Init commit

README.md

@@ -1,3 +1,60 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: mistral-v0.4-7B-q4-pe
+  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-v0.4-7B-q4-pe
+
+This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit) on the pe 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: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f40be430176335286518189e8effb167ae4f2a0ee1e70da5460861a48c0ab9
+size 83945296

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.894409937888199,
+    "total_flos": 7.730765272920883e+16,
+    "train_loss": 0.01017542961082654,
+    "train_runtime": 2023.7651,
+    "train_samples_per_second": 0.796,
+    "train_steps_per_second": 0.099
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.894409937888199,
+    "total_flos": 7.730765272920883e+16,
+    "train_loss": 0.01017542961082654,
+    "train_runtime": 2023.7651,
+    "train_samples_per_second": 0.796,
+    "train_steps_per_second": 0.099
+}

trainer_log.jsonl

@@ -0,0 +1,21 @@
+{"current_steps": 10, "total_steps": 200, "loss": 0.0874, "lr": 2.5e-05, "epoch": 0.2484472049689441, "percentage": 5.0, "elapsed_time": "0:01:37", "remaining_time": "0:30:46"}
+{"current_steps": 20, "total_steps": 200, "loss": 0.024, "lr": 5e-05, "epoch": 0.4968944099378882, "percentage": 10.0, "elapsed_time": "0:03:18", "remaining_time": "0:29:50"}
+{"current_steps": 30, "total_steps": 200, "loss": 0.0231, "lr": 4.962019382530521e-05, "epoch": 0.7453416149068323, "percentage": 15.0, "elapsed_time": "0:05:01", "remaining_time": "0:28:26"}
+{"current_steps": 40, "total_steps": 200, "loss": 0.0181, "lr": 4.849231551964771e-05, "epoch": 0.9937888198757764, "percentage": 20.0, "elapsed_time": "0:06:44", "remaining_time": "0:26:57"}
+{"current_steps": 50, "total_steps": 200, "loss": 0.0097, "lr": 4.665063509461097e-05, "epoch": 1.2236024844720497, "percentage": 25.0, "elapsed_time": "0:08:20", "remaining_time": "0:25:00"}
+{"current_steps": 60, "total_steps": 200, "loss": 0.0099, "lr": 4.415111107797445e-05, "epoch": 1.4720496894409938, "percentage": 30.0, "elapsed_time": "0:10:02", "remaining_time": "0:23:24"}
+{"current_steps": 70, "total_steps": 200, "loss": 0.0074, "lr": 4.1069690242163484e-05, "epoch": 1.720496894409938, "percentage": 35.0, "elapsed_time": "0:11:48", "remaining_time": "0:21:56"}
+{"current_steps": 80, "total_steps": 200, "loss": 0.0091, "lr": 3.7500000000000003e-05, "epoch": 1.968944099378882, "percentage": 40.0, "elapsed_time": "0:13:41", "remaining_time": "0:20:32"}
+{"current_steps": 90, "total_steps": 200, "loss": 0.0032, "lr": 3.355050358314172e-05, "epoch": 2.198757763975155, "percentage": 45.0, "elapsed_time": "0:15:20", "remaining_time": "0:18:44"}
+{"current_steps": 100, "total_steps": 200, "loss": 0.0037, "lr": 2.9341204441673266e-05, "epoch": 2.4472049689440993, "percentage": 50.0, "elapsed_time": "0:16:57", "remaining_time": "0:16:57"}
+{"current_steps": 110, "total_steps": 200, "loss": 0.0025, "lr": 2.5e-05, "epoch": 2.6956521739130435, "percentage": 55.0, "elapsed_time": "0:18:38", "remaining_time": "0:15:15"}
+{"current_steps": 120, "total_steps": 200, "loss": 0.0022, "lr": 2.0658795558326743e-05, "epoch": 2.9440993788819876, "percentage": 60.0, "elapsed_time": "0:20:18", "remaining_time": "0:13:32"}
+{"current_steps": 130, "total_steps": 200, "loss": 0.001, "lr": 1.6449496416858284e-05, "epoch": 3.1739130434782608, "percentage": 65.0, "elapsed_time": "0:21:56", "remaining_time": "0:11:48"}
+{"current_steps": 140, "total_steps": 200, "loss": 0.0008, "lr": 1.2500000000000006e-05, "epoch": 3.422360248447205, "percentage": 70.0, "elapsed_time": "0:23:40", "remaining_time": "0:10:08"}
+{"current_steps": 150, "total_steps": 200, "loss": 0.0005, "lr": 8.930309757836517e-06, "epoch": 3.670807453416149, "percentage": 75.0, "elapsed_time": "0:25:19", "remaining_time": "0:08:26"}
+{"current_steps": 160, "total_steps": 200, "loss": 0.0004, "lr": 5.848888922025553e-06, "epoch": 3.919254658385093, "percentage": 80.0, "elapsed_time": "0:27:00", "remaining_time": "0:06:45"}
+{"current_steps": 170, "total_steps": 200, "loss": 0.0002, "lr": 3.3493649053890326e-06, "epoch": 4.149068322981367, "percentage": 85.0, "elapsed_time": "0:28:34", "remaining_time": "0:05:02"}
+{"current_steps": 180, "total_steps": 200, "loss": 0.0001, "lr": 1.5076844803522922e-06, "epoch": 4.39751552795031, "percentage": 90.0, "elapsed_time": "0:30:15", "remaining_time": "0:03:21"}
+{"current_steps": 190, "total_steps": 200, "loss": 0.0001, "lr": 3.7980617469479953e-07, "epoch": 4.645962732919255, "percentage": 95.0, "elapsed_time": "0:32:00", "remaining_time": "0:01:41"}
+{"current_steps": 200, "total_steps": 200, "loss": 0.0001, "lr": 0.0, "epoch": 4.894409937888199, "percentage": 100.0, "elapsed_time": "0:33:40", "remaining_time": "0:00:00"}
+{"current_steps": 200, "total_steps": 200, "epoch": 4.894409937888199, "percentage": 100.0, "elapsed_time": "0:33:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.894409937888199,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2484472049689441,
+      "grad_norm": 0.27082329988479614,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0874,
+      "step": 10
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 0.1463955044746399,
+      "learning_rate": 5e-05,
+      "loss": 0.024,
+      "step": 20
+    },
+    {
+      "epoch": 0.7453416149068323,
+      "grad_norm": 0.3136928379535675,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.0231,
+      "step": 30
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 0.13906799256801605,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.0181,
+      "step": 40
+    },
+    {
+      "epoch": 1.2236024844720497,
+      "grad_norm": 0.12204258888959885,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.0097,
+      "step": 50
+    },
+    {
+      "epoch": 1.4720496894409938,
+      "grad_norm": 0.13101451098918915,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.0099,
+      "step": 60
+    },
+    {
+      "epoch": 1.720496894409938,
+      "grad_norm": 0.07784764468669891,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.0074,
+      "step": 70
+    },
+    {
+      "epoch": 1.968944099378882,
+      "grad_norm": 0.12637487053871155,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0091,
+      "step": 80
+    },
+    {
+      "epoch": 2.198757763975155,
+      "grad_norm": 0.04680779576301575,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0032,
+      "step": 90
+    },
+    {
+      "epoch": 2.4472049689440993,
+      "grad_norm": 0.17413705587387085,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0037,
+      "step": 100
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 0.058823954313993454,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0025,
+      "step": 110
+    },
+    {
+      "epoch": 2.9440993788819876,
+      "grad_norm": 0.08512682467699051,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0022,
+      "step": 120
+    },
+    {
+      "epoch": 3.1739130434782608,
+      "grad_norm": 0.050768449902534485,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.001,
+      "step": 130
+    },
+    {
+      "epoch": 3.422360248447205,
+      "grad_norm": 0.07241635769605637,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0008,
+      "step": 140
+    },
+    {
+      "epoch": 3.670807453416149,
+      "grad_norm": 0.02915179915726185,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 3.919254658385093,
+      "grad_norm": 0.01426270604133606,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 4.149068322981367,
+      "grad_norm": 0.023959646001458168,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0002,
+      "step": 170
+    },
+    {
+      "epoch": 4.39751552795031,
+      "grad_norm": 0.00856300164014101,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0001,
+      "step": 180
+    },
+    {
+      "epoch": 4.645962732919255,
+      "grad_norm": 0.010647363029420376,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.0001,
+      "step": 190
+    },
+    {
+      "epoch": 4.894409937888199,
+      "grad_norm": 0.0016118749044835567,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 200
+    },
+    {
+      "epoch": 4.894409937888199,
+      "step": 200,
+      "total_flos": 7.730765272920883e+16,
+      "train_loss": 0.01017542961082654,
+      "train_runtime": 2023.7651,
+      "train_samples_per_second": 0.796,
+      "train_steps_per_second": 0.099
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.730765272920883e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3516a591d7d35980f95ff06f84083af329fc30bdfe9923b28d24cc57761cb9df
+size 5688