Upload 12 files

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: train_2024-03-25-22-22-32
+  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. -->
+
+# train_2024-03-25-22-22-32
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the super-mario-bros-ascii 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: 5e-05
+- 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
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "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": 0.1,
+  "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"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3b0bdd8de03c4ccad5bf6ae20bb54edae04de8ee917cfcd1e5994d095e07dc
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.39,
+    "train_loss": 1.2066423391302428,
+    "train_runtime": 1350.3046,
+    "train_samples_per_second": 5.439,
+    "train_steps_per_second": 0.34
+}

runs/Mar25_22-24-10_pc/events.out.tfevents.1711402188.pc.31545.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686f404d1e840f8ce4351d1aacd35830aa5c047857fd6d9265575d189eccb704
+size 6780

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": 0.39,
+    "train_loss": 1.2066423391302428,
+    "train_runtime": 1350.3046,
+    "train_samples_per_second": 5.439,
+    "train_steps_per_second": 0.34
+}

trainer_log.jsonl

@@ -0,0 +1,13 @@
+{"current_steps": 5, "total_steps": 459, "loss": 4.5464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9985361990992455e-05, "epoch": 0.03, "percentage": 1.09, "elapsed_time": "0:01:44", "remaining_time": "2:38:37"}
+{"current_steps": 10, "total_steps": 459, "loss": 3.5691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9941465105674435e-05, "epoch": 0.07, "percentage": 2.18, "elapsed_time": "0:03:35", "remaining_time": "2:41:25"}
+{"current_steps": 15, "total_steps": 459, "loss": 2.6628, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.986836074908616e-05, "epoch": 0.1, "percentage": 3.27, "elapsed_time": "0:05:28", "remaining_time": "2:41:57"}
+{"current_steps": 20, "total_steps": 459, "loss": 1.6234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.976613452940604e-05, "epoch": 0.13, "percentage": 4.36, "elapsed_time": "0:07:25", "remaining_time": "2:42:53"}
+{"current_steps": 25, "total_steps": 459, "loss": 0.4965, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9634906157700036e-05, "epoch": 0.16, "percentage": 5.45, "elapsed_time": "0:09:18", "remaining_time": "2:41:33"}
+{"current_steps": 30, "total_steps": 459, "loss": 0.2314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9474829307735115e-05, "epoch": 0.2, "percentage": 6.54, "elapsed_time": "0:11:08", "remaining_time": "2:39:18"}
+{"current_steps": 35, "total_steps": 459, "loss": 0.2109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9286091436021015e-05, "epoch": 0.23, "percentage": 7.63, "elapsed_time": "0:12:58", "remaining_time": "2:37:06"}
+{"current_steps": 40, "total_steps": 459, "loss": 0.243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.906891356229103e-05, "epoch": 0.26, "percentage": 8.71, "elapsed_time": "0:14:47", "remaining_time": "2:34:54"}
+{"current_steps": 45, "total_steps": 459, "loss": 0.1753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.882355001067892e-05, "epoch": 0.29, "percentage": 9.8, "elapsed_time": "0:16:41", "remaining_time": "2:33:33"}
+{"current_steps": 50, "total_steps": 459, "loss": 0.2237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.855028811189496e-05, "epoch": 0.33, "percentage": 10.89, "elapsed_time": "0:18:31", "remaining_time": "2:31:34"}
+{"current_steps": 55, "total_steps": 459, "loss": 0.1995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8249447866750025e-05, "epoch": 0.36, "percentage": 11.98, "elapsed_time": "0:20:24", "remaining_time": "2:29:52"}
+{"current_steps": 60, "total_steps": 459, "loss": 0.259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.792138157142158e-05, "epoch": 0.39, "percentage": 13.07, "elapsed_time": "0:22:13", "remaining_time": "2:27:48"}
+{"current_steps": 60, "total_steps": 459, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.39, "percentage": 13.07, "elapsed_time": "0:22:13", "remaining_time": "2:27:48"}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.39215686274509803,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9985361990992455e-05,
+      "loss": 4.5464,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9941465105674435e-05,
+      "loss": 3.5691,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.986836074908616e-05,
+      "loss": 2.6628,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.976613452940604e-05,
+      "loss": 1.6234,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9634906157700036e-05,
+      "loss": 0.4965,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.9474829307735115e-05,
+      "loss": 0.2314,
+      "step": 30
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9286091436021015e-05,
+      "loss": 0.2109,
+      "step": 35
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.906891356229103e-05,
+      "loss": 0.243,
+      "step": 40
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.882355001067892e-05,
+      "loss": 0.1753,
+      "step": 45
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.855028811189496e-05,
+      "loss": 0.2237,
+      "step": 50
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.8249447866750025e-05,
+      "loss": 0.1995,
+      "step": 55
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.792138157142158e-05,
+      "loss": 0.259,
+      "step": 60
+    },
+    {
+      "epoch": 0.39,
+      "step": 60,
+      "total_flos": 5.967075326400922e+16,
+      "train_loss": 1.2066423391302428,
+      "train_runtime": 1350.3046,
+      "train_samples_per_second": 5.439,
+      "train_steps_per_second": 0.34
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 459,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 5.967075326400922e+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 sha256:426c39677bb8f4dbe5ebeb13fe06eb055be97246de6ed225b53ea34138df3f1d
+size 4920