End of training
Browse files- README.md +56 -0
- trainer_state.json +42 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
license: llama3.1
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: chess-no-cot-lora-adapter-4b-llama-3.1-8b
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# chess-no-cot-lora-adapter-4b-llama-3.1-8b
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3.0
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- PEFT 0.12.0
|
53 |
+
- Transformers 4.44.0
|
54 |
+
- Pytorch 2.4.0+cu121
|
55 |
+
- Datasets 2.20.0
|
56 |
+
- Tokenizers 0.19.1
|
trainer_state.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 192,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 3.0,
|
13 |
+
"step": 192,
|
14 |
+
"total_flos": 2.031101718065971e+16,
|
15 |
+
"train_loss": 0.5908492008845011,
|
16 |
+
"train_runtime": 553.6386,
|
17 |
+
"train_samples_per_second": 5.516,
|
18 |
+
"train_steps_per_second": 0.347
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 192,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 3,
|
25 |
+
"save_steps": 500,
|
26 |
+
"stateful_callbacks": {
|
27 |
+
"TrainerControl": {
|
28 |
+
"args": {
|
29 |
+
"should_epoch_stop": false,
|
30 |
+
"should_evaluate": false,
|
31 |
+
"should_log": false,
|
32 |
+
"should_save": true,
|
33 |
+
"should_training_stop": true
|
34 |
+
},
|
35 |
+
"attributes": {}
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"total_flos": 2.031101718065971e+16,
|
39 |
+
"train_batch_size": 16,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": null
|
42 |
+
}
|