BraylonDash
commited on
Commit
•
50e9903
1
Parent(s):
a3009ef
Model save
Browse files- README.md +74 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +40 -0
- all_results.json +21 -0
- eval_results.json +16 -0
- merges.txt +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +325 -0
- train_results.json +8 -0
- trainer_state.json +412 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: microsoft/phi-2
|
9 |
+
model-index:
|
10 |
+
- name: phi-2-gpo-test-longest-iter-v1-4
|
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 |
+
# phi-2-gpo-test-longest-iter-v1-4
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0015
|
22 |
+
- Rewards/chosen: 0.0002
|
23 |
+
- Rewards/rejected: -0.0007
|
24 |
+
- Rewards/accuracies: 0.5360
|
25 |
+
- Rewards/margins: 0.0010
|
26 |
+
- Logps/rejected: -278.6109
|
27 |
+
- Logps/chosen: -306.2527
|
28 |
+
- Logits/rejected: 0.0934
|
29 |
+
- Logits/chosen: -0.0054
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 5e-06
|
49 |
+
- train_batch_size: 4
|
50 |
+
- eval_batch_size: 4
|
51 |
+
- seed: 42
|
52 |
+
- distributed_type: multi-GPU
|
53 |
+
- gradient_accumulation_steps: 4
|
54 |
+
- total_train_batch_size: 16
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: cosine
|
57 |
+
- lr_scheduler_warmup_ratio: 0.1
|
58 |
+
- num_epochs: 4
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
64 |
+
| 0.001 | 1.6 | 100 | 0.0015 | 0.0000 | -0.0003 | 0.5040 | 0.0004 | -278.5704 | -306.2733 | 0.0926 | -0.0051 |
|
65 |
+
| 0.001 | 3.2 | 200 | 0.0015 | -0.0000 | -0.0004 | 0.4885 | 0.0004 | -278.5775 | -306.2765 | 0.0977 | -0.0020 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- PEFT 0.7.1
|
71 |
+
- Transformers 4.36.2
|
72 |
+
- Pytorch 2.2.1+cu121
|
73 |
+
- Datasets 2.14.6
|
74 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/phi-2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"dense",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53abdd8d977e378f38919016b3b2cae63e96725c685edcb2728030b495653d02
|
3 |
+
size 41977616
|
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257
|
40 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.97,
|
3 |
+
"eval_logits/chosen": -0.005432075820863247,
|
4 |
+
"eval_logits/rejected": 0.09337250888347626,
|
5 |
+
"eval_logps/chosen": -306.2527160644531,
|
6 |
+
"eval_logps/rejected": -278.61090087890625,
|
7 |
+
"eval_loss": 0.0015043426537886262,
|
8 |
+
"eval_rewards/accuracies": 0.5360000133514404,
|
9 |
+
"eval_rewards/chosen": 0.00021375658980105072,
|
10 |
+
"eval_rewards/margins": 0.000962120364420116,
|
11 |
+
"eval_rewards/rejected": -0.0007483638473786414,
|
12 |
+
"eval_runtime": 420.5209,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 4.756,
|
15 |
+
"eval_steps_per_second": 1.189,
|
16 |
+
"train_loss": 0.001002159876318934,
|
17 |
+
"train_runtime": 2735.225,
|
18 |
+
"train_samples": 61135,
|
19 |
+
"train_samples_per_second": 1.462,
|
20 |
+
"train_steps_per_second": 0.091
|
21 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.97,
|
3 |
+
"eval_logits/chosen": -0.005432075820863247,
|
4 |
+
"eval_logits/rejected": 0.09337250888347626,
|
5 |
+
"eval_logps/chosen": -306.2527160644531,
|
6 |
+
"eval_logps/rejected": -278.61090087890625,
|
7 |
+
"eval_loss": 0.0015043426537886262,
|
8 |
+
"eval_rewards/accuracies": 0.5360000133514404,
|
9 |
+
"eval_rewards/chosen": 0.00021375658980105072,
|
10 |
+
"eval_rewards/margins": 0.000962120364420116,
|
11 |
+
"eval_rewards/rejected": -0.0007483638473786414,
|
12 |
+
"eval_runtime": 420.5209,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 4.756,
|
15 |
+
"eval_steps_per_second": 1.189
|
16 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": " ",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": false
|
19 |
+
},
|
20 |
+
"50258": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50259": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50260": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50261": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50262": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50263": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50264": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50265": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50266": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50267": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50268": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50269": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50270": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50271": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50272": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50273": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50274": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50275": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50276": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50277": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50278": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50279": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50280": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"50281": {
|
205 |
+
"content": " ",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"50282": {
|
213 |
+
"content": " ",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"50283": {
|
221 |
+
"content": " ",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"50284": {
|
229 |
+
"content": " ",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": true,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"50285": {
|
237 |
+
"content": " ",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": true,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"50286": {
|
245 |
+
"content": " ",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": true,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"50287": {
|
253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"50288": {
|
261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": true,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"50289": {
|
269 |
+
"content": "\t\t\t\t\t\t\t",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"50290": {
|
277 |
+
"content": "\t\t\t\t\t\t",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"50291": {
|
285 |
+
"content": "\t\t\t\t\t",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"50292": {
|
293 |
+
"content": "\t\t\t\t",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"50293": {
|
301 |
+
"content": "\t\t\t",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"50294": {
|
309 |
+
"content": "\t\t",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
}
|
316 |
+
},
|
317 |
+
"bos_token": "<|endoftext|>",
|
318 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
319 |
+
"clean_up_tokenization_spaces": true,
|
320 |
+
"eos_token": "<|endoftext|>",
|
321 |
+
"model_max_length": 2048,
|
322 |
+
"pad_token": "<|endoftext|>",
|
323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
324 |
+
"unk_token": "<|endoftext|>"
|
325 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.97,
|
3 |
+
"train_loss": 0.001002159876318934,
|
4 |
+
"train_runtime": 2735.225,
|
5 |
+
"train_samples": 61135,
|
6 |
+
"train_samples_per_second": 1.462,
|
7 |
+
"train_steps_per_second": 0.091
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.968,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 248,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 2.0000000000000002e-07,
|
14 |
+
"logits/chosen": 0.34545159339904785,
|
15 |
+
"logits/rejected": 0.2957597076892853,
|
16 |
+
"logps/chosen": -217.1103973388672,
|
17 |
+
"logps/rejected": -154.90234375,
|
18 |
+
"loss": 0.0009,
|
19 |
+
"rewards/accuracies": 0.0,
|
20 |
+
"rewards/chosen": 0.0,
|
21 |
+
"rewards/margins": 0.0,
|
22 |
+
"rewards/rejected": 0.0,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.16,
|
27 |
+
"learning_rate": 2.0000000000000003e-06,
|
28 |
+
"logits/chosen": 0.24290476739406586,
|
29 |
+
"logits/rejected": 0.1927487701177597,
|
30 |
+
"logps/chosen": -189.50128173828125,
|
31 |
+
"logps/rejected": -162.37692260742188,
|
32 |
+
"loss": 0.0011,
|
33 |
+
"rewards/accuracies": 0.3055555522441864,
|
34 |
+
"rewards/chosen": -0.0005859931115992367,
|
35 |
+
"rewards/margins": -0.001147971022874117,
|
36 |
+
"rewards/rejected": 0.0005619778530672193,
|
37 |
+
"step": 10
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.32,
|
41 |
+
"learning_rate": 4.000000000000001e-06,
|
42 |
+
"logits/chosen": 0.1098150983452797,
|
43 |
+
"logits/rejected": 0.06667135655879974,
|
44 |
+
"logps/chosen": -170.3683319091797,
|
45 |
+
"logps/rejected": -145.548095703125,
|
46 |
+
"loss": 0.0011,
|
47 |
+
"rewards/accuracies": 0.38749998807907104,
|
48 |
+
"rewards/chosen": -2.7951715310337022e-05,
|
49 |
+
"rewards/margins": -0.00022801189334131777,
|
50 |
+
"rewards/rejected": 0.00020006010890938342,
|
51 |
+
"step": 20
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.48,
|
55 |
+
"learning_rate": 4.993800445762451e-06,
|
56 |
+
"logits/chosen": 0.15559187531471252,
|
57 |
+
"logits/rejected": 0.15184751152992249,
|
58 |
+
"logps/chosen": -184.87167358398438,
|
59 |
+
"logps/rejected": -146.75131225585938,
|
60 |
+
"loss": 0.0011,
|
61 |
+
"rewards/accuracies": 0.39375001192092896,
|
62 |
+
"rewards/chosen": -0.00036125333281233907,
|
63 |
+
"rewards/margins": -0.0002040974359260872,
|
64 |
+
"rewards/rejected": -0.00015715583867859095,
|
65 |
+
"step": 30
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.64,
|
69 |
+
"learning_rate": 4.944388344834205e-06,
|
70 |
+
"logits/chosen": 0.11296383291482925,
|
71 |
+
"logits/rejected": 0.20522311329841614,
|
72 |
+
"logps/chosen": -182.8056640625,
|
73 |
+
"logps/rejected": -148.15756225585938,
|
74 |
+
"loss": 0.0009,
|
75 |
+
"rewards/accuracies": 0.4625000059604645,
|
76 |
+
"rewards/chosen": -0.00020849374413955957,
|
77 |
+
"rewards/margins": 0.001540421275421977,
|
78 |
+
"rewards/rejected": -0.0017489150632172823,
|
79 |
+
"step": 40
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8,
|
83 |
+
"learning_rate": 4.8465431931347904e-06,
|
84 |
+
"logits/chosen": 0.2731459140777588,
|
85 |
+
"logits/rejected": 0.17598305642604828,
|
86 |
+
"logps/chosen": -196.51651000976562,
|
87 |
+
"logps/rejected": -161.89797973632812,
|
88 |
+
"loss": 0.001,
|
89 |
+
"rewards/accuracies": 0.4437499940395355,
|
90 |
+
"rewards/chosen": -0.0016538338968530297,
|
91 |
+
"rewards/margins": 0.000834259029943496,
|
92 |
+
"rewards/rejected": -0.0024880929850041866,
|
93 |
+
"step": 50
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.96,
|
97 |
+
"learning_rate": 4.702203692102539e-06,
|
98 |
+
"logits/chosen": 0.19920073449611664,
|
99 |
+
"logits/rejected": 0.17924004793167114,
|
100 |
+
"logps/chosen": -182.0515594482422,
|
101 |
+
"logps/rejected": -150.9364013671875,
|
102 |
+
"loss": 0.001,
|
103 |
+
"rewards/accuracies": 0.40625,
|
104 |
+
"rewards/chosen": 0.00011732898565242067,
|
105 |
+
"rewards/margins": 0.0012116450816392899,
|
106 |
+
"rewards/rejected": -0.0010943160159513354,
|
107 |
+
"step": 60
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.12,
|
111 |
+
"learning_rate": 4.514229781074239e-06,
|
112 |
+
"logits/chosen": 0.1093553751707077,
|
113 |
+
"logits/rejected": 0.17700831592082977,
|
114 |
+
"logps/chosen": -203.3074188232422,
|
115 |
+
"logps/rejected": -173.57713317871094,
|
116 |
+
"loss": 0.001,
|
117 |
+
"rewards/accuracies": 0.4312500059604645,
|
118 |
+
"rewards/chosen": -0.00015989062376320362,
|
119 |
+
"rewards/margins": 0.0011065483558923006,
|
120 |
+
"rewards/rejected": -0.0012664392124861479,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.28,
|
125 |
+
"learning_rate": 4.286345970517195e-06,
|
126 |
+
"logits/chosen": 0.13181297481060028,
|
127 |
+
"logits/rejected": 0.1530202180147171,
|
128 |
+
"logps/chosen": -193.3525848388672,
|
129 |
+
"logps/rejected": -161.02328491210938,
|
130 |
+
"loss": 0.0011,
|
131 |
+
"rewards/accuracies": 0.40625,
|
132 |
+
"rewards/chosen": 0.00105115189217031,
|
133 |
+
"rewards/margins": 0.00026105757569894195,
|
134 |
+
"rewards/rejected": 0.0007900940254330635,
|
135 |
+
"step": 80
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.44,
|
139 |
+
"learning_rate": 4.023067544670082e-06,
|
140 |
+
"logits/chosen": 0.10432066023349762,
|
141 |
+
"logits/rejected": 0.11901885271072388,
|
142 |
+
"logps/chosen": -184.4915771484375,
|
143 |
+
"logps/rejected": -151.45025634765625,
|
144 |
+
"loss": 0.0009,
|
145 |
+
"rewards/accuracies": 0.46875,
|
146 |
+
"rewards/chosen": 0.0010537179186940193,
|
147 |
+
"rewards/margins": 0.002086392603814602,
|
148 |
+
"rewards/rejected": -0.0010326746851205826,
|
149 |
+
"step": 90
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.6,
|
153 |
+
"learning_rate": 3.7296110958116845e-06,
|
154 |
+
"logits/chosen": 0.17887040972709656,
|
155 |
+
"logits/rejected": 0.13352127373218536,
|
156 |
+
"logps/chosen": -176.19094848632812,
|
157 |
+
"logps/rejected": -149.05015563964844,
|
158 |
+
"loss": 0.001,
|
159 |
+
"rewards/accuracies": 0.375,
|
160 |
+
"rewards/chosen": 0.0006333684432320297,
|
161 |
+
"rewards/margins": 0.00030291633447632194,
|
162 |
+
"rewards/rejected": 0.00033045216696336865,
|
163 |
+
"step": 100
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.6,
|
167 |
+
"eval_logits/chosen": -0.005087433848530054,
|
168 |
+
"eval_logits/rejected": 0.09259650856256485,
|
169 |
+
"eval_logps/chosen": -306.27325439453125,
|
170 |
+
"eval_logps/rejected": -278.57037353515625,
|
171 |
+
"eval_loss": 0.0014748616376891732,
|
172 |
+
"eval_rewards/accuracies": 0.5040000081062317,
|
173 |
+
"eval_rewards/chosen": 8.555292879464105e-06,
|
174 |
+
"eval_rewards/margins": 0.00035174566437490284,
|
175 |
+
"eval_rewards/rejected": -0.0003431903896853328,
|
176 |
+
"eval_runtime": 421.2425,
|
177 |
+
"eval_samples_per_second": 4.748,
|
178 |
+
"eval_steps_per_second": 1.187,
|
179 |
+
"step": 100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.76,
|
183 |
+
"learning_rate": 3.4117911628292944e-06,
|
184 |
+
"logits/chosen": 0.1393759548664093,
|
185 |
+
"logits/rejected": 0.09525509178638458,
|
186 |
+
"logps/chosen": -194.57229614257812,
|
187 |
+
"logps/rejected": -159.84437561035156,
|
188 |
+
"loss": 0.001,
|
189 |
+
"rewards/accuracies": 0.40625,
|
190 |
+
"rewards/chosen": 0.0006214675377123058,
|
191 |
+
"rewards/margins": 0.0007887079264037311,
|
192 |
+
"rewards/rejected": -0.00016724050510674715,
|
193 |
+
"step": 110
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 1.92,
|
197 |
+
"learning_rate": 3.075905022087675e-06,
|
198 |
+
"logits/chosen": 0.19464930891990662,
|
199 |
+
"logits/rejected": 0.26265355944633484,
|
200 |
+
"logps/chosen": -182.62338256835938,
|
201 |
+
"logps/rejected": -146.72181701660156,
|
202 |
+
"loss": 0.001,
|
203 |
+
"rewards/accuracies": 0.45625001192092896,
|
204 |
+
"rewards/chosen": 0.00028288367320783436,
|
205 |
+
"rewards/margins": 0.0012492609675973654,
|
206 |
+
"rewards/rejected": -0.0009663773817010224,
|
207 |
+
"step": 120
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.08,
|
211 |
+
"learning_rate": 2.728607913349464e-06,
|
212 |
+
"logits/chosen": 0.2267303168773651,
|
213 |
+
"logits/rejected": 0.21481864154338837,
|
214 |
+
"logps/chosen": -175.65589904785156,
|
215 |
+
"logps/rejected": -143.40615844726562,
|
216 |
+
"loss": 0.0011,
|
217 |
+
"rewards/accuracies": 0.40625,
|
218 |
+
"rewards/chosen": 0.0007823506603017449,
|
219 |
+
"rewards/margins": 0.00022141262888908386,
|
220 |
+
"rewards/rejected": 0.000560938089620322,
|
221 |
+
"step": 130
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.24,
|
225 |
+
"learning_rate": 2.376781173017589e-06,
|
226 |
+
"logits/chosen": 0.18638554215431213,
|
227 |
+
"logits/rejected": 0.19504567980766296,
|
228 |
+
"logps/chosen": -181.9698486328125,
|
229 |
+
"logps/rejected": -152.50296020507812,
|
230 |
+
"loss": 0.001,
|
231 |
+
"rewards/accuracies": 0.4312500059604645,
|
232 |
+
"rewards/chosen": 0.002239116234704852,
|
233 |
+
"rewards/margins": 0.001197666977532208,
|
234 |
+
"rewards/rejected": 0.0010414490243420005,
|
235 |
+
"step": 140
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.4,
|
239 |
+
"learning_rate": 2.0273958875043877e-06,
|
240 |
+
"logits/chosen": 0.17610232532024384,
|
241 |
+
"logits/rejected": 0.1723514050245285,
|
242 |
+
"logps/chosen": -199.57699584960938,
|
243 |
+
"logps/rejected": -177.21139526367188,
|
244 |
+
"loss": 0.001,
|
245 |
+
"rewards/accuracies": 0.4124999940395355,
|
246 |
+
"rewards/chosen": 0.0006620158674195409,
|
247 |
+
"rewards/margins": 0.0013073014561086893,
|
248 |
+
"rewards/rejected": -0.0006452856468968093,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.56,
|
253 |
+
"learning_rate": 1.6873747682962393e-06,
|
254 |
+
"logits/chosen": 0.07310830056667328,
|
255 |
+
"logits/rejected": 0.17652472853660583,
|
256 |
+
"logps/chosen": -183.4370880126953,
|
257 |
+
"logps/rejected": -141.97218322753906,
|
258 |
+
"loss": 0.001,
|
259 |
+
"rewards/accuracies": 0.5,
|
260 |
+
"rewards/chosen": 0.0025453295093029737,
|
261 |
+
"rewards/margins": 0.0023006144911050797,
|
262 |
+
"rewards/rejected": 0.00024471539654769003,
|
263 |
+
"step": 160
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 2.72,
|
267 |
+
"learning_rate": 1.363454985517803e-06,
|
268 |
+
"logits/chosen": 0.10622234642505646,
|
269 |
+
"logits/rejected": 0.20915362238883972,
|
270 |
+
"logps/chosen": -185.3426971435547,
|
271 |
+
"logps/rejected": -146.079345703125,
|
272 |
+
"loss": 0.0009,
|
273 |
+
"rewards/accuracies": 0.4625000059604645,
|
274 |
+
"rewards/chosen": 0.0036269682459533215,
|
275 |
+
"rewards/margins": 0.002667922293767333,
|
276 |
+
"rewards/rejected": 0.0009590461850166321,
|
277 |
+
"step": 170
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 2.88,
|
281 |
+
"learning_rate": 1.062054677808238e-06,
|
282 |
+
"logits/chosen": 0.19405516982078552,
|
283 |
+
"logits/rejected": 0.16787810623645782,
|
284 |
+
"logps/chosen": -199.97219848632812,
|
285 |
+
"logps/rejected": -163.14398193359375,
|
286 |
+
"loss": 0.001,
|
287 |
+
"rewards/accuracies": 0.44999998807907104,
|
288 |
+
"rewards/chosen": 0.0023652021773159504,
|
289 |
+
"rewards/margins": 0.0015264868270605803,
|
290 |
+
"rewards/rejected": 0.000838715408463031,
|
291 |
+
"step": 180
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 3.04,
|
295 |
+
"learning_rate": 7.891457834794711e-07,
|
296 |
+
"logits/chosen": 0.21832183003425598,
|
297 |
+
"logits/rejected": 0.20919294655323029,
|
298 |
+
"logps/chosen": -167.15711975097656,
|
299 |
+
"logps/rejected": -146.7445526123047,
|
300 |
+
"loss": 0.001,
|
301 |
+
"rewards/accuracies": 0.4000000059604645,
|
302 |
+
"rewards/chosen": 8.343837544089183e-05,
|
303 |
+
"rewards/margins": 0.0007264987798407674,
|
304 |
+
"rewards/rejected": -0.0006430605426430702,
|
305 |
+
"step": 190
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 3.2,
|
309 |
+
"learning_rate": 5.501357126768117e-07,
|
310 |
+
"logits/chosen": 0.07451615482568741,
|
311 |
+
"logits/rejected": 0.10825479030609131,
|
312 |
+
"logps/chosen": -187.6416015625,
|
313 |
+
"logps/rejected": -153.81216430664062,
|
314 |
+
"loss": 0.001,
|
315 |
+
"rewards/accuracies": 0.42500001192092896,
|
316 |
+
"rewards/chosen": 0.0008775632595643401,
|
317 |
+
"rewards/margins": 0.0012995953438803554,
|
318 |
+
"rewards/rejected": -0.00042203222983516753,
|
319 |
+
"step": 200
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 3.2,
|
323 |
+
"eval_logits/chosen": -0.0019514876184985042,
|
324 |
+
"eval_logits/rejected": 0.0977490246295929,
|
325 |
+
"eval_logps/chosen": -306.2765197753906,
|
326 |
+
"eval_logps/rejected": -278.5775146484375,
|
327 |
+
"eval_loss": 0.0015296473866328597,
|
328 |
+
"eval_rewards/accuracies": 0.4884999990463257,
|
329 |
+
"eval_rewards/chosen": -2.441116339468863e-05,
|
330 |
+
"eval_rewards/margins": 0.00038999062962830067,
|
331 |
+
"eval_rewards/rejected": -0.000414401845773682,
|
332 |
+
"eval_runtime": 420.5773,
|
333 |
+
"eval_samples_per_second": 4.755,
|
334 |
+
"eval_steps_per_second": 1.189,
|
335 |
+
"step": 200
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 3.36,
|
339 |
+
"learning_rate": 3.4976020508682345e-07,
|
340 |
+
"logits/chosen": 0.24440991878509521,
|
341 |
+
"logits/rejected": 0.20419850945472717,
|
342 |
+
"logps/chosen": -173.31942749023438,
|
343 |
+
"logps/rejected": -149.56796264648438,
|
344 |
+
"loss": 0.001,
|
345 |
+
"rewards/accuracies": 0.4625000059604645,
|
346 |
+
"rewards/chosen": 0.0018821163102984428,
|
347 |
+
"rewards/margins": 0.0013987896963953972,
|
348 |
+
"rewards/rejected": 0.0004833267885260284,
|
349 |
+
"step": 210
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 3.52,
|
353 |
+
"learning_rate": 1.9198949610721273e-07,
|
354 |
+
"logits/chosen": 0.195010706782341,
|
355 |
+
"logits/rejected": 0.1568932682275772,
|
356 |
+
"logps/chosen": -196.238525390625,
|
357 |
+
"logps/rejected": -168.1038055419922,
|
358 |
+
"loss": 0.0009,
|
359 |
+
"rewards/accuracies": 0.4375,
|
360 |
+
"rewards/chosen": 0.0010507756378501654,
|
361 |
+
"rewards/margins": 0.0023238039575517178,
|
362 |
+
"rewards/rejected": -0.001273027970455587,
|
363 |
+
"step": 220
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 3.68,
|
367 |
+
"learning_rate": 7.994965069994143e-08,
|
368 |
+
"logits/chosen": 0.1438043862581253,
|
369 |
+
"logits/rejected": 0.13570797443389893,
|
370 |
+
"logps/chosen": -193.8529815673828,
|
371 |
+
"logps/rejected": -155.14317321777344,
|
372 |
+
"loss": 0.001,
|
373 |
+
"rewards/accuracies": 0.42500001192092896,
|
374 |
+
"rewards/chosen": 0.0007188455201685429,
|
375 |
+
"rewards/margins": 0.0012139389291405678,
|
376 |
+
"rewards/rejected": -0.0004950935835950077,
|
377 |
+
"step": 230
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 3.84,
|
381 |
+
"learning_rate": 1.5860623616664183e-08,
|
382 |
+
"logits/chosen": 0.1838085651397705,
|
383 |
+
"logits/rejected": 0.06515821814537048,
|
384 |
+
"logps/chosen": -176.7322235107422,
|
385 |
+
"logps/rejected": -146.44021606445312,
|
386 |
+
"loss": 0.0009,
|
387 |
+
"rewards/accuracies": 0.45625001192092896,
|
388 |
+
"rewards/chosen": 0.004661304876208305,
|
389 |
+
"rewards/margins": 0.0025658137165009975,
|
390 |
+
"rewards/rejected": 0.0020954906940460205,
|
391 |
+
"step": 240
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 3.97,
|
395 |
+
"step": 248,
|
396 |
+
"total_flos": 0.0,
|
397 |
+
"train_loss": 0.001002159876318934,
|
398 |
+
"train_runtime": 2735.225,
|
399 |
+
"train_samples_per_second": 1.462,
|
400 |
+
"train_steps_per_second": 0.091
|
401 |
+
}
|
402 |
+
],
|
403 |
+
"logging_steps": 10,
|
404 |
+
"max_steps": 248,
|
405 |
+
"num_input_tokens_seen": 0,
|
406 |
+
"num_train_epochs": 4,
|
407 |
+
"save_steps": 100,
|
408 |
+
"total_flos": 0.0,
|
409 |
+
"train_batch_size": 4,
|
410 |
+
"trial_name": null,
|
411 |
+
"trial_params": null
|
412 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41f0c0340faadffa4ac9ed6d012e41672248a16cdc002a155416d73cdcfc481e
|
3 |
+
size 5880
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|