Model save
Browse files- README.md +75 -0
- all_results.json +8 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- train_results.json +8 -0
- trainer_state.json +573 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Minbyul/mistral-7b-wo-kqa_golden-sft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: mistral-7b-dpo-full-sft-wo-kqa_golden
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# mistral-7b-dpo-full-sft-wo-kqa_golden
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [Minbyul/mistral-7b-wo-kqa_golden-sft](https://huggingface.co/Minbyul/mistral-7b-wo-kqa_golden-sft) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0019
|
21 |
+
- Rewards/chosen: -0.4479
|
22 |
+
- Rewards/rejected: -10.0624
|
23 |
+
- Rewards/accuracies: 1.0
|
24 |
+
- Rewards/margins: 9.6145
|
25 |
+
- Logps/rejected: -1559.6263
|
26 |
+
- Logps/chosen: -241.4165
|
27 |
+
- Logits/rejected: -2.0553
|
28 |
+
- Logits/chosen: -1.3416
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 5e-07
|
48 |
+
- train_batch_size: 8
|
49 |
+
- eval_batch_size: 8
|
50 |
+
- seed: 42
|
51 |
+
- distributed_type: multi-GPU
|
52 |
+
- num_devices: 4
|
53 |
+
- gradient_accumulation_steps: 2
|
54 |
+
- total_train_batch_size: 64
|
55 |
+
- total_eval_batch_size: 32
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: cosine
|
58 |
+
- lr_scheduler_warmup_ratio: 0.1
|
59 |
+
- num_epochs: 1
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 0.2478 | 0.31 | 100 | 0.0352 | -0.1739 | -4.4264 | 1.0 | 4.2525 | -996.0294 | -214.0196 | -2.9200 | -2.1162 |
|
66 |
+
| 0.1385 | 0.61 | 200 | 0.0041 | -0.3360 | -8.1997 | 1.0 | 7.8637 | -1373.3590 | -230.2282 | -2.3336 | -1.6287 |
|
67 |
+
| 0.0899 | 0.92 | 300 | 0.0019 | -0.4479 | -10.0624 | 1.0 | 9.6145 | -1559.6263 | -241.4165 | -2.0553 | -1.3416 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.39.0.dev0
|
73 |
+
- Pytorch 2.1.2
|
74 |
+
- Datasets 2.14.6
|
75 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.23720380818807385,
|
4 |
+
"train_runtime": 5120.8034,
|
5 |
+
"train_samples": 20928,
|
6 |
+
"train_samples_per_second": 4.087,
|
7 |
+
"train_steps_per_second": 0.064
|
8 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.39.0.dev0"
|
6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11a5f9501c140442a6e12ca6d405a609616293ce4a25fdb2bbca8d41d6991318
|
3 |
+
size 4943162336
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8969ca2d52c294c90dc5e125606011d75579da565469ef9d5cae38799ba3a960
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ede0399704ae34fac4a7690a953d65c356a855ae202383db8cb1c2aed36ed2b8
|
3 |
+
size 4540516344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.23720380818807385,
|
4 |
+
"train_runtime": 5120.8034,
|
5 |
+
"train_samples": 20928,
|
6 |
+
"train_samples_per_second": 4.087,
|
7 |
+
"train_steps_per_second": 0.064
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 327,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 37.56032423344454,
|
14 |
+
"learning_rate": 1.5151515151515152e-08,
|
15 |
+
"logits/chosen": -3.115293502807617,
|
16 |
+
"logits/rejected": -3.0863265991210938,
|
17 |
+
"logps/chosen": -870.7420043945312,
|
18 |
+
"logps/rejected": -1334.502685546875,
|
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": 0.03,
|
28 |
+
"grad_norm": 37.49331944203386,
|
29 |
+
"learning_rate": 1.5151515151515152e-07,
|
30 |
+
"logits/chosen": -3.0526609420776367,
|
31 |
+
"logits/rejected": -3.0749807357788086,
|
32 |
+
"logps/chosen": -940.7243041992188,
|
33 |
+
"logps/rejected": -1276.6510009765625,
|
34 |
+
"loss": 0.6922,
|
35 |
+
"rewards/accuracies": 0.5486111044883728,
|
36 |
+
"rewards/chosen": 0.001147550530731678,
|
37 |
+
"rewards/margins": 0.0018619541078805923,
|
38 |
+
"rewards/rejected": -0.000714403809979558,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.06,
|
43 |
+
"grad_norm": 32.798777633158615,
|
44 |
+
"learning_rate": 3.0303030303030305e-07,
|
45 |
+
"logits/chosen": -3.0576233863830566,
|
46 |
+
"logits/rejected": -3.0690040588378906,
|
47 |
+
"logps/chosen": -956.8638916015625,
|
48 |
+
"logps/rejected": -1231.0487060546875,
|
49 |
+
"loss": 0.668,
|
50 |
+
"rewards/accuracies": 0.699999988079071,
|
51 |
+
"rewards/chosen": 0.03549911081790924,
|
52 |
+
"rewards/margins": 0.057550616562366486,
|
53 |
+
"rewards/rejected": -0.022051498293876648,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.09,
|
58 |
+
"grad_norm": 31.200374512571734,
|
59 |
+
"learning_rate": 4.545454545454545e-07,
|
60 |
+
"logits/chosen": -3.1981358528137207,
|
61 |
+
"logits/rejected": -3.1817786693573,
|
62 |
+
"logps/chosen": -1004.2825927734375,
|
63 |
+
"logps/rejected": -1336.2808837890625,
|
64 |
+
"loss": 0.6056,
|
65 |
+
"rewards/accuracies": 0.800000011920929,
|
66 |
+
"rewards/chosen": -0.0012753400951623917,
|
67 |
+
"rewards/margins": 0.2531731426715851,
|
68 |
+
"rewards/rejected": -0.25444847345352173,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.12,
|
73 |
+
"grad_norm": 31.57664285278684,
|
74 |
+
"learning_rate": 4.993009492952949e-07,
|
75 |
+
"logits/chosen": -3.2853000164031982,
|
76 |
+
"logits/rejected": -3.300828218460083,
|
77 |
+
"logps/chosen": -1001.1776123046875,
|
78 |
+
"logps/rejected": -1323.44287109375,
|
79 |
+
"loss": 0.5156,
|
80 |
+
"rewards/accuracies": 0.8125,
|
81 |
+
"rewards/chosen": -0.10599758476018906,
|
82 |
+
"rewards/margins": 0.550561785697937,
|
83 |
+
"rewards/rejected": -0.656559407711029,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.15,
|
88 |
+
"grad_norm": 32.0572257728948,
|
89 |
+
"learning_rate": 4.958864353026382e-07,
|
90 |
+
"logits/chosen": -3.3941280841827393,
|
91 |
+
"logits/rejected": -3.3549060821533203,
|
92 |
+
"logps/chosen": -880.5036010742188,
|
93 |
+
"logps/rejected": -1494.1220703125,
|
94 |
+
"loss": 0.4348,
|
95 |
+
"rewards/accuracies": 0.8812500238418579,
|
96 |
+
"rewards/chosen": -0.06764356046915054,
|
97 |
+
"rewards/margins": 1.6453561782836914,
|
98 |
+
"rewards/rejected": -1.712999701499939,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.18,
|
103 |
+
"grad_norm": 37.653606745673876,
|
104 |
+
"learning_rate": 4.896669632591651e-07,
|
105 |
+
"logits/chosen": -3.4180691242218018,
|
106 |
+
"logits/rejected": -3.3949356079101562,
|
107 |
+
"logps/chosen": -997.1550903320312,
|
108 |
+
"logps/rejected": -1486.9512939453125,
|
109 |
+
"loss": 0.4241,
|
110 |
+
"rewards/accuracies": 0.84375,
|
111 |
+
"rewards/chosen": -0.191396564245224,
|
112 |
+
"rewards/margins": 1.6561005115509033,
|
113 |
+
"rewards/rejected": -1.847496747970581,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.21,
|
118 |
+
"grad_norm": 27.62213668513971,
|
119 |
+
"learning_rate": 4.80713482008226e-07,
|
120 |
+
"logits/chosen": -3.2756118774414062,
|
121 |
+
"logits/rejected": -3.325742721557617,
|
122 |
+
"logps/chosen": -1002.0143432617188,
|
123 |
+
"logps/rejected": -1562.6756591796875,
|
124 |
+
"loss": 0.3597,
|
125 |
+
"rewards/accuracies": 0.8062499761581421,
|
126 |
+
"rewards/chosen": -0.11527639627456665,
|
127 |
+
"rewards/margins": 2.851576566696167,
|
128 |
+
"rewards/rejected": -2.966853380203247,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.24,
|
133 |
+
"grad_norm": 24.96995353325617,
|
134 |
+
"learning_rate": 4.691281286981619e-07,
|
135 |
+
"logits/chosen": -3.2543506622314453,
|
136 |
+
"logits/rejected": -3.2743306159973145,
|
137 |
+
"logps/chosen": -1047.9954833984375,
|
138 |
+
"logps/rejected": -1567.3741455078125,
|
139 |
+
"loss": 0.3576,
|
140 |
+
"rewards/accuracies": 0.84375,
|
141 |
+
"rewards/chosen": -0.11167576164007187,
|
142 |
+
"rewards/margins": 2.7660152912139893,
|
143 |
+
"rewards/rejected": -2.8776910305023193,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.28,
|
148 |
+
"grad_norm": 27.750313403051702,
|
149 |
+
"learning_rate": 4.550430636492389e-07,
|
150 |
+
"logits/chosen": -3.152367115020752,
|
151 |
+
"logits/rejected": -3.1291539669036865,
|
152 |
+
"logps/chosen": -958.4727783203125,
|
153 |
+
"logps/rejected": -1616.8697509765625,
|
154 |
+
"loss": 0.3037,
|
155 |
+
"rewards/accuracies": 0.887499988079071,
|
156 |
+
"rewards/chosen": -0.08375158160924911,
|
157 |
+
"rewards/margins": 3.5008788108825684,
|
158 |
+
"rewards/rejected": -3.5846304893493652,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.31,
|
163 |
+
"grad_norm": 30.508104431701753,
|
164 |
+
"learning_rate": 4.386189627302036e-07,
|
165 |
+
"logits/chosen": -3.1359643936157227,
|
166 |
+
"logits/rejected": -3.0350069999694824,
|
167 |
+
"logps/chosen": -1068.0445556640625,
|
168 |
+
"logps/rejected": -1752.9798583984375,
|
169 |
+
"loss": 0.2478,
|
170 |
+
"rewards/accuracies": 0.8999999761581421,
|
171 |
+
"rewards/chosen": -0.297347754240036,
|
172 |
+
"rewards/margins": 4.142968654632568,
|
173 |
+
"rewards/rejected": -4.440316200256348,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.31,
|
178 |
+
"eval_logits/chosen": -2.116163492202759,
|
179 |
+
"eval_logits/rejected": -2.9199953079223633,
|
180 |
+
"eval_logps/chosen": -214.01956176757812,
|
181 |
+
"eval_logps/rejected": -996.0294189453125,
|
182 |
+
"eval_loss": 0.03523317724466324,
|
183 |
+
"eval_rewards/accuracies": 1.0,
|
184 |
+
"eval_rewards/chosen": -0.1739114671945572,
|
185 |
+
"eval_rewards/margins": 4.2524919509887695,
|
186 |
+
"eval_rewards/rejected": -4.426403999328613,
|
187 |
+
"eval_runtime": 6.9945,
|
188 |
+
"eval_samples_per_second": 9.15,
|
189 |
+
"eval_steps_per_second": 0.286,
|
190 |
+
"step": 100
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.34,
|
194 |
+
"grad_norm": 30.142384194174287,
|
195 |
+
"learning_rate": 4.200431844427298e-07,
|
196 |
+
"logits/chosen": -3.1088919639587402,
|
197 |
+
"logits/rejected": -2.9363715648651123,
|
198 |
+
"logps/chosen": -956.9268798828125,
|
199 |
+
"logps/rejected": -1825.817138671875,
|
200 |
+
"loss": 0.2479,
|
201 |
+
"rewards/accuracies": 0.925000011920929,
|
202 |
+
"rewards/chosen": -0.4095672070980072,
|
203 |
+
"rewards/margins": 4.6759538650512695,
|
204 |
+
"rewards/rejected": -5.085520267486572,
|
205 |
+
"step": 110
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.37,
|
209 |
+
"grad_norm": 30.548015460707564,
|
210 |
+
"learning_rate": 3.9952763262280397e-07,
|
211 |
+
"logits/chosen": -3.0125510692596436,
|
212 |
+
"logits/rejected": -2.8323769569396973,
|
213 |
+
"logps/chosen": -974.1087646484375,
|
214 |
+
"logps/rejected": -1928.265380859375,
|
215 |
+
"loss": 0.2222,
|
216 |
+
"rewards/accuracies": 0.90625,
|
217 |
+
"rewards/chosen": -0.6024614572525024,
|
218 |
+
"rewards/margins": 5.620959281921387,
|
219 |
+
"rewards/rejected": -6.223421096801758,
|
220 |
+
"step": 120
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.4,
|
224 |
+
"grad_norm": 23.95507006913498,
|
225 |
+
"learning_rate": 3.7730633914035584e-07,
|
226 |
+
"logits/chosen": -2.9912257194519043,
|
227 |
+
"logits/rejected": -2.7818751335144043,
|
228 |
+
"logps/chosen": -1056.4798583984375,
|
229 |
+
"logps/rejected": -2160.14990234375,
|
230 |
+
"loss": 0.1988,
|
231 |
+
"rewards/accuracies": 0.949999988079071,
|
232 |
+
"rewards/chosen": -0.6903690099716187,
|
233 |
+
"rewards/margins": 7.284422397613525,
|
234 |
+
"rewards/rejected": -7.974791526794434,
|
235 |
+
"step": 130
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.43,
|
239 |
+
"grad_norm": 42.81780370407222,
|
240 |
+
"learning_rate": 3.5363279417257385e-07,
|
241 |
+
"logits/chosen": -2.8955721855163574,
|
242 |
+
"logits/rejected": -2.754878044128418,
|
243 |
+
"logps/chosen": -1038.2923583984375,
|
244 |
+
"logps/rejected": -1966.652587890625,
|
245 |
+
"loss": 0.2092,
|
246 |
+
"rewards/accuracies": 0.90625,
|
247 |
+
"rewards/chosen": -1.0339103937149048,
|
248 |
+
"rewards/margins": 5.819826126098633,
|
249 |
+
"rewards/rejected": -6.85373592376709,
|
250 |
+
"step": 140
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.46,
|
254 |
+
"grad_norm": 31.239186243610785,
|
255 |
+
"learning_rate": 3.287770545059052e-07,
|
256 |
+
"logits/chosen": -2.8968818187713623,
|
257 |
+
"logits/rejected": -2.668034076690674,
|
258 |
+
"logps/chosen": -1137.552978515625,
|
259 |
+
"logps/rejected": -2158.06298828125,
|
260 |
+
"loss": 0.1807,
|
261 |
+
"rewards/accuracies": 0.949999988079071,
|
262 |
+
"rewards/chosen": -1.3718111515045166,
|
263 |
+
"rewards/margins": 7.208723545074463,
|
264 |
+
"rewards/rejected": -8.580533981323242,
|
265 |
+
"step": 150
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.49,
|
269 |
+
"grad_norm": 30.783011951421607,
|
270 |
+
"learning_rate": 3.030226628538842e-07,
|
271 |
+
"logits/chosen": -2.7924959659576416,
|
272 |
+
"logits/rejected": -2.620363473892212,
|
273 |
+
"logps/chosen": -1211.665771484375,
|
274 |
+
"logps/rejected": -2208.79833984375,
|
275 |
+
"loss": 0.1596,
|
276 |
+
"rewards/accuracies": 0.949999988079071,
|
277 |
+
"rewards/chosen": -1.6732728481292725,
|
278 |
+
"rewards/margins": 7.373621463775635,
|
279 |
+
"rewards/rejected": -9.046895027160645,
|
280 |
+
"step": 160
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.52,
|
284 |
+
"grad_norm": 38.33986073767423,
|
285 |
+
"learning_rate": 2.7666341333378004e-07,
|
286 |
+
"logits/chosen": -2.7492575645446777,
|
287 |
+
"logits/rejected": -2.5758957862854004,
|
288 |
+
"logps/chosen": -1068.8045654296875,
|
289 |
+
"logps/rejected": -2013.82421875,
|
290 |
+
"loss": 0.1765,
|
291 |
+
"rewards/accuracies": 0.9624999761581421,
|
292 |
+
"rewards/chosen": -1.2596815824508667,
|
293 |
+
"rewards/margins": 6.303467750549316,
|
294 |
+
"rewards/rejected": -7.563148498535156,
|
295 |
+
"step": 170
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.55,
|
299 |
+
"grad_norm": 46.105813888725216,
|
300 |
+
"learning_rate": 2.5e-07,
|
301 |
+
"logits/chosen": -2.7488133907318115,
|
302 |
+
"logits/rejected": -2.492980480194092,
|
303 |
+
"logps/chosen": -1113.6063232421875,
|
304 |
+
"logps/rejected": -2361.96923828125,
|
305 |
+
"loss": 0.1225,
|
306 |
+
"rewards/accuracies": 0.956250011920929,
|
307 |
+
"rewards/chosen": -1.5648447275161743,
|
308 |
+
"rewards/margins": 8.788183212280273,
|
309 |
+
"rewards/rejected": -10.353028297424316,
|
310 |
+
"step": 180
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.58,
|
314 |
+
"grad_norm": 38.659892201318485,
|
315 |
+
"learning_rate": 2.2333658666621994e-07,
|
316 |
+
"logits/chosen": -2.716352939605713,
|
317 |
+
"logits/rejected": -2.4929823875427246,
|
318 |
+
"logps/chosen": -1151.252685546875,
|
319 |
+
"logps/rejected": -2195.82958984375,
|
320 |
+
"loss": 0.1587,
|
321 |
+
"rewards/accuracies": 0.956250011920929,
|
322 |
+
"rewards/chosen": -1.521728277206421,
|
323 |
+
"rewards/margins": 7.973954677581787,
|
324 |
+
"rewards/rejected": -9.495683670043945,
|
325 |
+
"step": 190
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.61,
|
329 |
+
"grad_norm": 34.038321670255556,
|
330 |
+
"learning_rate": 1.9697733714611587e-07,
|
331 |
+
"logits/chosen": -2.77030873298645,
|
332 |
+
"logits/rejected": -2.5207982063293457,
|
333 |
+
"logps/chosen": -1151.6956787109375,
|
334 |
+
"logps/rejected": -2134.08349609375,
|
335 |
+
"loss": 0.1385,
|
336 |
+
"rewards/accuracies": 0.956250011920929,
|
337 |
+
"rewards/chosen": -1.476732850074768,
|
338 |
+
"rewards/margins": 6.9633917808532715,
|
339 |
+
"rewards/rejected": -8.440125465393066,
|
340 |
+
"step": 200
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.61,
|
344 |
+
"eval_logits/chosen": -1.6287028789520264,
|
345 |
+
"eval_logits/rejected": -2.333620548248291,
|
346 |
+
"eval_logps/chosen": -230.22816467285156,
|
347 |
+
"eval_logps/rejected": -1373.3590087890625,
|
348 |
+
"eval_loss": 0.00411956338211894,
|
349 |
+
"eval_rewards/accuracies": 1.0,
|
350 |
+
"eval_rewards/chosen": -0.3359977602958679,
|
351 |
+
"eval_rewards/margins": 7.863701820373535,
|
352 |
+
"eval_rewards/rejected": -8.199699401855469,
|
353 |
+
"eval_runtime": 6.9561,
|
354 |
+
"eval_samples_per_second": 9.201,
|
355 |
+
"eval_steps_per_second": 0.288,
|
356 |
+
"step": 200
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.64,
|
360 |
+
"grad_norm": 25.859030241191462,
|
361 |
+
"learning_rate": 1.7122294549409482e-07,
|
362 |
+
"logits/chosen": -2.7445123195648193,
|
363 |
+
"logits/rejected": -2.477301597595215,
|
364 |
+
"logps/chosen": -1209.62158203125,
|
365 |
+
"logps/rejected": -2304.346435546875,
|
366 |
+
"loss": 0.1239,
|
367 |
+
"rewards/accuracies": 0.96875,
|
368 |
+
"rewards/chosen": -1.5678670406341553,
|
369 |
+
"rewards/margins": 8.935761451721191,
|
370 |
+
"rewards/rejected": -10.503628730773926,
|
371 |
+
"step": 210
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.67,
|
375 |
+
"grad_norm": 54.09588414480716,
|
376 |
+
"learning_rate": 1.4636720582742613e-07,
|
377 |
+
"logits/chosen": -2.6386165618896484,
|
378 |
+
"logits/rejected": -2.3536062240600586,
|
379 |
+
"logps/chosen": -1170.019287109375,
|
380 |
+
"logps/rejected": -2326.010986328125,
|
381 |
+
"loss": 0.1338,
|
382 |
+
"rewards/accuracies": 0.949999988079071,
|
383 |
+
"rewards/chosen": -1.9397300481796265,
|
384 |
+
"rewards/margins": 8.54932975769043,
|
385 |
+
"rewards/rejected": -10.489059448242188,
|
386 |
+
"step": 220
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.7,
|
390 |
+
"grad_norm": 35.229208104251256,
|
391 |
+
"learning_rate": 1.2269366085964422e-07,
|
392 |
+
"logits/chosen": -2.594449758529663,
|
393 |
+
"logits/rejected": -2.3216192722320557,
|
394 |
+
"logps/chosen": -1134.5150146484375,
|
395 |
+
"logps/rejected": -2302.87158203125,
|
396 |
+
"loss": 0.1241,
|
397 |
+
"rewards/accuracies": 0.956250011920929,
|
398 |
+
"rewards/chosen": -2.0043346881866455,
|
399 |
+
"rewards/margins": 8.11410903930664,
|
400 |
+
"rewards/rejected": -10.118444442749023,
|
401 |
+
"step": 230
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.73,
|
405 |
+
"grad_norm": 35.55573135898996,
|
406 |
+
"learning_rate": 1.00472367377196e-07,
|
407 |
+
"logits/chosen": -2.6050658226013184,
|
408 |
+
"logits/rejected": -2.3415164947509766,
|
409 |
+
"logps/chosen": -1212.265380859375,
|
410 |
+
"logps/rejected": -2304.11669921875,
|
411 |
+
"loss": 0.1046,
|
412 |
+
"rewards/accuracies": 0.956250011920929,
|
413 |
+
"rewards/chosen": -1.8809270858764648,
|
414 |
+
"rewards/margins": 8.250687599182129,
|
415 |
+
"rewards/rejected": -10.131612777709961,
|
416 |
+
"step": 240
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.76,
|
420 |
+
"grad_norm": 31.88590245463047,
|
421 |
+
"learning_rate": 7.99568155572701e-08,
|
422 |
+
"logits/chosen": -2.6101841926574707,
|
423 |
+
"logits/rejected": -2.0731587409973145,
|
424 |
+
"logps/chosen": -1139.8570556640625,
|
425 |
+
"logps/rejected": -2845.157470703125,
|
426 |
+
"loss": 0.0885,
|
427 |
+
"rewards/accuracies": 0.9624999761581421,
|
428 |
+
"rewards/chosen": -1.8957105875015259,
|
429 |
+
"rewards/margins": 13.620719909667969,
|
430 |
+
"rewards/rejected": -15.516430854797363,
|
431 |
+
"step": 250
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.8,
|
435 |
+
"grad_norm": 51.7448993159194,
|
436 |
+
"learning_rate": 6.13810372697964e-08,
|
437 |
+
"logits/chosen": -2.5568299293518066,
|
438 |
+
"logits/rejected": -2.152559757232666,
|
439 |
+
"logps/chosen": -1236.4830322265625,
|
440 |
+
"logps/rejected": -2579.609619140625,
|
441 |
+
"loss": 0.1114,
|
442 |
+
"rewards/accuracies": 0.956250011920929,
|
443 |
+
"rewards/chosen": -2.0548171997070312,
|
444 |
+
"rewards/margins": 11.762044906616211,
|
445 |
+
"rewards/rejected": -13.816862106323242,
|
446 |
+
"step": 260
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.83,
|
450 |
+
"grad_norm": 27.4784440806591,
|
451 |
+
"learning_rate": 4.4956936350761005e-08,
|
452 |
+
"logits/chosen": -2.598968267440796,
|
453 |
+
"logits/rejected": -2.217064619064331,
|
454 |
+
"logps/chosen": -1198.1903076171875,
|
455 |
+
"logps/rejected": -2465.025634765625,
|
456 |
+
"loss": 0.0966,
|
457 |
+
"rewards/accuracies": 0.9750000238418579,
|
458 |
+
"rewards/chosen": -2.0705723762512207,
|
459 |
+
"rewards/margins": 9.766708374023438,
|
460 |
+
"rewards/rejected": -11.837281227111816,
|
461 |
+
"step": 270
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.86,
|
465 |
+
"grad_norm": 35.99094553945511,
|
466 |
+
"learning_rate": 3.087187130183805e-08,
|
467 |
+
"logits/chosen": -2.51914119720459,
|
468 |
+
"logits/rejected": -2.214329481124878,
|
469 |
+
"logps/chosen": -1253.900146484375,
|
470 |
+
"logps/rejected": -2469.315185546875,
|
471 |
+
"loss": 0.1108,
|
472 |
+
"rewards/accuracies": 0.9750000238418579,
|
473 |
+
"rewards/chosen": -2.140868663787842,
|
474 |
+
"rewards/margins": 9.513227462768555,
|
475 |
+
"rewards/rejected": -11.654096603393555,
|
476 |
+
"step": 280
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.89,
|
480 |
+
"grad_norm": 62.565118319363144,
|
481 |
+
"learning_rate": 1.928651799177408e-08,
|
482 |
+
"logits/chosen": -2.5865471363067627,
|
483 |
+
"logits/rejected": -2.248619556427002,
|
484 |
+
"logps/chosen": -1134.03173828125,
|
485 |
+
"logps/rejected": -2389.395751953125,
|
486 |
+
"loss": 0.1085,
|
487 |
+
"rewards/accuracies": 0.96875,
|
488 |
+
"rewards/chosen": -2.002607822418213,
|
489 |
+
"rewards/margins": 8.705282211303711,
|
490 |
+
"rewards/rejected": -10.707889556884766,
|
491 |
+
"step": 290
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.92,
|
495 |
+
"grad_norm": 37.73877960542491,
|
496 |
+
"learning_rate": 1.0333036740834855e-08,
|
497 |
+
"logits/chosen": -2.552736520767212,
|
498 |
+
"logits/rejected": -2.2399215698242188,
|
499 |
+
"logps/chosen": -1204.527587890625,
|
500 |
+
"logps/rejected": -2376.899169921875,
|
501 |
+
"loss": 0.0899,
|
502 |
+
"rewards/accuracies": 0.9937499761581421,
|
503 |
+
"rewards/chosen": -2.1047260761260986,
|
504 |
+
"rewards/margins": 8.565834045410156,
|
505 |
+
"rewards/rejected": -10.670559883117676,
|
506 |
+
"step": 300
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.92,
|
510 |
+
"eval_logits/chosen": -1.3416023254394531,
|
511 |
+
"eval_logits/rejected": -2.055326461791992,
|
512 |
+
"eval_logps/chosen": -241.41647338867188,
|
513 |
+
"eval_logps/rejected": -1559.6263427734375,
|
514 |
+
"eval_loss": 0.0018886247416958213,
|
515 |
+
"eval_rewards/accuracies": 1.0,
|
516 |
+
"eval_rewards/chosen": -0.44788068532943726,
|
517 |
+
"eval_rewards/margins": 9.614492416381836,
|
518 |
+
"eval_rewards/rejected": -10.062373161315918,
|
519 |
+
"eval_runtime": 6.9591,
|
520 |
+
"eval_samples_per_second": 9.197,
|
521 |
+
"eval_steps_per_second": 0.287,
|
522 |
+
"step": 300
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.95,
|
526 |
+
"grad_norm": 29.76747785442669,
|
527 |
+
"learning_rate": 4.113564697361821e-09,
|
528 |
+
"logits/chosen": -2.521284580230713,
|
529 |
+
"logits/rejected": -2.1441428661346436,
|
530 |
+
"logps/chosen": -1216.38916015625,
|
531 |
+
"logps/rejected": -2597.3994140625,
|
532 |
+
"loss": 0.0804,
|
533 |
+
"rewards/accuracies": 0.9624999761581421,
|
534 |
+
"rewards/chosen": -1.9038699865341187,
|
535 |
+
"rewards/margins": 11.402238845825195,
|
536 |
+
"rewards/rejected": -13.306109428405762,
|
537 |
+
"step": 310
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.98,
|
541 |
+
"grad_norm": 32.64158882779933,
|
542 |
+
"learning_rate": 6.990507047049676e-10,
|
543 |
+
"logits/chosen": -2.489298105239868,
|
544 |
+
"logits/rejected": -2.159824848175049,
|
545 |
+
"logps/chosen": -1119.7908935546875,
|
546 |
+
"logps/rejected": -2548.427001953125,
|
547 |
+
"loss": 0.0939,
|
548 |
+
"rewards/accuracies": 0.9624999761581421,
|
549 |
+
"rewards/chosen": -2.2767906188964844,
|
550 |
+
"rewards/margins": 10.406248092651367,
|
551 |
+
"rewards/rejected": -12.683038711547852,
|
552 |
+
"step": 320
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 1.0,
|
556 |
+
"step": 327,
|
557 |
+
"total_flos": 0.0,
|
558 |
+
"train_loss": 0.23720380818807385,
|
559 |
+
"train_runtime": 5120.8034,
|
560 |
+
"train_samples_per_second": 4.087,
|
561 |
+
"train_steps_per_second": 0.064
|
562 |
+
}
|
563 |
+
],
|
564 |
+
"logging_steps": 10,
|
565 |
+
"max_steps": 327,
|
566 |
+
"num_input_tokens_seen": 0,
|
567 |
+
"num_train_epochs": 1,
|
568 |
+
"save_steps": 100,
|
569 |
+
"total_flos": 0.0,
|
570 |
+
"train_batch_size": 8,
|
571 |
+
"trial_name": null,
|
572 |
+
"trial_params": null
|
573 |
+
}
|