Model save
Browse files- README.md +63 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +57 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
9 |
+
model-index:
|
10 |
+
- name: phi_3-offline-dpo-noise-0.0-42
|
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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/causal/huggingface/runs/pnu5z3m9)
|
18 |
+
# phi_3-offline-dpo-noise-0.0-42
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-06
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 4
|
42 |
+
- seed: 42
|
43 |
+
- distributed_type: multi-GPU
|
44 |
+
- num_devices: 4
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 64
|
47 |
+
- total_eval_batch_size: 16
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
51 |
+
- num_epochs: 1
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- PEFT 0.7.1
|
60 |
+
- Transformers 4.42.3
|
61 |
+
- Pytorch 2.3.0+cu121
|
62 |
+
- Datasets 2.14.6
|
63 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9230769230769231,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6940749088923136,
|
5 |
+
"train_runtime": 53.4359,
|
6 |
+
"train_samples": 200,
|
7 |
+
"train_samples_per_second": 3.743,
|
8 |
+
"train_steps_per_second": 0.056
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9230769230769231,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6940749088923136,
|
5 |
+
"train_runtime": 53.4359,
|
6 |
+
"train_samples": 200,
|
7 |
+
"train_samples_per_second": 3.743,
|
8 |
+
"train_steps_per_second": 0.056
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9230769230769231,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 3,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.3076923076923077,
|
13 |
+
"grad_norm": 0.22362739856280167,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"logits/chosen": 11.287857055664062,
|
16 |
+
"logits/rejected": 11.603424072265625,
|
17 |
+
"logps/chosen": -380.2095642089844,
|
18 |
+
"logps/rejected": -391.62744140625,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.9230769230769231,
|
28 |
+
"step": 3,
|
29 |
+
"total_flos": 0.0,
|
30 |
+
"train_loss": 0.6940749088923136,
|
31 |
+
"train_runtime": 53.4359,
|
32 |
+
"train_samples_per_second": 3.743,
|
33 |
+
"train_steps_per_second": 0.056
|
34 |
+
}
|
35 |
+
],
|
36 |
+
"logging_steps": 10,
|
37 |
+
"max_steps": 3,
|
38 |
+
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 1,
|
40 |
+
"save_steps": 100,
|
41 |
+
"stateful_callbacks": {
|
42 |
+
"TrainerControl": {
|
43 |
+
"args": {
|
44 |
+
"should_epoch_stop": false,
|
45 |
+
"should_evaluate": false,
|
46 |
+
"should_log": false,
|
47 |
+
"should_save": true,
|
48 |
+
"should_training_stop": true
|
49 |
+
},
|
50 |
+
"attributes": {}
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"total_flos": 0.0,
|
54 |
+
"train_batch_size": 4,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": null
|
57 |
+
}
|