Model save

README.md

@@ -0,0 +1,79 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+license: apache-2.0
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Mistral-7B_task-1_60-samples_config-2_full
+ 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_task-1_60-samples_config-2_full
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4381
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 2.1677 | 0.6957 | 2 | 1.9772 |
+| 2.0588 | 1.7391 | 5 | 1.7098 |
+| 1.6144 | 2.7826 | 8 | 1.4226 |
+| 1.3861 | 3.8261 | 11 | 1.1334 |
+| 1.0181 | 4.8696 | 14 | 0.9961 |
+| 0.9301 | 5.9130 | 17 | 0.9633 |
+| 0.8066 | 6.9565 | 20 | 0.9348 |
+| 0.7473 | 8.0 | 23 | 0.9316 |
+| 0.6909 | 8.6957 | 25 | 0.9585 |
+| 0.5525 | 9.7391 | 28 | 0.9743 |
+| 0.49 | 10.7826 | 31 | 1.0671 |
+| 0.3604 | 11.8261 | 34 | 1.1000 |
+| 0.3096 | 12.8696 | 37 | 1.2756 |
+| 0.2231 | 13.9130 | 40 | 1.3029 |
+| 0.1846 | 14.9565 | 43 | 1.4381 |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f487f51fc7872675a51d4f747da1651a15123f8688cfb5f852418e7d48b566
+oid sha256:164a19fdc70a19fd025fc046181cfe31dd57fb65e8651ecf3f8184fa3fdf8d20
 size 167832240

all_results.json

@@ -0,0 +1,9 @@
+{
+ "epoch": 14.956521739130435,
+ "total_flos": 1.009626071957504e+16,
+ "train_loss": 0.8760424204343973,
+ "train_runtime": 806.7681,
+ "train_samples": 46,
+ "train_samples_per_second": 2.851,
+ "train_steps_per_second": 0.124
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+ "epoch": 14.956521739130435,
+ "total_flos": 1.009626071957504e+16,
+ "train_loss": 0.8760424204343973,
+ "train_runtime": 806.7681,
+ "train_samples": 46,
+ "train_samples_per_second": 2.851,
+ "train_steps_per_second": 0.124
+}

trainer_state.json

@@ -0,0 +1,325 @@
+{
+ "best_metric": 0.9315621256828308,
+ "best_model_checkpoint": "data/Mistral-7B_task-1_60-samples_config-2_full/checkpoint-23",
+ "epoch": 14.956521739130435,
+ "eval_steps": 500,
+ "global_step": 43,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.34782608695652173,
+ "grad_norm": 2.7660365104675293,
+ "learning_rate": 1e-05,
+ "loss": 2.1412,
+ "step": 1
+ },
+ {
+ "epoch": 0.6956521739130435,
+ "grad_norm": 2.761305332183838,
+ "learning_rate": 2e-05,
+ "loss": 2.1677,
+ "step": 2
+ },
+ {
+ "epoch": 0.6956521739130435,
+ "eval_loss": 1.9772213697433472,
+ "eval_runtime": 4.8565,
+ "eval_samples_per_second": 2.471,
+ "eval_steps_per_second": 2.471,
+ "step": 2
+ },
+ {
+ "epoch": 1.391304347826087,
+ "grad_norm": 2.450890064239502,
+ "learning_rate": 4e-05,
+ "loss": 2.0588,
+ "step": 4
+ },
+ {
+ "epoch": 1.7391304347826086,
+ "eval_loss": 1.7097864151000977,
+ "eval_runtime": 4.8552,
+ "eval_samples_per_second": 2.472,
+ "eval_steps_per_second": 2.472,
+ "step": 5
+ },
+ {
+ "epoch": 2.0869565217391304,
+ "grad_norm": 1.6053310632705688,
+ "learning_rate": 6e-05,
+ "loss": 1.862,
+ "step": 6
+ },
+ {
+ "epoch": 2.782608695652174,
+ "grad_norm": 1.1415278911590576,
+ "learning_rate": 8e-05,
+ "loss": 1.6144,
+ "step": 8
+ },
+ {
+ "epoch": 2.782608695652174,
+ "eval_loss": 1.4225901365280151,
+ "eval_runtime": 4.8447,
+ "eval_samples_per_second": 2.477,
+ "eval_steps_per_second": 2.477,
+ "step": 8
+ },
+ {
+ "epoch": 3.4782608695652173,
+ "grad_norm": 1.6181377172470093,
+ "learning_rate": 0.0001,
+ "loss": 1.3861,
+ "step": 10
+ },
+ {
+ "epoch": 3.8260869565217392,
+ "eval_loss": 1.1334022283554077,
+ "eval_runtime": 4.8621,
+ "eval_samples_per_second": 2.468,
+ "eval_steps_per_second": 2.468,
+ "step": 11
+ },
+ {
+ "epoch": 4.173913043478261,
+ "grad_norm": 1.2450289726257324,
+ "learning_rate": 9.987820251299122e-05,
+ "loss": 1.1643,
+ "step": 12
+ },
+ {
+ "epoch": 4.869565217391305,
+ "grad_norm": 0.8130146265029907,
+ "learning_rate": 9.951340343707852e-05,
+ "loss": 1.0181,
+ "step": 14
+ },
+ {
+ "epoch": 4.869565217391305,
+ "eval_loss": 0.9961085915565491,
+ "eval_runtime": 4.854,
+ "eval_samples_per_second": 2.472,
+ "eval_steps_per_second": 2.472,
+ "step": 14
+ },
+ {
+ "epoch": 5.565217391304348,
+ "grad_norm": 0.6594259738922119,
+ "learning_rate": 9.890738003669029e-05,
+ "loss": 0.9301,
+ "step": 16
+ },
+ {
+ "epoch": 5.913043478260869,
+ "eval_loss": 0.9633287787437439,
+ "eval_runtime": 4.8357,
+ "eval_samples_per_second": 2.482,
+ "eval_steps_per_second": 2.482,
+ "step": 17
+ },
+ {
+ "epoch": 6.260869565217392,
+ "grad_norm": 0.6981428861618042,
+ "learning_rate": 9.806308479691595e-05,
+ "loss": 0.8321,
+ "step": 18
+ },
+ {
+ "epoch": 6.956521739130435,
+ "grad_norm": 0.6706119179725647,
+ "learning_rate": 9.698463103929542e-05,
+ "loss": 0.8066,
+ "step": 20
+ },
+ {
+ "epoch": 6.956521739130435,
+ "eval_loss": 0.9347649216651917,
+ "eval_runtime": 4.8358,
+ "eval_samples_per_second": 2.482,
+ "eval_steps_per_second": 2.482,
+ "step": 20
+ },
+ {
+ "epoch": 7.6521739130434785,
+ "grad_norm": 0.5864876508712769,
+ "learning_rate": 9.567727288213005e-05,
+ "loss": 0.7473,
+ "step": 22
+ },
+ {
+ "epoch": 8.0,
+ "eval_loss": 0.9315621256828308,
+ "eval_runtime": 4.8328,
+ "eval_samples_per_second": 2.483,
+ "eval_steps_per_second": 2.483,
+ "step": 23
+ },
+ {
+ "epoch": 8.347826086956522,
+ "grad_norm": 0.634713888168335,
+ "learning_rate": 9.414737964294636e-05,
+ "loss": 0.6909,
+ "step": 24
+ },
+ {
+ "epoch": 8.695652173913043,
+ "eval_loss": 0.9585385322570801,
+ "eval_runtime": 4.8356,
+ "eval_samples_per_second": 2.482,
+ "eval_steps_per_second": 2.482,
+ "step": 25
+ },
+ {
+ "epoch": 9.043478260869565,
+ "grad_norm": 0.8111370801925659,
+ "learning_rate": 9.24024048078213e-05,
+ "loss": 0.6233,
+ "step": 26
+ },
+ {
+ "epoch": 9.73913043478261,
+ "grad_norm": 0.8550280332565308,
+ "learning_rate": 9.045084971874738e-05,
+ "loss": 0.5525,
+ "step": 28
+ },
+ {
+ "epoch": 9.73913043478261,
+ "eval_loss": 0.9742663502693176,
+ "eval_runtime": 4.8332,
+ "eval_samples_per_second": 2.483,
+ "eval_steps_per_second": 2.483,
+ "step": 28
+ },
+ {
+ "epoch": 10.434782608695652,
+ "grad_norm": 0.790436863899231,
+ "learning_rate": 8.83022221559489e-05,
+ "loss": 0.49,
+ "step": 30
+ },
+ {
+ "epoch": 10.782608695652174,
+ "eval_loss": 1.0670939683914185,
+ "eval_runtime": 4.834,
+ "eval_samples_per_second": 2.482,
+ "eval_steps_per_second": 2.482,
+ "step": 31
+ },
+ {
+ "epoch": 11.130434782608695,
+ "grad_norm": 1.2715283632278442,
+ "learning_rate": 8.596699001693255e-05,
+ "loss": 0.4556,
+ "step": 32
+ },
+ {
+ "epoch": 11.826086956521738,
+ "grad_norm": 0.8485116362571716,
+ "learning_rate": 8.345653031794292e-05,
+ "loss": 0.3604,
+ "step": 34
+ },
+ {
+ "epoch": 11.826086956521738,
+ "eval_loss": 1.0999555587768555,
+ "eval_runtime": 4.8347,
+ "eval_samples_per_second": 2.482,
+ "eval_steps_per_second": 2.482,
+ "step": 34
+ },
+ {
+ "epoch": 12.521739130434783,
+ "grad_norm": 0.8741176724433899,
+ "learning_rate": 8.07830737662829e-05,
+ "loss": 0.3096,
+ "step": 36
+ },
+ {
+ "epoch": 12.869565217391305,
+ "eval_loss": 1.275596022605896,
+ "eval_runtime": 4.8346,
+ "eval_samples_per_second": 2.482,
+ "eval_steps_per_second": 2.482,
+ "step": 37
+ },
+ {
+ "epoch": 13.217391304347826,
+ "grad_norm": 1.3192121982574463,
+ "learning_rate": 7.795964517353735e-05,
+ "loss": 0.2648,
+ "step": 38
+ },
+ {
+ "epoch": 13.91304347826087,
+ "grad_norm": 1.0160993337631226,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.2231,
+ "step": 40
+ },
+ {
+ "epoch": 13.91304347826087,
+ "eval_loss": 1.302903175354004,
+ "eval_runtime": 4.8323,
+ "eval_samples_per_second": 2.483,
+ "eval_steps_per_second": 2.483,
+ "step": 40
+ },
+ {
+ "epoch": 14.608695652173914,
+ "grad_norm": 0.6346321105957031,
+ "learning_rate": 7.191855733945387e-05,
+ "loss": 0.1846,
+ "step": 42
+ },
+ {
+ "epoch": 14.956521739130435,
+ "eval_loss": 1.4380816221237183,
+ "eval_runtime": 4.8324,
+ "eval_samples_per_second": 2.483,
+ "eval_steps_per_second": 2.483,
+ "step": 43
+ },
+ {
+ "epoch": 14.956521739130435,
+ "step": 43,
+ "total_flos": 1.009626071957504e+16,
+ "train_loss": 0.8760424204343973,
+ "train_runtime": 806.7681,
+ "train_samples_per_second": 2.851,
+ "train_steps_per_second": 0.124
+ }
+ ],
+ "logging_steps": 2,
+ "max_steps": 100,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 50,
+ "save_steps": 25,
+ "stateful_callbacks": {
+ "EarlyStoppingCallback": {
+ "args": {
+ "early_stopping_patience": 7,
+ "early_stopping_threshold": 0.0
+ },
+ "attributes": {
+ "early_stopping_patience_counter": 0
+ }
+ },
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": true
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 1.009626071957504e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}