.1

adapter_config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/llava-med-v1.5-mistral-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c72b657ca72ada314cf35b395edbf0d889717b22afc6d177d4dcf22d80659c3
+size 167832240

special_tokens_map.json ADDED Viewed

	@@ -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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json ADDED Viewed

	@@ -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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,492 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9903536977491961,
+  "eval_steps": 500,
+  "global_step": 77,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-05,
+      "loss": 1.6351,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 1.6528,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001,
+      "loss": 1.6835,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.995614150494293e-05,
+      "loss": 1.6183,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.982464296247522e-05,
+      "loss": 1.6164,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.96057350657239e-05,
+      "loss": 1.4991,
+      "step": 6
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.929980185352526e-05,
+      "loss": 1.4829,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.4138,
+      "step": 8
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 1.4584,
+      "step": 9
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.786597487660337e-05,
+      "loss": 1.3482,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.721881851187406e-05,
+      "loss": 1.3124,
+      "step": 11
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.648882429441257e-05,
+      "loss": 1.236,
+      "step": 12
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.2427,
+      "step": 13
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.478558801197065e-05,
+      "loss": 1.1855,
+      "step": 14
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.381533400219318e-05,
+      "loss": 1.1507,
+      "step": 15
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.276821300802534e-05,
+      "loss": 1.1127,
+      "step": 16
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.164606203550497e-05,
+      "loss": 1.0321,
+      "step": 17
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0016,
+      "step": 18
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.9184672866292e-05,
+      "loss": 0.9561,
+      "step": 19
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.784975278258783e-05,
+      "loss": 0.9562,
+      "step": 20
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 0.8827,
+      "step": 21
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.498316702566828e-05,
+      "loss": 0.8499,
+      "step": 22
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.8233,
+      "step": 23
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 0.8412,
+      "step": 24
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.022995574311876e-05,
+      "loss": 0.7966,
+      "step": 25
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.85356783842216e-05,
+      "loss": 0.7664,
+      "step": 26
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.679133974894983e-05,
+      "loss": 0.7188,
+      "step": 27
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6549,
+      "step": 28
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.316480175599309e-05,
+      "loss": 0.6638,
+      "step": 29
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.128896457825364e-05,
+      "loss": 0.6472,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.937577932260515e-05,
+      "loss": 0.6237,
+      "step": 31
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.742860236609077e-05,
+      "loss": 0.5706,
+      "step": 32
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5788,
+      "step": 33
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.344599103076329e-05,
+      "loss": 0.5543,
+      "step": 34
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.141754350553279e-05,
+      "loss": 0.5639,
+      "step": 35
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.9369065729286245e-05,
+      "loss": 0.5404,
+      "step": 36
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.730415142812059e-05,
+      "loss": 0.5429,
+      "step": 37
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.506,
+      "step": 38
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.4793,
+      "step": 39
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.104712099416785e-05,
+      "loss": 0.4886,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.895287900583216e-05,
+      "loss": 0.4514,
+      "step": 41
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 0.4984,
+      "step": 42
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.4464,
+      "step": 43
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.269584857187943e-05,
+      "loss": 0.4846,
+      "step": 44
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.063093427071376e-05,
+      "loss": 0.4491,
+      "step": 45
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.858245649446721e-05,
+      "loss": 0.4662,
+      "step": 46
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.655400896923672e-05,
+      "loss": 0.4442,
+      "step": 47
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.454,
+      "step": 48
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.257139763390925e-05,
+      "loss": 0.3953,
+      "step": 49
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.062422067739485e-05,
+      "loss": 0.4575,
+      "step": 50
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.4269,
+      "step": 51
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.6835198244006927e-05,
+      "loss": 0.411,
+      "step": 52
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4304,
+      "step": 53
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.3208660251050158e-05,
+      "loss": 0.4284,
+      "step": 54
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.1464321615778422e-05,
+      "loss": 0.4016,
+      "step": 55
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.977004425688126e-05,
+      "loss": 0.428,
+      "step": 56
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8128800512565513e-05,
+      "loss": 0.3949,
+      "step": 57
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4035,
+      "step": 58
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.5016832974331724e-05,
+      "loss": 0.3929,
+      "step": 59
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 0.37,
+      "step": 60
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2150247217412186e-05,
+      "loss": 0.3788,
+      "step": 61
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.0815327133708015e-05,
+      "loss": 0.4043,
+      "step": 62
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4129,
+      "step": 63
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.353937964495029e-06,
+      "loss": 0.3976,
+      "step": 64
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7.2317869919746705e-06,
+      "loss": 0.3999,
+      "step": 65
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.184665997806832e-06,
+      "loss": 0.3564,
+      "step": 66
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.214411988029355e-06,
+      "loss": 0.3593,
+      "step": 67
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3916,
+      "step": 68
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.3861,
+      "step": 69
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.7811814881259503e-06,
+      "loss": 0.3967,
+      "step": 70
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.134025123396638e-06,
+      "loss": 0.3624,
+      "step": 71
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5708419435684462e-06,
+      "loss": 0.358,
+      "step": 72
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3965,
+      "step": 73
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.001981464747565e-07,
+      "loss": 0.3942,
+      "step": 74
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.9426493427611177e-07,
+      "loss": 0.3857,
+      "step": 75
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.753570375247815e-07,
+      "loss": 0.4294,
+      "step": 76
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.385849505708084e-08,
+      "loss": 0.3373,
+      "step": 77
+    },
+    {
+      "epoch": 0.99,
+      "step": 77,
+      "total_flos": 543429523144704.0,
+      "train_loss": 0.7125843113118951,
+      "train_runtime": 6470.7689,
+      "train_samples_per_second": 0.769,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 77,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 543429523144704.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:98dc69a327eeb5cae0bb3ec3a5aa9597b40dc23a5424c000af31fcf78d31aa55
+size 7288