Model save
Browse files- README.md +60 -0
- all_results.json +9 -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 +9 -0
- trainer_state.json +1962 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: TTTXXX01/All_like-zephyr-7b-sft-full
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: IL_LSAll-7b-sft-full
|
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 |
+
# IL_LSAll-7b-sft-full
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [TTTXXX01/All_like-zephyr-7b-sft-full](https://huggingface.co/TTTXXX01/All_like-zephyr-7b-sft-full) on an unknown dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 6
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 4
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 48
|
45 |
+
- total_eval_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.41.2
|
58 |
+
- Pytorch 2.3.0+cu121
|
59 |
+
- Datasets 2.19.1
|
60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": -0.5441001898826946,
|
5 |
+
"train_runtime": 14755.3414,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.143,
|
8 |
+
"train_steps_per_second": 0.086
|
9 |
+
}
|
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": "4.41.2"
|
6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92e4e7ff805619be660550bc85c03e15504d238231757b91311e0124ec1a19cb
|
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:b7cac2f3f9a2d38e400c741b82314237447d7fd97fa9749fd1129b31606721b6
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a454211a6741359726e9744afd9081d62c55c372c0e8515fe0cf23538d482ff
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": -0.5441001898826946,
|
5 |
+
"train_runtime": 14755.3414,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.143,
|
8 |
+
"train_steps_per_second": 0.086
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1962 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1274,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0007849293563579278,
|
13 |
+
"grad_norm": 12.185681356731548,
|
14 |
+
"learning_rate": 3.90625e-09,
|
15 |
+
"logits/chosen": 5914.52099609375,
|
16 |
+
"logits/rejected": 2785.021484375,
|
17 |
+
"logps/chosen": -212.45889282226562,
|
18 |
+
"logps/rejected": -98.59669494628906,
|
19 |
+
"loss": -0.5,
|
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": 0.007849293563579277,
|
28 |
+
"grad_norm": 12.066996910892104,
|
29 |
+
"learning_rate": 3.9062499999999997e-08,
|
30 |
+
"logits/chosen": 4973.8837890625,
|
31 |
+
"logits/rejected": 4328.134765625,
|
32 |
+
"logps/chosen": -204.26583862304688,
|
33 |
+
"logps/rejected": -179.7384033203125,
|
34 |
+
"loss": -0.5002,
|
35 |
+
"rewards/accuracies": 0.5092592835426331,
|
36 |
+
"rewards/chosen": 0.01802830956876278,
|
37 |
+
"rewards/margins": 0.050810396671295166,
|
38 |
+
"rewards/rejected": -0.03278208523988724,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015698587127158554,
|
43 |
+
"grad_norm": 12.40225209927528,
|
44 |
+
"learning_rate": 7.812499999999999e-08,
|
45 |
+
"logits/chosen": 6083.919921875,
|
46 |
+
"logits/rejected": 4834.20361328125,
|
47 |
+
"logps/chosen": -217.2095489501953,
|
48 |
+
"logps/rejected": -196.75619506835938,
|
49 |
+
"loss": -0.4999,
|
50 |
+
"rewards/accuracies": 0.5416666269302368,
|
51 |
+
"rewards/chosen": 0.0016701116692274809,
|
52 |
+
"rewards/margins": 0.044297512620687485,
|
53 |
+
"rewards/rejected": -0.042627401649951935,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.023547880690737835,
|
58 |
+
"grad_norm": 10.962805442919553,
|
59 |
+
"learning_rate": 1.1718749999999999e-07,
|
60 |
+
"logits/chosen": 6084.23046875,
|
61 |
+
"logits/rejected": 5104.7353515625,
|
62 |
+
"logps/chosen": -250.57443237304688,
|
63 |
+
"logps/rejected": -209.3799285888672,
|
64 |
+
"loss": -0.5004,
|
65 |
+
"rewards/accuracies": 0.5833333730697632,
|
66 |
+
"rewards/chosen": -0.0020918771624565125,
|
67 |
+
"rewards/margins": 0.0802379846572876,
|
68 |
+
"rewards/rejected": -0.0823298767209053,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03139717425431711,
|
73 |
+
"grad_norm": 11.382523812855037,
|
74 |
+
"learning_rate": 1.5624999999999999e-07,
|
75 |
+
"logits/chosen": 5311.8466796875,
|
76 |
+
"logits/rejected": 4346.83544921875,
|
77 |
+
"logps/chosen": -211.97207641601562,
|
78 |
+
"logps/rejected": -181.73471069335938,
|
79 |
+
"loss": -0.5007,
|
80 |
+
"rewards/accuracies": 0.6083333492279053,
|
81 |
+
"rewards/chosen": 0.10717787593603134,
|
82 |
+
"rewards/margins": 0.15485556423664093,
|
83 |
+
"rewards/rejected": -0.04767768830060959,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.03924646781789639,
|
88 |
+
"grad_norm": 11.553897270025715,
|
89 |
+
"learning_rate": 1.9531249999999998e-07,
|
90 |
+
"logits/chosen": 6424.97900390625,
|
91 |
+
"logits/rejected": 5042.32275390625,
|
92 |
+
"logps/chosen": -265.31195068359375,
|
93 |
+
"logps/rejected": -206.8114776611328,
|
94 |
+
"loss": -0.5014,
|
95 |
+
"rewards/accuracies": 0.6833333373069763,
|
96 |
+
"rewards/chosen": 0.31464529037475586,
|
97 |
+
"rewards/margins": 0.4264959394931793,
|
98 |
+
"rewards/rejected": -0.11185060441493988,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04709576138147567,
|
103 |
+
"grad_norm": 11.145995154334138,
|
104 |
+
"learning_rate": 2.3437499999999998e-07,
|
105 |
+
"logits/chosen": 5484.03857421875,
|
106 |
+
"logits/rejected": 4559.96728515625,
|
107 |
+
"logps/chosen": -213.78250122070312,
|
108 |
+
"logps/rejected": -209.134765625,
|
109 |
+
"loss": -0.5026,
|
110 |
+
"rewards/accuracies": 0.6166666746139526,
|
111 |
+
"rewards/chosen": 0.22148728370666504,
|
112 |
+
"rewards/margins": 0.5561731457710266,
|
113 |
+
"rewards/rejected": -0.3346858322620392,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.054945054945054944,
|
118 |
+
"grad_norm": 10.594540156239251,
|
119 |
+
"learning_rate": 2.734375e-07,
|
120 |
+
"logits/chosen": 5194.1630859375,
|
121 |
+
"logits/rejected": 4918.46630859375,
|
122 |
+
"logps/chosen": -178.32403564453125,
|
123 |
+
"logps/rejected": -177.35049438476562,
|
124 |
+
"loss": -0.504,
|
125 |
+
"rewards/accuracies": 0.658333420753479,
|
126 |
+
"rewards/chosen": 0.15687695145606995,
|
127 |
+
"rewards/margins": 0.7756644487380981,
|
128 |
+
"rewards/rejected": -0.6187874674797058,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.06279434850863422,
|
133 |
+
"grad_norm": 10.745561073774455,
|
134 |
+
"learning_rate": 3.1249999999999997e-07,
|
135 |
+
"logits/chosen": 5773.69873046875,
|
136 |
+
"logits/rejected": 5269.18994140625,
|
137 |
+
"logps/chosen": -196.75479125976562,
|
138 |
+
"logps/rejected": -182.96005249023438,
|
139 |
+
"loss": -0.508,
|
140 |
+
"rewards/accuracies": 0.6416666507720947,
|
141 |
+
"rewards/chosen": -0.18619374930858612,
|
142 |
+
"rewards/margins": 1.1833512783050537,
|
143 |
+
"rewards/rejected": -1.3695449829101562,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0706436420722135,
|
148 |
+
"grad_norm": 11.77104917639987,
|
149 |
+
"learning_rate": 3.5156249999999997e-07,
|
150 |
+
"logits/chosen": 6040.1220703125,
|
151 |
+
"logits/rejected": 5181.70849609375,
|
152 |
+
"logps/chosen": -219.984619140625,
|
153 |
+
"logps/rejected": -190.1697235107422,
|
154 |
+
"loss": -0.514,
|
155 |
+
"rewards/accuracies": 0.76666659116745,
|
156 |
+
"rewards/chosen": -1.10239577293396,
|
157 |
+
"rewards/margins": 4.623492240905762,
|
158 |
+
"rewards/rejected": -5.725888252258301,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07849293563579278,
|
163 |
+
"grad_norm": 11.742155692581838,
|
164 |
+
"learning_rate": 3.9062499999999997e-07,
|
165 |
+
"logits/chosen": 5969.318359375,
|
166 |
+
"logits/rejected": 5747.93798828125,
|
167 |
+
"logps/chosen": -213.4771728515625,
|
168 |
+
"logps/rejected": -208.06533813476562,
|
169 |
+
"loss": -0.513,
|
170 |
+
"rewards/accuracies": 0.6916667222976685,
|
171 |
+
"rewards/chosen": -3.246516466140747,
|
172 |
+
"rewards/margins": 5.377118110656738,
|
173 |
+
"rewards/rejected": -8.623634338378906,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08634222919937205,
|
178 |
+
"grad_norm": 10.563011580121817,
|
179 |
+
"learning_rate": 4.2968749999999996e-07,
|
180 |
+
"logits/chosen": 6467.24267578125,
|
181 |
+
"logits/rejected": 5287.21533203125,
|
182 |
+
"logps/chosen": -187.99197387695312,
|
183 |
+
"logps/rejected": -189.99929809570312,
|
184 |
+
"loss": -0.52,
|
185 |
+
"rewards/accuracies": 0.6750000715255737,
|
186 |
+
"rewards/chosen": -4.877109050750732,
|
187 |
+
"rewards/margins": 6.129989147186279,
|
188 |
+
"rewards/rejected": -11.007098197937012,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.09419152276295134,
|
193 |
+
"grad_norm": 12.375994948676796,
|
194 |
+
"learning_rate": 4.6874999999999996e-07,
|
195 |
+
"logits/chosen": 6386.46826171875,
|
196 |
+
"logits/rejected": 5315.35107421875,
|
197 |
+
"logps/chosen": -209.4300079345703,
|
198 |
+
"logps/rejected": -211.3661651611328,
|
199 |
+
"loss": -0.5229,
|
200 |
+
"rewards/accuracies": 0.6583333611488342,
|
201 |
+
"rewards/chosen": -6.593257904052734,
|
202 |
+
"rewards/margins": 6.60781717300415,
|
203 |
+
"rewards/rejected": -13.201074600219727,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.10204081632653061,
|
208 |
+
"grad_norm": 10.769412676611394,
|
209 |
+
"learning_rate": 4.999962424962166e-07,
|
210 |
+
"logits/chosen": 6304.9599609375,
|
211 |
+
"logits/rejected": 5837.7001953125,
|
212 |
+
"logps/chosen": -214.27236938476562,
|
213 |
+
"logps/rejected": -210.44900512695312,
|
214 |
+
"loss": -0.5258,
|
215 |
+
"rewards/accuracies": 0.7166666984558105,
|
216 |
+
"rewards/chosen": -4.4638848304748535,
|
217 |
+
"rewards/margins": 8.34054946899414,
|
218 |
+
"rewards/rejected": -12.804433822631836,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.10989010989010989,
|
223 |
+
"grad_norm": 12.295935556547667,
|
224 |
+
"learning_rate": 4.998647417232375e-07,
|
225 |
+
"logits/chosen": 6149.7275390625,
|
226 |
+
"logits/rejected": 5416.37841796875,
|
227 |
+
"logps/chosen": -192.96670532226562,
|
228 |
+
"logps/rejected": -192.98519897460938,
|
229 |
+
"loss": -0.5265,
|
230 |
+
"rewards/accuracies": 0.6416666507720947,
|
231 |
+
"rewards/chosen": -7.299239158630371,
|
232 |
+
"rewards/margins": 8.094062805175781,
|
233 |
+
"rewards/rejected": -15.393301010131836,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.11773940345368916,
|
238 |
+
"grad_norm": 14.539764643796898,
|
239 |
+
"learning_rate": 4.995454786965036e-07,
|
240 |
+
"logits/chosen": 6326.96337890625,
|
241 |
+
"logits/rejected": 5289.18701171875,
|
242 |
+
"logps/chosen": -207.80078125,
|
243 |
+
"logps/rejected": -189.2040252685547,
|
244 |
+
"loss": -0.5306,
|
245 |
+
"rewards/accuracies": 0.7166667580604553,
|
246 |
+
"rewards/chosen": -6.116393089294434,
|
247 |
+
"rewards/margins": 10.78992748260498,
|
248 |
+
"rewards/rejected": -16.906322479248047,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.12558869701726844,
|
253 |
+
"grad_norm": 11.207640568489824,
|
254 |
+
"learning_rate": 4.990386933279972e-07,
|
255 |
+
"logits/chosen": 6298.8232421875,
|
256 |
+
"logits/rejected": 5626.849609375,
|
257 |
+
"logps/chosen": -205.1914520263672,
|
258 |
+
"logps/rejected": -215.720703125,
|
259 |
+
"loss": -0.5322,
|
260 |
+
"rewards/accuracies": 0.6916667222976685,
|
261 |
+
"rewards/chosen": -7.663259983062744,
|
262 |
+
"rewards/margins": 10.99985408782959,
|
263 |
+
"rewards/rejected": -18.66311264038086,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.13343799058084774,
|
268 |
+
"grad_norm": 11.148522573070823,
|
269 |
+
"learning_rate": 4.983447664444096e-07,
|
270 |
+
"logits/chosen": 6521.455078125,
|
271 |
+
"logits/rejected": 5816.02978515625,
|
272 |
+
"logps/chosen": -216.96273803710938,
|
273 |
+
"logps/rejected": -212.0134735107422,
|
274 |
+
"loss": -0.5304,
|
275 |
+
"rewards/accuracies": 0.6500000357627869,
|
276 |
+
"rewards/chosen": -7.342079162597656,
|
277 |
+
"rewards/margins": 8.349851608276367,
|
278 |
+
"rewards/rejected": -15.691930770874023,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.141287284144427,
|
283 |
+
"grad_norm": 11.676516090807922,
|
284 |
+
"learning_rate": 4.97464219500968e-07,
|
285 |
+
"logits/chosen": 5680.8671875,
|
286 |
+
"logits/rejected": 4962.62646484375,
|
287 |
+
"logps/chosen": -195.90188598632812,
|
288 |
+
"logps/rejected": -194.9904327392578,
|
289 |
+
"loss": -0.5311,
|
290 |
+
"rewards/accuracies": 0.6666666865348816,
|
291 |
+
"rewards/chosen": -7.374118804931641,
|
292 |
+
"rewards/margins": 9.45504379272461,
|
293 |
+
"rewards/rejected": -16.829160690307617,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.14913657770800628,
|
298 |
+
"grad_norm": 11.938372210953599,
|
299 |
+
"learning_rate": 4.963977141895843e-07,
|
300 |
+
"logits/chosen": 5801.43798828125,
|
301 |
+
"logits/rejected": 4985.052734375,
|
302 |
+
"logps/chosen": -210.7730255126953,
|
303 |
+
"logps/rejected": -217.6445770263672,
|
304 |
+
"loss": -0.5382,
|
305 |
+
"rewards/accuracies": 0.7416667342185974,
|
306 |
+
"rewards/chosen": -7.014087677001953,
|
307 |
+
"rewards/margins": 19.390995025634766,
|
308 |
+
"rewards/rejected": -26.405080795288086,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.15698587127158556,
|
313 |
+
"grad_norm": 13.331326878281788,
|
314 |
+
"learning_rate": 4.951460519416227e-07,
|
315 |
+
"logits/chosen": 5768.001953125,
|
316 |
+
"logits/rejected": 5333.7431640625,
|
317 |
+
"logps/chosen": -189.96151733398438,
|
318 |
+
"logps/rejected": -217.80111694335938,
|
319 |
+
"loss": -0.5373,
|
320 |
+
"rewards/accuracies": 0.7250000238418579,
|
321 |
+
"rewards/chosen": -7.417243957519531,
|
322 |
+
"rewards/margins": 13.712860107421875,
|
323 |
+
"rewards/rejected": -21.130104064941406,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16483516483516483,
|
328 |
+
"grad_norm": 12.088213484190312,
|
329 |
+
"learning_rate": 4.937101733256606e-07,
|
330 |
+
"logits/chosen": 5204.8251953125,
|
331 |
+
"logits/rejected": 4647.6201171875,
|
332 |
+
"logps/chosen": -165.14723205566406,
|
333 |
+
"logps/rejected": -181.01913452148438,
|
334 |
+
"loss": -0.5388,
|
335 |
+
"rewards/accuracies": 0.6416667699813843,
|
336 |
+
"rewards/chosen": -11.233977317810059,
|
337 |
+
"rewards/margins": 12.604203224182129,
|
338 |
+
"rewards/rejected": -23.83818244934082,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1726844583987441,
|
343 |
+
"grad_norm": 12.084984368162589,
|
344 |
+
"learning_rate": 4.920911573406924e-07,
|
345 |
+
"logits/chosen": 6338.34814453125,
|
346 |
+
"logits/rejected": 5404.54736328125,
|
347 |
+
"logps/chosen": -202.90597534179688,
|
348 |
+
"logps/rejected": -184.44300842285156,
|
349 |
+
"loss": -0.5367,
|
350 |
+
"rewards/accuracies": 0.7083333134651184,
|
351 |
+
"rewards/chosen": -6.569375514984131,
|
352 |
+
"rewards/margins": 13.876904487609863,
|
353 |
+
"rewards/rejected": -20.446279525756836,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.18053375196232338,
|
358 |
+
"grad_norm": 12.304556304864667,
|
359 |
+
"learning_rate": 4.902902206053098e-07,
|
360 |
+
"logits/chosen": 5835.81005859375,
|
361 |
+
"logits/rejected": 5272.3916015625,
|
362 |
+
"logps/chosen": -195.09201049804688,
|
363 |
+
"logps/rejected": -200.99949645996094,
|
364 |
+
"loss": -0.5379,
|
365 |
+
"rewards/accuracies": 0.7250000238418579,
|
366 |
+
"rewards/chosen": -7.753264427185059,
|
367 |
+
"rewards/margins": 13.478750228881836,
|
368 |
+
"rewards/rejected": -21.232013702392578,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.18838304552590268,
|
373 |
+
"grad_norm": 11.858671948962757,
|
374 |
+
"learning_rate": 4.883087164434672e-07,
|
375 |
+
"logits/chosen": 5319.9375,
|
376 |
+
"logits/rejected": 4253.84716796875,
|
377 |
+
"logps/chosen": -176.44406127929688,
|
378 |
+
"logps/rejected": -179.34446716308594,
|
379 |
+
"loss": -0.5415,
|
380 |
+
"rewards/accuracies": 0.7166666388511658,
|
381 |
+
"rewards/chosen": -8.815033912658691,
|
382 |
+
"rewards/margins": 15.839999198913574,
|
383 |
+
"rewards/rejected": -24.655033111572266,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.19623233908948196,
|
388 |
+
"grad_norm": 12.860987570352677,
|
389 |
+
"learning_rate": 4.861481338675183e-07,
|
390 |
+
"logits/chosen": 6238.8427734375,
|
391 |
+
"logits/rejected": 5548.5595703125,
|
392 |
+
"logps/chosen": -178.11911010742188,
|
393 |
+
"logps/rejected": -211.85556030273438,
|
394 |
+
"loss": -0.5352,
|
395 |
+
"rewards/accuracies": 0.6999999284744263,
|
396 |
+
"rewards/chosen": -10.975238800048828,
|
397 |
+
"rewards/margins": 16.373638153076172,
|
398 |
+
"rewards/rejected": -27.348876953125,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.20408163265306123,
|
403 |
+
"grad_norm": 13.77676710172865,
|
404 |
+
"learning_rate": 4.838100964592904e-07,
|
405 |
+
"logits/chosen": 6332.92919921875,
|
406 |
+
"logits/rejected": 5130.1845703125,
|
407 |
+
"logps/chosen": -207.98056030273438,
|
408 |
+
"logps/rejected": -187.11793518066406,
|
409 |
+
"loss": -0.5338,
|
410 |
+
"rewards/accuracies": 0.7333333492279053,
|
411 |
+
"rewards/chosen": -8.262109756469727,
|
412 |
+
"rewards/margins": 12.631866455078125,
|
413 |
+
"rewards/rejected": -20.89397430419922,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2119309262166405,
|
418 |
+
"grad_norm": 12.370375575916855,
|
419 |
+
"learning_rate": 4.812963611500339e-07,
|
420 |
+
"logits/chosen": 6204.505859375,
|
421 |
+
"logits/rejected": 6015.0693359375,
|
422 |
+
"logps/chosen": -207.0754852294922,
|
423 |
+
"logps/rejected": -211.184326171875,
|
424 |
+
"loss": -0.5453,
|
425 |
+
"rewards/accuracies": 0.6166666746139526,
|
426 |
+
"rewards/chosen": -10.319671630859375,
|
427 |
+
"rewards/margins": 12.235608100891113,
|
428 |
+
"rewards/rejected": -22.55527687072754,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21978021978021978,
|
433 |
+
"grad_norm": 13.333747180731516,
|
434 |
+
"learning_rate": 4.786088169001671e-07,
|
435 |
+
"logits/chosen": 5350.53857421875,
|
436 |
+
"logits/rejected": 4659.34033203125,
|
437 |
+
"logps/chosen": -170.44593811035156,
|
438 |
+
"logps/rejected": -196.863525390625,
|
439 |
+
"loss": -0.5446,
|
440 |
+
"rewards/accuracies": 0.7666667699813843,
|
441 |
+
"rewards/chosen": -7.295041084289551,
|
442 |
+
"rewards/margins": 20.267045974731445,
|
443 |
+
"rewards/rejected": -27.562082290649414,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.22762951334379905,
|
448 |
+
"grad_norm": 13.96823158237144,
|
449 |
+
"learning_rate": 4.7574948327980567e-07,
|
450 |
+
"logits/chosen": 7450.26806640625,
|
451 |
+
"logits/rejected": 5533.2412109375,
|
452 |
+
"logps/chosen": -243.9921112060547,
|
453 |
+
"logps/rejected": -212.14205932617188,
|
454 |
+
"loss": -0.5499,
|
455 |
+
"rewards/accuracies": 0.7333333492279053,
|
456 |
+
"rewards/chosen": -6.9636712074279785,
|
457 |
+
"rewards/margins": 22.662681579589844,
|
458 |
+
"rewards/rejected": -29.626354217529297,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.23547880690737832,
|
463 |
+
"grad_norm": 12.558950857731215,
|
464 |
+
"learning_rate": 4.727205089511466e-07,
|
465 |
+
"logits/chosen": 5432.5947265625,
|
466 |
+
"logits/rejected": 5410.603515625,
|
467 |
+
"logps/chosen": -177.76187133789062,
|
468 |
+
"logps/rejected": -198.78128051757812,
|
469 |
+
"loss": -0.5399,
|
470 |
+
"rewards/accuracies": 0.6666666865348816,
|
471 |
+
"rewards/chosen": -10.289421081542969,
|
472 |
+
"rewards/margins": 18.305423736572266,
|
473 |
+
"rewards/rejected": -28.5948429107666,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.24332810047095763,
|
478 |
+
"grad_norm": 14.201922916787394,
|
479 |
+
"learning_rate": 4.6952417005384247e-07,
|
480 |
+
"logits/chosen": 6099.38818359375,
|
481 |
+
"logits/rejected": 5433.0458984375,
|
482 |
+
"logps/chosen": -183.69717407226562,
|
483 |
+
"logps/rejected": -196.2397918701172,
|
484 |
+
"loss": -0.54,
|
485 |
+
"rewards/accuracies": 0.75,
|
486 |
+
"rewards/chosen": -6.116464614868164,
|
487 |
+
"rewards/margins": 14.655021667480469,
|
488 |
+
"rewards/rejected": -20.771484375,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.25117739403453687,
|
493 |
+
"grad_norm": 13.369021747374136,
|
494 |
+
"learning_rate": 4.661628684945851e-07,
|
495 |
+
"logits/chosen": 6102.36767578125,
|
496 |
+
"logits/rejected": 5295.1162109375,
|
497 |
+
"logps/chosen": -207.60568237304688,
|
498 |
+
"logps/rejected": -228.161865234375,
|
499 |
+
"loss": -0.541,
|
500 |
+
"rewards/accuracies": 0.6583333611488342,
|
501 |
+
"rewards/chosen": -6.5486907958984375,
|
502 |
+
"rewards/margins": 19.595294952392578,
|
503 |
+
"rewards/rejected": -26.14398765563965,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.25902668759811615,
|
508 |
+
"grad_norm": 13.537470631829464,
|
509 |
+
"learning_rate": 4.626391301421782e-07,
|
510 |
+
"logits/chosen": 5880.90625,
|
511 |
+
"logits/rejected": 5355.83837890625,
|
512 |
+
"logps/chosen": -203.02908325195312,
|
513 |
+
"logps/rejected": -200.60757446289062,
|
514 |
+
"loss": -0.5351,
|
515 |
+
"rewards/accuracies": 0.699999988079071,
|
516 |
+
"rewards/chosen": -8.575886726379395,
|
517 |
+
"rewards/margins": 14.708877563476562,
|
518 |
+
"rewards/rejected": -23.28476333618164,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.2668759811616955,
|
523 |
+
"grad_norm": 12.219470457302588,
|
524 |
+
"learning_rate": 4.5895560292945996e-07,
|
525 |
+
"logits/chosen": 6148.09423828125,
|
526 |
+
"logits/rejected": 6284.05419921875,
|
527 |
+
"logps/chosen": -199.61947631835938,
|
528 |
+
"logps/rejected": -241.6748504638672,
|
529 |
+
"loss": -0.5415,
|
530 |
+
"rewards/accuracies": 0.7250000238418579,
|
531 |
+
"rewards/chosen": -5.761203289031982,
|
532 |
+
"rewards/margins": 15.546130180358887,
|
533 |
+
"rewards/rejected": -21.30733299255371,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.27472527472527475,
|
538 |
+
"grad_norm": 14.312166127291615,
|
539 |
+
"learning_rate": 4.5511505486349865e-07,
|
540 |
+
"logits/chosen": 6496.5771484375,
|
541 |
+
"logits/rejected": 5905.1181640625,
|
542 |
+
"logps/chosen": -199.84910583496094,
|
543 |
+
"logps/rejected": -234.73599243164062,
|
544 |
+
"loss": -0.548,
|
545 |
+
"rewards/accuracies": 0.7833333611488342,
|
546 |
+
"rewards/chosen": -5.023402214050293,
|
547 |
+
"rewards/margins": 22.890575408935547,
|
548 |
+
"rewards/rejected": -27.913976669311523,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.282574568288854,
|
553 |
+
"grad_norm": 14.088746309162621,
|
554 |
+
"learning_rate": 4.5112037194555876e-07,
|
555 |
+
"logits/chosen": 6001.92578125,
|
556 |
+
"logits/rejected": 5925.07861328125,
|
557 |
+
"logps/chosen": -190.96304321289062,
|
558 |
+
"logps/rejected": -233.9935760498047,
|
559 |
+
"loss": -0.543,
|
560 |
+
"rewards/accuracies": 0.7333332896232605,
|
561 |
+
"rewards/chosen": -13.039606094360352,
|
562 |
+
"rewards/margins": 21.672157287597656,
|
563 |
+
"rewards/rejected": -34.711761474609375,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2904238618524333,
|
568 |
+
"grad_norm": 14.758996475483764,
|
569 |
+
"learning_rate": 4.4697455600239863e-07,
|
570 |
+
"logits/chosen": 5456.59375,
|
571 |
+
"logits/rejected": 5158.630859375,
|
572 |
+
"logps/chosen": -194.8301544189453,
|
573 |
+
"logps/rejected": -197.39712524414062,
|
574 |
+
"loss": -0.5361,
|
575 |
+
"rewards/accuracies": 0.6916666626930237,
|
576 |
+
"rewards/chosen": -10.408088684082031,
|
577 |
+
"rewards/margins": 18.91793441772461,
|
578 |
+
"rewards/rejected": -29.326025009155273,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.29827315541601257,
|
583 |
+
"grad_norm": 14.815915118950619,
|
584 |
+
"learning_rate": 4.426807224305315e-07,
|
585 |
+
"logits/chosen": 6503.11962890625,
|
586 |
+
"logits/rejected": 5408.39306640625,
|
587 |
+
"logps/chosen": -235.3462677001953,
|
588 |
+
"logps/rejected": -212.32003784179688,
|
589 |
+
"loss": -0.546,
|
590 |
+
"rewards/accuracies": 0.7416666746139526,
|
591 |
+
"rewards/chosen": -7.005249977111816,
|
592 |
+
"rewards/margins": 22.305225372314453,
|
593 |
+
"rewards/rejected": -29.310476303100586,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.30612244897959184,
|
598 |
+
"grad_norm": 13.698299560417563,
|
599 |
+
"learning_rate": 4.3824209785514326e-07,
|
600 |
+
"logits/chosen": 6644.3505859375,
|
601 |
+
"logits/rejected": 5104.09521484375,
|
602 |
+
"logps/chosen": -221.2438201904297,
|
603 |
+
"logps/rejected": -218.32943725585938,
|
604 |
+
"loss": -0.5524,
|
605 |
+
"rewards/accuracies": 0.7666667103767395,
|
606 |
+
"rewards/chosen": -5.750358581542969,
|
607 |
+
"rewards/margins": 32.725975036621094,
|
608 |
+
"rewards/rejected": -38.47633743286133,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3139717425431711,
|
613 |
+
"grad_norm": 13.596298740826661,
|
614 |
+
"learning_rate": 4.3366201770542687e-07,
|
615 |
+
"logits/chosen": 5721.71435546875,
|
616 |
+
"logits/rejected": 5618.02978515625,
|
617 |
+
"logps/chosen": -200.8018341064453,
|
618 |
+
"logps/rejected": -226.2516632080078,
|
619 |
+
"loss": -0.5414,
|
620 |
+
"rewards/accuracies": 0.7416666746139526,
|
621 |
+
"rewards/chosen": -10.013228416442871,
|
622 |
+
"rewards/margins": 27.498947143554688,
|
623 |
+
"rewards/rejected": -37.51217269897461,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.3218210361067504,
|
628 |
+
"grad_norm": 21.60392631215127,
|
629 |
+
"learning_rate": 4.2894392370815567e-07,
|
630 |
+
"logits/chosen": 6170.86328125,
|
631 |
+
"logits/rejected": 5508.14208984375,
|
632 |
+
"logps/chosen": -222.9990234375,
|
633 |
+
"logps/rejected": -256.97540283203125,
|
634 |
+
"loss": -0.5648,
|
635 |
+
"rewards/accuracies": 0.7416666746139526,
|
636 |
+
"rewards/chosen": -10.512117385864258,
|
637 |
+
"rewards/margins": 38.01092529296875,
|
638 |
+
"rewards/rejected": -48.52304458618164,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.32967032967032966,
|
643 |
+
"grad_norm": 19.0790120070253,
|
644 |
+
"learning_rate": 4.2409136130137845e-07,
|
645 |
+
"logits/chosen": 5799.7158203125,
|
646 |
+
"logits/rejected": 5273.5751953125,
|
647 |
+
"logps/chosen": -217.6487274169922,
|
648 |
+
"logps/rejected": -227.30331420898438,
|
649 |
+
"loss": -0.5479,
|
650 |
+
"rewards/accuracies": 0.7333333492279053,
|
651 |
+
"rewards/chosen": -13.61878776550293,
|
652 |
+
"rewards/margins": 32.44309997558594,
|
653 |
+
"rewards/rejected": -46.0618896484375,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.33751962323390894,
|
658 |
+
"grad_norm": 14.50200341648645,
|
659 |
+
"learning_rate": 4.1910797697018017e-07,
|
660 |
+
"logits/chosen": 5581.63720703125,
|
661 |
+
"logits/rejected": 4674.400390625,
|
662 |
+
"logps/chosen": -190.4328155517578,
|
663 |
+
"logps/rejected": -197.7171173095703,
|
664 |
+
"loss": -0.5513,
|
665 |
+
"rewards/accuracies": 0.7749999761581421,
|
666 |
+
"rewards/chosen": -10.687819480895996,
|
667 |
+
"rewards/margins": 25.796178817749023,
|
668 |
+
"rewards/rejected": -36.48400115966797,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3453689167974882,
|
673 |
+
"grad_norm": 14.931746475331163,
|
674 |
+
"learning_rate": 4.1399751550651084e-07,
|
675 |
+
"logits/chosen": 5941.59814453125,
|
676 |
+
"logits/rejected": 5881.9892578125,
|
677 |
+
"logps/chosen": -192.48472595214844,
|
678 |
+
"logps/rejected": -226.8599853515625,
|
679 |
+
"loss": -0.5495,
|
680 |
+
"rewards/accuracies": 0.7416666746139526,
|
681 |
+
"rewards/chosen": -10.09138011932373,
|
682 |
+
"rewards/margins": 25.08499526977539,
|
683 |
+
"rewards/rejected": -35.17637634277344,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3532182103610675,
|
688 |
+
"grad_norm": 14.476601288378774,
|
689 |
+
"learning_rate": 4.087638171951401e-07,
|
690 |
+
"logits/chosen": 6844.02978515625,
|
691 |
+
"logits/rejected": 4965.66552734375,
|
692 |
+
"logps/chosen": -215.19436645507812,
|
693 |
+
"logps/rejected": -201.01358032226562,
|
694 |
+
"loss": -0.5446,
|
695 |
+
"rewards/accuracies": 0.75,
|
696 |
+
"rewards/chosen": -6.425619602203369,
|
697 |
+
"rewards/margins": 31.595306396484375,
|
698 |
+
"rewards/rejected": -38.02092361450195,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.36106750392464676,
|
703 |
+
"grad_norm": 12.493477466659453,
|
704 |
+
"learning_rate": 4.034108149278543e-07,
|
705 |
+
"logits/chosen": 7059.74365234375,
|
706 |
+
"logits/rejected": 5534.33447265625,
|
707 |
+
"logps/chosen": -259.2933654785156,
|
708 |
+
"logps/rejected": -219.4051971435547,
|
709 |
+
"loss": -0.549,
|
710 |
+
"rewards/accuracies": 0.7333333492279053,
|
711 |
+
"rewards/chosen": -8.861111640930176,
|
712 |
+
"rewards/margins": 20.336048126220703,
|
713 |
+
"rewards/rejected": -29.197154998779297,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.36891679748822603,
|
718 |
+
"grad_norm": 14.398041055949756,
|
719 |
+
"learning_rate": 3.979425312480629e-07,
|
720 |
+
"logits/chosen": 6101.0927734375,
|
721 |
+
"logits/rejected": 5368.69140625,
|
722 |
+
"logps/chosen": -222.6365203857422,
|
723 |
+
"logps/rejected": -240.66592407226562,
|
724 |
+
"loss": -0.5474,
|
725 |
+
"rewards/accuracies": 0.7583333253860474,
|
726 |
+
"rewards/chosen": -10.3717622756958,
|
727 |
+
"rewards/margins": 27.727893829345703,
|
728 |
+
"rewards/rejected": -38.09965515136719,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.37676609105180536,
|
733 |
+
"grad_norm": 13.515928817603175,
|
734 |
+
"learning_rate": 3.923630753280357e-07,
|
735 |
+
"logits/chosen": 6586.9609375,
|
736 |
+
"logits/rejected": 5732.6962890625,
|
737 |
+
"logps/chosen": -218.5810089111328,
|
738 |
+
"logps/rejected": -215.1974334716797,
|
739 |
+
"loss": -0.547,
|
740 |
+
"rewards/accuracies": 0.800000011920929,
|
741 |
+
"rewards/chosen": -11.185822486877441,
|
742 |
+
"rewards/margins": 29.6158390045166,
|
743 |
+
"rewards/rejected": -40.801658630371094,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.38461538461538464,
|
748 |
+
"grad_norm": 17.390744031191396,
|
749 |
+
"learning_rate": 3.866766398810424e-07,
|
750 |
+
"logits/chosen": 6174.2861328125,
|
751 |
+
"logits/rejected": 5929.84326171875,
|
752 |
+
"logps/chosen": -180.99270629882812,
|
753 |
+
"logps/rejected": -239.779541015625,
|
754 |
+
"loss": -0.5608,
|
755 |
+
"rewards/accuracies": 0.7749999761581421,
|
756 |
+
"rewards/chosen": -4.384220123291016,
|
757 |
+
"rewards/margins": 33.371002197265625,
|
758 |
+
"rewards/rejected": -37.75522232055664,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3924646781789639,
|
763 |
+
"grad_norm": 20.545482385498747,
|
764 |
+
"learning_rate": 3.8088749801071496e-07,
|
765 |
+
"logits/chosen": 6699.80078125,
|
766 |
+
"logits/rejected": 5181.845703125,
|
767 |
+
"logps/chosen": -241.4040985107422,
|
768 |
+
"logps/rejected": -258.91363525390625,
|
769 |
+
"loss": -0.5433,
|
770 |
+
"rewards/accuracies": 0.73333340883255,
|
771 |
+
"rewards/chosen": -19.450458526611328,
|
772 |
+
"rewards/margins": 36.94696807861328,
|
773 |
+
"rewards/rejected": -56.397430419921875,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4003139717425432,
|
778 |
+
"grad_norm": 15.348191714605942,
|
779 |
+
"learning_rate": 3.75e-07,
|
780 |
+
"logits/chosen": 5331.91162109375,
|
781 |
+
"logits/rejected": 4749.47265625,
|
782 |
+
"logps/chosen": -195.63552856445312,
|
783 |
+
"logps/rejected": -202.39199829101562,
|
784 |
+
"loss": -0.5533,
|
785 |
+
"rewards/accuracies": 0.824999988079071,
|
786 |
+
"rewards/chosen": -6.15253210067749,
|
787 |
+
"rewards/margins": 29.87417221069336,
|
788 |
+
"rewards/rejected": -36.02670669555664,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.40816326530612246,
|
793 |
+
"grad_norm": 17.179270022544692,
|
794 |
+
"learning_rate": 3.6901857004211443e-07,
|
795 |
+
"logits/chosen": 5678.765625,
|
796 |
+
"logits/rejected": 5301.3427734375,
|
797 |
+
"logps/chosen": -209.762939453125,
|
798 |
+
"logps/rejected": -227.5038604736328,
|
799 |
+
"loss": -0.5304,
|
800 |
+
"rewards/accuracies": 0.6833332777023315,
|
801 |
+
"rewards/chosen": -11.296924591064453,
|
802 |
+
"rewards/margins": 20.41892433166504,
|
803 |
+
"rewards/rejected": -31.71584701538086,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.41601255886970173,
|
808 |
+
"grad_norm": 12.968043224968394,
|
809 |
+
"learning_rate": 3.6294770291596076e-07,
|
810 |
+
"logits/chosen": 6412.17138671875,
|
811 |
+
"logits/rejected": 5298.6142578125,
|
812 |
+
"logps/chosen": -220.1424102783203,
|
813 |
+
"logps/rejected": -227.05404663085938,
|
814 |
+
"loss": -0.5559,
|
815 |
+
"rewards/accuracies": 0.6666666269302368,
|
816 |
+
"rewards/chosen": -7.219654083251953,
|
817 |
+
"rewards/margins": 21.074071884155273,
|
818 |
+
"rewards/rejected": -28.29372787475586,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.423861852433281,
|
823 |
+
"grad_norm": 21.703435125964788,
|
824 |
+
"learning_rate": 3.5679196060850034e-07,
|
825 |
+
"logits/chosen": 6090.72607421875,
|
826 |
+
"logits/rejected": 5481.96728515625,
|
827 |
+
"logps/chosen": -220.23135375976562,
|
828 |
+
"logps/rejected": -224.384521484375,
|
829 |
+
"loss": -0.5486,
|
830 |
+
"rewards/accuracies": 0.7500000596046448,
|
831 |
+
"rewards/chosen": -9.41352653503418,
|
832 |
+
"rewards/margins": 26.732208251953125,
|
833 |
+
"rewards/rejected": -36.14573669433594,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.4317111459968603,
|
838 |
+
"grad_norm": 37.52988937079133,
|
839 |
+
"learning_rate": 3.505559688866229e-07,
|
840 |
+
"logits/chosen": 5888.26220703125,
|
841 |
+
"logits/rejected": 5514.62841796875,
|
842 |
+
"logps/chosen": -225.4257049560547,
|
843 |
+
"logps/rejected": -265.7478332519531,
|
844 |
+
"loss": -0.5531,
|
845 |
+
"rewards/accuracies": 0.7166666984558105,
|
846 |
+
"rewards/chosen": -10.685269355773926,
|
847 |
+
"rewards/margins": 29.998464584350586,
|
848 |
+
"rewards/rejected": -40.683738708496094,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.43956043956043955,
|
853 |
+
"grad_norm": 16.990632916112638,
|
854 |
+
"learning_rate": 3.4424441382108826e-07,
|
855 |
+
"logits/chosen": 5950.71142578125,
|
856 |
+
"logits/rejected": 5591.7197265625,
|
857 |
+
"logps/chosen": -216.213134765625,
|
858 |
+
"logps/rejected": -236.20703125,
|
859 |
+
"loss": -0.544,
|
860 |
+
"rewards/accuracies": 0.7083333730697632,
|
861 |
+
"rewards/chosen": -12.937848091125488,
|
862 |
+
"rewards/margins": 30.05996322631836,
|
863 |
+
"rewards/rejected": -42.99781036376953,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.4474097331240188,
|
868 |
+
"grad_norm": 21.823795774201802,
|
869 |
+
"learning_rate": 3.378620382651523e-07,
|
870 |
+
"logits/chosen": 6279.9443359375,
|
871 |
+
"logits/rejected": 5810.06005859375,
|
872 |
+
"logps/chosen": -254.17337036132812,
|
873 |
+
"logps/rejected": -264.60821533203125,
|
874 |
+
"loss": -0.5522,
|
875 |
+
"rewards/accuracies": 0.7250000238418579,
|
876 |
+
"rewards/chosen": -11.213506698608398,
|
877 |
+
"rewards/margins": 29.624225616455078,
|
878 |
+
"rewards/rejected": -40.837730407714844,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4552590266875981,
|
883 |
+
"grad_norm": 14.737833568834182,
|
884 |
+
"learning_rate": 3.314136382905234e-07,
|
885 |
+
"logits/chosen": 6228.8447265625,
|
886 |
+
"logits/rejected": 5667.69580078125,
|
887 |
+
"logps/chosen": -219.33993530273438,
|
888 |
+
"logps/rejected": -250.21707153320312,
|
889 |
+
"loss": -0.5449,
|
890 |
+
"rewards/accuracies": 0.7500000596046448,
|
891 |
+
"rewards/chosen": -6.924456596374512,
|
892 |
+
"rewards/margins": 29.981273651123047,
|
893 |
+
"rewards/rejected": -36.90573501586914,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.4631083202511774,
|
898 |
+
"grad_norm": 13.760212196324753,
|
899 |
+
"learning_rate": 3.249040595833274e-07,
|
900 |
+
"logits/chosen": 6781.17822265625,
|
901 |
+
"logits/rejected": 5766.2646484375,
|
902 |
+
"logps/chosen": -239.05776977539062,
|
903 |
+
"logps/rejected": -213.7412872314453,
|
904 |
+
"loss": -0.5554,
|
905 |
+
"rewards/accuracies": 0.75,
|
906 |
+
"rewards/chosen": -7.3319220542907715,
|
907 |
+
"rewards/margins": 27.55051040649414,
|
908 |
+
"rewards/rejected": -34.88243103027344,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.47095761381475665,
|
913 |
+
"grad_norm": 19.441232852710126,
|
914 |
+
"learning_rate": 3.1833819380279023e-07,
|
915 |
+
"logits/chosen": 6427.10107421875,
|
916 |
+
"logits/rejected": 5508.02001953125,
|
917 |
+
"logps/chosen": -188.13037109375,
|
918 |
+
"logps/rejected": -230.70938110351562,
|
919 |
+
"loss": -0.5525,
|
920 |
+
"rewards/accuracies": 0.824999988079071,
|
921 |
+
"rewards/chosen": -10.582036972045898,
|
922 |
+
"rewards/margins": 30.44106674194336,
|
923 |
+
"rewards/rejected": -41.023101806640625,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.478806907378336,
|
928 |
+
"grad_norm": 13.388579418872117,
|
929 |
+
"learning_rate": 3.11720974905373e-07,
|
930 |
+
"logits/chosen": 6165.43896484375,
|
931 |
+
"logits/rejected": 5416.3076171875,
|
932 |
+
"logps/chosen": -216.6073455810547,
|
933 |
+
"logps/rejected": -230.8435516357422,
|
934 |
+
"loss": -0.56,
|
935 |
+
"rewards/accuracies": 0.7833333611488342,
|
936 |
+
"rewards/chosen": -10.489218711853027,
|
937 |
+
"rewards/margins": 34.93179702758789,
|
938 |
+
"rewards/rejected": -45.421016693115234,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.48665620094191525,
|
943 |
+
"grad_norm": 18.107686999639345,
|
944 |
+
"learning_rate": 3.0505737543712275e-07,
|
945 |
+
"logits/chosen": 5264.59521484375,
|
946 |
+
"logits/rejected": 4359.83251953125,
|
947 |
+
"logps/chosen": -194.50704956054688,
|
948 |
+
"logps/rejected": -204.3115692138672,
|
949 |
+
"loss": -0.5575,
|
950 |
+
"rewards/accuracies": 0.8166667222976685,
|
951 |
+
"rewards/chosen": -10.748395919799805,
|
952 |
+
"rewards/margins": 32.46430206298828,
|
953 |
+
"rewards/rejected": -43.21269607543945,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4945054945054945,
|
958 |
+
"grad_norm": 16.23681720440276,
|
959 |
+
"learning_rate": 2.9835240279702513e-07,
|
960 |
+
"logits/chosen": 6860.98046875,
|
961 |
+
"logits/rejected": 5905.08056640625,
|
962 |
+
"logps/chosen": -250.0574188232422,
|
963 |
+
"logps/rejected": -243.52294921875,
|
964 |
+
"loss": -0.56,
|
965 |
+
"rewards/accuracies": 0.7833333015441895,
|
966 |
+
"rewards/chosen": -7.241453647613525,
|
967 |
+
"rewards/margins": 42.033416748046875,
|
968 |
+
"rewards/rejected": -49.274871826171875,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.5023547880690737,
|
973 |
+
"grad_norm": 15.133905436958523,
|
974 |
+
"learning_rate": 2.9161109547416667e-07,
|
975 |
+
"logits/chosen": 6525.08740234375,
|
976 |
+
"logits/rejected": 5607.15185546875,
|
977 |
+
"logps/chosen": -222.1215362548828,
|
978 |
+
"logps/rejected": -249.20364379882812,
|
979 |
+
"loss": -0.5586,
|
980 |
+
"rewards/accuracies": 0.7083333730697632,
|
981 |
+
"rewards/chosen": -11.359973907470703,
|
982 |
+
"rewards/margins": 23.3347225189209,
|
983 |
+
"rewards/rejected": -34.69469451904297,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.5102040816326531,
|
988 |
+
"grad_norm": 16.011606806242707,
|
989 |
+
"learning_rate": 2.848385192615339e-07,
|
990 |
+
"logits/chosen": 5628.36181640625,
|
991 |
+
"logits/rejected": 4637.24462890625,
|
992 |
+
"logps/chosen": -205.99490356445312,
|
993 |
+
"logps/rejected": -203.79971313476562,
|
994 |
+
"loss": -0.5518,
|
995 |
+
"rewards/accuracies": 0.7666666507720947,
|
996 |
+
"rewards/chosen": -9.655582427978516,
|
997 |
+
"rewards/margins": 25.41636848449707,
|
998 |
+
"rewards/rejected": -35.07195281982422,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5180533751962323,
|
1003 |
+
"grad_norm": 21.247801665890794,
|
1004 |
+
"learning_rate": 2.780397634492949e-07,
|
1005 |
+
"logits/chosen": 6310.8505859375,
|
1006 |
+
"logits/rejected": 5097.1552734375,
|
1007 |
+
"logps/chosen": -227.1197509765625,
|
1008 |
+
"logps/rejected": -238.29598999023438,
|
1009 |
+
"loss": -0.5485,
|
1010 |
+
"rewards/accuracies": 0.7916666269302368,
|
1011 |
+
"rewards/chosen": -9.73323917388916,
|
1012 |
+
"rewards/margins": 40.615299224853516,
|
1013 |
+
"rewards/rejected": -50.34853744506836,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5259026687598116,
|
1018 |
+
"grad_norm": 15.560809488629776,
|
1019 |
+
"learning_rate": 2.71219937000424e-07,
|
1020 |
+
"logits/chosen": 6286.98486328125,
|
1021 |
+
"logits/rejected": 5196.23583984375,
|
1022 |
+
"logps/chosen": -220.25863647460938,
|
1023 |
+
"logps/rejected": -234.5564422607422,
|
1024 |
+
"loss": -0.5473,
|
1025 |
+
"rewards/accuracies": 0.8166667222976685,
|
1026 |
+
"rewards/chosen": -13.499173164367676,
|
1027 |
+
"rewards/margins": 32.202857971191406,
|
1028 |
+
"rewards/rejected": -45.702030181884766,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.533751962323391,
|
1033 |
+
"grad_norm": 14.170981357167607,
|
1034 |
+
"learning_rate": 2.6438416471154273e-07,
|
1035 |
+
"logits/chosen": 6083.7236328125,
|
1036 |
+
"logits/rejected": 5118.7060546875,
|
1037 |
+
"logps/chosen": -222.4500274658203,
|
1038 |
+
"logps/rejected": -222.7382354736328,
|
1039 |
+
"loss": -0.5508,
|
1040 |
+
"rewards/accuracies": 0.7583333253860474,
|
1041 |
+
"rewards/chosen": -8.788731575012207,
|
1042 |
+
"rewards/margins": 34.72281265258789,
|
1043 |
+
"rewards/rejected": -43.51154708862305,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.5416012558869702,
|
1048 |
+
"grad_norm": 13.47806294145218,
|
1049 |
+
"learning_rate": 2.5753758336186326e-07,
|
1050 |
+
"logits/chosen": 6007.140625,
|
1051 |
+
"logits/rejected": 5543.3837890625,
|
1052 |
+
"logps/chosen": -219.5069580078125,
|
1053 |
+
"logps/rejected": -257.30035400390625,
|
1054 |
+
"loss": -0.5561,
|
1055 |
+
"rewards/accuracies": 0.7416667342185974,
|
1056 |
+
"rewards/chosen": -10.400491714477539,
|
1057 |
+
"rewards/margins": 30.703176498413086,
|
1058 |
+
"rewards/rejected": -41.10367202758789,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5494505494505495,
|
1063 |
+
"grad_norm": 14.319715146996487,
|
1064 |
+
"learning_rate": 2.5068533785312666e-07,
|
1065 |
+
"logits/chosen": 5713.2421875,
|
1066 |
+
"logits/rejected": 5524.46728515625,
|
1067 |
+
"logps/chosen": -200.09414672851562,
|
1068 |
+
"logps/rejected": -227.26785278320312,
|
1069 |
+
"loss": -0.5387,
|
1070 |
+
"rewards/accuracies": 0.7666667103767395,
|
1071 |
+
"rewards/chosen": -10.833822250366211,
|
1072 |
+
"rewards/margins": 29.460071563720703,
|
1073 |
+
"rewards/rejected": -40.29389190673828,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.5572998430141287,
|
1078 |
+
"grad_norm": 15.375895555824917,
|
1079 |
+
"learning_rate": 2.4383257734343794e-07,
|
1080 |
+
"logits/chosen": 5675.8701171875,
|
1081 |
+
"logits/rejected": 5728.0244140625,
|
1082 |
+
"logps/chosen": -204.74752807617188,
|
1083 |
+
"logps/rejected": -241.16943359375,
|
1084 |
+
"loss": -0.5554,
|
1085 |
+
"rewards/accuracies": 0.75,
|
1086 |
+
"rewards/chosen": -10.83613395690918,
|
1087 |
+
"rewards/margins": 27.712646484375,
|
1088 |
+
"rewards/rejected": -38.54877853393555,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.565149136577708,
|
1093 |
+
"grad_norm": 14.873727955111258,
|
1094 |
+
"learning_rate": 2.3698445137790258e-07,
|
1095 |
+
"logits/chosen": 6093.0908203125,
|
1096 |
+
"logits/rejected": 5287.7705078125,
|
1097 |
+
"logps/chosen": -226.853271484375,
|
1098 |
+
"logps/rejected": -238.8446502685547,
|
1099 |
+
"loss": -0.5478,
|
1100 |
+
"rewards/accuracies": 0.7833333015441895,
|
1101 |
+
"rewards/chosen": -7.8500471115112305,
|
1102 |
+
"rewards/margins": 31.229473114013672,
|
1103 |
+
"rewards/rejected": -39.07952117919922,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5729984301412873,
|
1108 |
+
"grad_norm": 17.247561991897758,
|
1109 |
+
"learning_rate": 2.3014610601897157e-07,
|
1110 |
+
"logits/chosen": 6625.6201171875,
|
1111 |
+
"logits/rejected": 5123.14208984375,
|
1112 |
+
"logps/chosen": -237.73007202148438,
|
1113 |
+
"logps/rejected": -221.32418823242188,
|
1114 |
+
"loss": -0.5595,
|
1115 |
+
"rewards/accuracies": 0.7166666984558105,
|
1116 |
+
"rewards/chosen": -12.584187507629395,
|
1117 |
+
"rewards/margins": 33.66630172729492,
|
1118 |
+
"rewards/rejected": -46.25048828125,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5808477237048666,
|
1123 |
+
"grad_norm": 19.18591397361123,
|
1124 |
+
"learning_rate": 2.2332267997940513e-07,
|
1125 |
+
"logits/chosen": 5518.5419921875,
|
1126 |
+
"logits/rejected": 4722.01513671875,
|
1127 |
+
"logps/chosen": -199.68359375,
|
1128 |
+
"logps/rejected": -204.318359375,
|
1129 |
+
"loss": -0.5589,
|
1130 |
+
"rewards/accuracies": 0.7750000357627869,
|
1131 |
+
"rewards/chosen": -7.2591447830200195,
|
1132 |
+
"rewards/margins": 34.41317367553711,
|
1133 |
+
"rewards/rejected": -41.672325134277344,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5886970172684458,
|
1138 |
+
"grad_norm": 13.735789569741188,
|
1139 |
+
"learning_rate": 2.1651930076075723e-07,
|
1140 |
+
"logits/chosen": 6000.32470703125,
|
1141 |
+
"logits/rejected": 5473.8232421875,
|
1142 |
+
"logps/chosen": -192.8706817626953,
|
1143 |
+
"logps/rejected": -205.87020874023438,
|
1144 |
+
"loss": -0.5484,
|
1145 |
+
"rewards/accuracies": 0.7166667580604553,
|
1146 |
+
"rewards/chosen": -12.444730758666992,
|
1147 |
+
"rewards/margins": 26.331233978271484,
|
1148 |
+
"rewards/rejected": -38.775962829589844,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.5965463108320251,
|
1153 |
+
"grad_norm": 14.884916482785034,
|
1154 |
+
"learning_rate": 2.0974108080028692e-07,
|
1155 |
+
"logits/chosen": 6278.75048828125,
|
1156 |
+
"logits/rejected": 5003.58544921875,
|
1157 |
+
"logps/chosen": -215.50863647460938,
|
1158 |
+
"logps/rejected": -215.87338256835938,
|
1159 |
+
"loss": -0.5446,
|
1160 |
+
"rewards/accuracies": 0.7083333134651184,
|
1161 |
+
"rewards/chosen": -12.257668495178223,
|
1162 |
+
"rewards/margins": 29.0852108001709,
|
1163 |
+
"rewards/rejected": -41.34288024902344,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6043956043956044,
|
1168 |
+
"grad_norm": 22.408784444588175,
|
1169 |
+
"learning_rate": 2.0299311362918773e-07,
|
1170 |
+
"logits/chosen": 6477.56787109375,
|
1171 |
+
"logits/rejected": 5610.052734375,
|
1172 |
+
"logps/chosen": -241.07846069335938,
|
1173 |
+
"logps/rejected": -267.69708251953125,
|
1174 |
+
"loss": -0.5442,
|
1175 |
+
"rewards/accuracies": 0.7500000596046448,
|
1176 |
+
"rewards/chosen": -11.34480094909668,
|
1177 |
+
"rewards/margins": 32.4921875,
|
1178 |
+
"rewards/rejected": -43.83699035644531,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6122448979591837,
|
1183 |
+
"grad_norm": 13.15499328897201,
|
1184 |
+
"learning_rate": 1.962804700450265e-07,
|
1185 |
+
"logits/chosen": 6326.91259765625,
|
1186 |
+
"logits/rejected": 6053.4404296875,
|
1187 |
+
"logps/chosen": -225.9958953857422,
|
1188 |
+
"logps/rejected": -271.9791564941406,
|
1189 |
+
"loss": -0.5457,
|
1190 |
+
"rewards/accuracies": 0.7583333849906921,
|
1191 |
+
"rewards/chosen": -9.890580177307129,
|
1192 |
+
"rewards/margins": 24.70089340209961,
|
1193 |
+
"rewards/rejected": -34.591468811035156,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.6200941915227629,
|
1198 |
+
"grad_norm": 18.37743177954423,
|
1199 |
+
"learning_rate": 1.8960819430126334e-07,
|
1200 |
+
"logits/chosen": 5896.37841796875,
|
1201 |
+
"logits/rejected": 5250.25146484375,
|
1202 |
+
"logps/chosen": -212.64840698242188,
|
1203 |
+
"logps/rejected": -240.15286254882812,
|
1204 |
+
"loss": -0.5526,
|
1205 |
+
"rewards/accuracies": 0.7833333611488342,
|
1206 |
+
"rewards/chosen": -14.517425537109375,
|
1207 |
+
"rewards/margins": 37.03769302368164,
|
1208 |
+
"rewards/rejected": -51.55511474609375,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.6279434850863422,
|
1213 |
+
"grad_norm": 15.962566634301062,
|
1214 |
+
"learning_rate": 1.8298130031671972e-07,
|
1215 |
+
"logits/chosen": 5897.72021484375,
|
1216 |
+
"logits/rejected": 5196.263671875,
|
1217 |
+
"logps/chosen": -231.2862091064453,
|
1218 |
+
"logps/rejected": -256.14483642578125,
|
1219 |
+
"loss": -0.5427,
|
1220 |
+
"rewards/accuracies": 0.7166666388511658,
|
1221 |
+
"rewards/chosen": -14.563385009765625,
|
1222 |
+
"rewards/margins": 28.883220672607422,
|
1223 |
+
"rewards/rejected": -43.44660568237305,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6357927786499215,
|
1228 |
+
"grad_norm": 14.503187832917975,
|
1229 |
+
"learning_rate": 1.7640476790784075e-07,
|
1230 |
+
"logits/chosen": 5457.9208984375,
|
1231 |
+
"logits/rejected": 4929.38916015625,
|
1232 |
+
"logps/chosen": -212.62448120117188,
|
1233 |
+
"logps/rejected": -262.00335693359375,
|
1234 |
+
"loss": -0.5505,
|
1235 |
+
"rewards/accuracies": 0.7499999403953552,
|
1236 |
+
"rewards/chosen": -10.169076919555664,
|
1237 |
+
"rewards/margins": 30.537002563476562,
|
1238 |
+
"rewards/rejected": -40.706077575683594,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.6436420722135008,
|
1243 |
+
"grad_norm": 17.287039922914133,
|
1244 |
+
"learning_rate": 1.6988353904658492e-07,
|
1245 |
+
"logits/chosen": 5933.09375,
|
1246 |
+
"logits/rejected": 4622.87109375,
|
1247 |
+
"logps/chosen": -228.77828979492188,
|
1248 |
+
"logps/rejected": -208.31448364257812,
|
1249 |
+
"loss": -0.556,
|
1250 |
+
"rewards/accuracies": 0.800000011920929,
|
1251 |
+
"rewards/chosen": -7.563757419586182,
|
1252 |
+
"rewards/margins": 32.06237030029297,
|
1253 |
+
"rewards/rejected": -39.62612533569336,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.6514913657770801,
|
1258 |
+
"grad_norm": 16.00623751669361,
|
1259 |
+
"learning_rate": 1.634225141467513e-07,
|
1260 |
+
"logits/chosen": 5868.5166015625,
|
1261 |
+
"logits/rejected": 5272.09912109375,
|
1262 |
+
"logps/chosen": -217.6871795654297,
|
1263 |
+
"logps/rejected": -241.2273712158203,
|
1264 |
+
"loss": -0.5533,
|
1265 |
+
"rewards/accuracies": 0.7416667342185974,
|
1266 |
+
"rewards/chosen": -13.501172065734863,
|
1267 |
+
"rewards/margins": 35.271339416503906,
|
1268 |
+
"rewards/rejected": -48.77251052856445,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6593406593406593,
|
1273 |
+
"grad_norm": 13.65824185805484,
|
1274 |
+
"learning_rate": 1.570265483815364e-07,
|
1275 |
+
"logits/chosen": 6410.0361328125,
|
1276 |
+
"logits/rejected": 5289.599609375,
|
1277 |
+
"logps/chosen": -243.1864471435547,
|
1278 |
+
"logps/rejected": -254.82406616210938,
|
1279 |
+
"loss": -0.5502,
|
1280 |
+
"rewards/accuracies": 0.675000011920929,
|
1281 |
+
"rewards/chosen": -15.856649398803711,
|
1282 |
+
"rewards/margins": 26.174245834350586,
|
1283 |
+
"rewards/rejected": -42.03089141845703,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.6671899529042387,
|
1288 |
+
"grad_norm": 14.96256454286525,
|
1289 |
+
"learning_rate": 1.5070044803508691e-07,
|
1290 |
+
"logits/chosen": 5922.5771484375,
|
1291 |
+
"logits/rejected": 5358.466796875,
|
1292 |
+
"logps/chosen": -228.34841918945312,
|
1293 |
+
"logps/rejected": -248.4814910888672,
|
1294 |
+
"loss": -0.5573,
|
1295 |
+
"rewards/accuracies": 0.7416666746139526,
|
1296 |
+
"rewards/chosen": -12.870938301086426,
|
1297 |
+
"rewards/margins": 35.15522003173828,
|
1298 |
+
"rewards/rejected": -48.02615737915039,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.6750392464678179,
|
1303 |
+
"grad_norm": 14.889400880268978,
|
1304 |
+
"learning_rate": 1.444489668907914e-07,
|
1305 |
+
"logits/chosen": 6385.53466796875,
|
1306 |
+
"logits/rejected": 5459.19091796875,
|
1307 |
+
"logps/chosen": -257.6268310546875,
|
1308 |
+
"logps/rejected": -245.7576446533203,
|
1309 |
+
"loss": -0.5477,
|
1310 |
+
"rewards/accuracies": 0.800000011920929,
|
1311 |
+
"rewards/chosen": -9.85617733001709,
|
1312 |
+
"rewards/margins": 33.21961212158203,
|
1313 |
+
"rewards/rejected": -43.07579803466797,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6828885400313972,
|
1318 |
+
"grad_norm": 13.291251228226638,
|
1319 |
+
"learning_rate": 1.3827680265902232e-07,
|
1320 |
+
"logits/chosen": 6342.3896484375,
|
1321 |
+
"logits/rejected": 5289.41796875,
|
1322 |
+
"logps/chosen": -241.23410034179688,
|
1323 |
+
"logps/rejected": -240.6619873046875,
|
1324 |
+
"loss": -0.5514,
|
1325 |
+
"rewards/accuracies": 0.783333420753479,
|
1326 |
+
"rewards/chosen": -11.137380599975586,
|
1327 |
+
"rewards/margins": 28.83567237854004,
|
1328 |
+
"rewards/rejected": -39.973052978515625,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6907378335949764,
|
1333 |
+
"grad_norm": 16.523056356741357,
|
1334 |
+
"learning_rate": 1.3218859344701632e-07,
|
1335 |
+
"logits/chosen": 5571.25390625,
|
1336 |
+
"logits/rejected": 5356.0625,
|
1337 |
+
"logps/chosen": -220.6587677001953,
|
1338 |
+
"logps/rejected": -270.5399169921875,
|
1339 |
+
"loss": -0.5457,
|
1340 |
+
"rewards/accuracies": 0.7749999761581421,
|
1341 |
+
"rewards/chosen": -10.14782428741455,
|
1342 |
+
"rewards/margins": 28.80292320251465,
|
1343 |
+
"rewards/rejected": -38.950748443603516,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6985871271585558,
|
1348 |
+
"grad_norm": 17.16912370914084,
|
1349 |
+
"learning_rate": 1.2618891427354172e-07,
|
1350 |
+
"logits/chosen": 6568.57421875,
|
1351 |
+
"logits/rejected": 5379.8818359375,
|
1352 |
+
"logps/chosen": -264.95001220703125,
|
1353 |
+
"logps/rejected": -252.56497192382812,
|
1354 |
+
"loss": -0.5498,
|
1355 |
+
"rewards/accuracies": 0.7916666269302368,
|
1356 |
+
"rewards/chosen": -7.353941917419434,
|
1357 |
+
"rewards/margins": 33.43050765991211,
|
1358 |
+
"rewards/rejected": -40.784446716308594,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.706436420722135,
|
1363 |
+
"grad_norm": 14.805310374425751,
|
1364 |
+
"learning_rate": 1.202822736309758e-07,
|
1365 |
+
"logits/chosen": 5562.001953125,
|
1366 |
+
"logits/rejected": 5189.39013671875,
|
1367 |
+
"logps/chosen": -214.02035522460938,
|
1368 |
+
"logps/rejected": -252.0713653564453,
|
1369 |
+
"loss": -0.5492,
|
1370 |
+
"rewards/accuracies": 0.7333333492279053,
|
1371 |
+
"rewards/chosen": -9.671173095703125,
|
1372 |
+
"rewards/margins": 31.970129013061523,
|
1373 |
+
"rewards/rejected": -41.64129638671875,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7142857142857143,
|
1378 |
+
"grad_norm": 15.154490017250051,
|
1379 |
+
"learning_rate": 1.1447311009737299e-07,
|
1380 |
+
"logits/chosen": 5476.24072265625,
|
1381 |
+
"logits/rejected": 5228.48291015625,
|
1382 |
+
"logps/chosen": -221.74267578125,
|
1383 |
+
"logps/rejected": -256.24432373046875,
|
1384 |
+
"loss": -0.5496,
|
1385 |
+
"rewards/accuracies": 0.783333420753479,
|
1386 |
+
"rewards/chosen": -13.516392707824707,
|
1387 |
+
"rewards/margins": 34.79946517944336,
|
1388 |
+
"rewards/rejected": -48.315860748291016,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.7221350078492935,
|
1393 |
+
"grad_norm": 22.407408345422997,
|
1394 |
+
"learning_rate": 1.0876578900107053e-07,
|
1395 |
+
"logits/chosen": 6060.7919921875,
|
1396 |
+
"logits/rejected": 5049.7998046875,
|
1397 |
+
"logps/chosen": -243.87020874023438,
|
1398 |
+
"logps/rejected": -245.1348114013672,
|
1399 |
+
"loss": -0.5507,
|
1400 |
+
"rewards/accuracies": 0.7916666865348816,
|
1401 |
+
"rewards/chosen": -11.448633193969727,
|
1402 |
+
"rewards/margins": 35.54388427734375,
|
1403 |
+
"rewards/rejected": -46.992515563964844,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.7299843014128728,
|
1408 |
+
"grad_norm": 14.713347007112848,
|
1409 |
+
"learning_rate": 1.0316459914033793e-07,
|
1410 |
+
"logits/chosen": 5965.28076171875,
|
1411 |
+
"logits/rejected": 4541.7861328125,
|
1412 |
+
"logps/chosen": -251.3324737548828,
|
1413 |
+
"logps/rejected": -233.15658569335938,
|
1414 |
+
"loss": -0.5469,
|
1415 |
+
"rewards/accuracies": 0.7416666746139526,
|
1416 |
+
"rewards/chosen": -15.343559265136719,
|
1417 |
+
"rewards/margins": 31.8887939453125,
|
1418 |
+
"rewards/rejected": -47.23234939575195,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.7378335949764521,
|
1423 |
+
"grad_norm": 16.078089093379223,
|
1424 |
+
"learning_rate": 9.767374956053584e-08,
|
1425 |
+
"logits/chosen": 5780.9345703125,
|
1426 |
+
"logits/rejected": 5092.5830078125,
|
1427 |
+
"logps/chosen": -230.3660888671875,
|
1428 |
+
"logps/rejected": -252.21774291992188,
|
1429 |
+
"loss": -0.5496,
|
1430 |
+
"rewards/accuracies": 0.7333333492279053,
|
1431 |
+
"rewards/chosen": -12.072437286376953,
|
1432 |
+
"rewards/margins": 35.165443420410156,
|
1433 |
+
"rewards/rejected": -47.237876892089844,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7456828885400314,
|
1438 |
+
"grad_norm": 16.261901912135954,
|
1439 |
+
"learning_rate": 9.229736639120561e-08,
|
1440 |
+
"logits/chosen": 5962.2880859375,
|
1441 |
+
"logits/rejected": 5526.39306640625,
|
1442 |
+
"logps/chosen": -228.35769653320312,
|
1443 |
+
"logps/rejected": -246.65869140625,
|
1444 |
+
"loss": -0.5429,
|
1445 |
+
"rewards/accuracies": 0.7833333611488342,
|
1446 |
+
"rewards/chosen": -10.55649471282959,
|
1447 |
+
"rewards/margins": 21.94769287109375,
|
1448 |
+
"rewards/rejected": -32.504188537597656,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.7535321821036107,
|
1453 |
+
"grad_norm": 13.221689149992935,
|
1454 |
+
"learning_rate": 8.70394897454659e-08,
|
1455 |
+
"logits/chosen": 5809.796875,
|
1456 |
+
"logits/rejected": 5207.8203125,
|
1457 |
+
"logps/chosen": -224.7841796875,
|
1458 |
+
"logps/rejected": -238.98696899414062,
|
1459 |
+
"loss": -0.5546,
|
1460 |
+
"rewards/accuracies": 0.8166667222976685,
|
1461 |
+
"rewards/chosen": -6.355766296386719,
|
1462 |
+
"rewards/margins": 30.154870986938477,
|
1463 |
+
"rewards/rejected": -36.51063537597656,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7613814756671899,
|
1468 |
+
"grad_norm": 15.744789799259141,
|
1469 |
+
"learning_rate": 8.19040706840472e-08,
|
1470 |
+
"logits/chosen": 5915.970703125,
|
1471 |
+
"logits/rejected": 4988.2001953125,
|
1472 |
+
"logps/chosen": -249.45468139648438,
|
1473 |
+
"logps/rejected": -252.91500854492188,
|
1474 |
+
"loss": -0.5573,
|
1475 |
+
"rewards/accuracies": 0.7750000357627869,
|
1476 |
+
"rewards/chosen": -9.234709739685059,
|
1477 |
+
"rewards/margins": 36.98971939086914,
|
1478 |
+
"rewards/rejected": -46.22443389892578,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7692307692307693,
|
1483 |
+
"grad_norm": 14.041623563140766,
|
1484 |
+
"learning_rate": 7.689496824624525e-08,
|
1485 |
+
"logits/chosen": 5622.8994140625,
|
1486 |
+
"logits/rejected": 4569.49462890625,
|
1487 |
+
"logps/chosen": -236.6791229248047,
|
1488 |
+
"logps/rejected": -245.09487915039062,
|
1489 |
+
"loss": -0.5557,
|
1490 |
+
"rewards/accuracies": 0.8166666030883789,
|
1491 |
+
"rewards/chosen": -7.862542152404785,
|
1492 |
+
"rewards/margins": 46.738731384277344,
|
1493 |
+
"rewards/rejected": -54.60127639770508,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.7770800627943485,
|
1498 |
+
"grad_norm": 18.103997714286827,
|
1499 |
+
"learning_rate": 7.201594655002458e-08,
|
1500 |
+
"logits/chosen": 5944.6259765625,
|
1501 |
+
"logits/rejected": 5010.23876953125,
|
1502 |
+
"logps/chosen": -238.925048828125,
|
1503 |
+
"logps/rejected": -244.1151580810547,
|
1504 |
+
"loss": -0.5534,
|
1505 |
+
"rewards/accuracies": 0.7250000238418579,
|
1506 |
+
"rewards/chosen": -13.030115127563477,
|
1507 |
+
"rewards/margins": 37.01529312133789,
|
1508 |
+
"rewards/rejected": -50.04541015625,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.7849293563579278,
|
1513 |
+
"grad_norm": 17.968333064385718,
|
1514 |
+
"learning_rate": 6.727067196345099e-08,
|
1515 |
+
"logits/chosen": 5641.294921875,
|
1516 |
+
"logits/rejected": 4806.80517578125,
|
1517 |
+
"logps/chosen": -224.1138458251953,
|
1518 |
+
"logps/rejected": -217.52890014648438,
|
1519 |
+
"loss": -0.5483,
|
1520 |
+
"rewards/accuracies": 0.7166666388511658,
|
1521 |
+
"rewards/chosen": -10.35799503326416,
|
1522 |
+
"rewards/margins": 26.82565689086914,
|
1523 |
+
"rewards/rejected": -37.18364715576172,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.792778649921507,
|
1528 |
+
"grad_norm": 13.263741910622812,
|
1529 |
+
"learning_rate": 6.26627103495786e-08,
|
1530 |
+
"logits/chosen": 5823.0947265625,
|
1531 |
+
"logits/rejected": 4895.5849609375,
|
1532 |
+
"logps/chosen": -223.3077850341797,
|
1533 |
+
"logps/rejected": -230.5642852783203,
|
1534 |
+
"loss": -0.5494,
|
1535 |
+
"rewards/accuracies": 0.7166666388511658,
|
1536 |
+
"rewards/chosen": -8.598567008972168,
|
1537 |
+
"rewards/margins": 30.532119750976562,
|
1538 |
+
"rewards/rejected": -39.13068389892578,
|
1539 |
+
"step": 1010
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.8006279434850864,
|
1543 |
+
"grad_norm": 14.14161334701853,
|
1544 |
+
"learning_rate": 5.8195524386862374e-08,
|
1545 |
+
"logits/chosen": 5912.64306640625,
|
1546 |
+
"logits/rejected": 5297.43408203125,
|
1547 |
+
"logps/chosen": -255.5826873779297,
|
1548 |
+
"logps/rejected": -267.65789794921875,
|
1549 |
+
"loss": -0.5487,
|
1550 |
+
"rewards/accuracies": 0.8333333730697632,
|
1551 |
+
"rewards/chosen": -7.4040656089782715,
|
1552 |
+
"rewards/margins": 34.17313766479492,
|
1553 |
+
"rewards/rejected": -41.57720184326172,
|
1554 |
+
"step": 1020
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.8084772370486656,
|
1558 |
+
"grad_norm": 16.110829515167328,
|
1559 |
+
"learning_rate": 5.38724709671092e-08,
|
1560 |
+
"logits/chosen": 6308.998046875,
|
1561 |
+
"logits/rejected": 5989.17822265625,
|
1562 |
+
"logps/chosen": -242.4403839111328,
|
1563 |
+
"logps/rejected": -275.2937927246094,
|
1564 |
+
"loss": -0.5528,
|
1565 |
+
"rewards/accuracies": 0.7916666269302368,
|
1566 |
+
"rewards/chosen": -10.972010612487793,
|
1567 |
+
"rewards/margins": 31.2025203704834,
|
1568 |
+
"rewards/rejected": -42.17452621459961,
|
1569 |
+
"step": 1030
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8163265306122449,
|
1573 |
+
"grad_norm": 19.509435425991782,
|
1574 |
+
"learning_rate": 4.969679867292276e-08,
|
1575 |
+
"logits/chosen": 5612.50244140625,
|
1576 |
+
"logits/rejected": 5153.9169921875,
|
1577 |
+
"logps/chosen": -233.4686279296875,
|
1578 |
+
"logps/rejected": -257.07269287109375,
|
1579 |
+
"loss": -0.5516,
|
1580 |
+
"rewards/accuracies": 0.7000001072883606,
|
1581 |
+
"rewards/chosen": -13.366943359375,
|
1582 |
+
"rewards/margins": 34.52176284790039,
|
1583 |
+
"rewards/rejected": -47.88870620727539,
|
1584 |
+
"step": 1040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8241758241758241,
|
1588 |
+
"grad_norm": 16.431746409803452,
|
1589 |
+
"learning_rate": 4.5671645336537416e-08,
|
1590 |
+
"logits/chosen": 5662.87255859375,
|
1591 |
+
"logits/rejected": 5196.033203125,
|
1592 |
+
"logps/chosen": -249.39706420898438,
|
1593 |
+
"logps/rejected": -264.2225341796875,
|
1594 |
+
"loss": -0.5558,
|
1595 |
+
"rewards/accuracies": 0.7333333492279053,
|
1596 |
+
"rewards/chosen": -11.916464805603027,
|
1597 |
+
"rewards/margins": 36.51172637939453,
|
1598 |
+
"rewards/rejected": -48.428192138671875,
|
1599 |
+
"step": 1050
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.8320251177394035,
|
1603 |
+
"grad_norm": 21.652998761202152,
|
1604 |
+
"learning_rate": 4.180003568187776e-08,
|
1605 |
+
"logits/chosen": 6986.6953125,
|
1606 |
+
"logits/rejected": 5531.6259765625,
|
1607 |
+
"logps/chosen": -275.694091796875,
|
1608 |
+
"logps/rejected": -260.778564453125,
|
1609 |
+
"loss": -0.5439,
|
1610 |
+
"rewards/accuracies": 0.7166666984558105,
|
1611 |
+
"rewards/chosen": -14.706733703613281,
|
1612 |
+
"rewards/margins": 26.032629013061523,
|
1613 |
+
"rewards/rejected": -40.73936080932617,
|
1614 |
+
"step": 1060
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.8398744113029827,
|
1618 |
+
"grad_norm": 14.876687749593671,
|
1619 |
+
"learning_rate": 3.8084879051612144e-08,
|
1620 |
+
"logits/chosen": 5824.328125,
|
1621 |
+
"logits/rejected": 5373.7041015625,
|
1622 |
+
"logps/chosen": -233.8295135498047,
|
1623 |
+
"logps/rejected": -236.5215606689453,
|
1624 |
+
"loss": -0.5511,
|
1625 |
+
"rewards/accuracies": 0.7250000238418579,
|
1626 |
+
"rewards/chosen": -8.586492538452148,
|
1627 |
+
"rewards/margins": 34.77070617675781,
|
1628 |
+
"rewards/rejected": -43.357200622558594,
|
1629 |
+
"step": 1070
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.847723704866562,
|
1633 |
+
"grad_norm": 16.725130244781578,
|
1634 |
+
"learning_rate": 3.452896722091128e-08,
|
1635 |
+
"logits/chosen": 6377.11328125,
|
1636 |
+
"logits/rejected": 4972.22021484375,
|
1637 |
+
"logps/chosen": -273.76922607421875,
|
1638 |
+
"logps/rejected": -250.38369750976562,
|
1639 |
+
"loss": -0.5561,
|
1640 |
+
"rewards/accuracies": 0.8083333969116211,
|
1641 |
+
"rewards/chosen": -7.199933052062988,
|
1642 |
+
"rewards/margins": 42.20384216308594,
|
1643 |
+
"rewards/rejected": -49.403770446777344,
|
1644 |
+
"step": 1080
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.8555729984301413,
|
1648 |
+
"grad_norm": 14.877863636251977,
|
1649 |
+
"learning_rate": 3.11349722995527e-08,
|
1650 |
+
"logits/chosen": 6464.0947265625,
|
1651 |
+
"logits/rejected": 4879.25830078125,
|
1652 |
+
"logps/chosen": -240.05032348632812,
|
1653 |
+
"logps/rejected": -255.6093292236328,
|
1654 |
+
"loss": -0.5505,
|
1655 |
+
"rewards/accuracies": 0.75,
|
1656 |
+
"rewards/chosen": -12.57571029663086,
|
1657 |
+
"rewards/margins": 30.14911460876465,
|
1658 |
+
"rewards/rejected": -42.724822998046875,
|
1659 |
+
"step": 1090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.8634222919937206,
|
1663 |
+
"grad_norm": 20.19569564301896,
|
1664 |
+
"learning_rate": 2.7905444723949762e-08,
|
1665 |
+
"logits/chosen": 6226.359375,
|
1666 |
+
"logits/rejected": 5178.37890625,
|
1667 |
+
"logps/chosen": -251.06362915039062,
|
1668 |
+
"logps/rejected": -240.5138702392578,
|
1669 |
+
"loss": -0.5505,
|
1670 |
+
"rewards/accuracies": 0.800000011920929,
|
1671 |
+
"rewards/chosen": -12.527270317077637,
|
1672 |
+
"rewards/margins": 38.48920440673828,
|
1673 |
+
"rewards/rejected": -51.0164794921875,
|
1674 |
+
"step": 1100
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8712715855572999,
|
1678 |
+
"grad_norm": 17.825514771274925,
|
1679 |
+
"learning_rate": 2.484281134061142e-08,
|
1680 |
+
"logits/chosen": 6591.82666015625,
|
1681 |
+
"logits/rejected": 5353.4365234375,
|
1682 |
+
"logps/chosen": -276.72772216796875,
|
1683 |
+
"logps/rejected": -268.7568359375,
|
1684 |
+
"loss": -0.5523,
|
1685 |
+
"rewards/accuracies": 0.7833333611488342,
|
1686 |
+
"rewards/chosen": -12.114155769348145,
|
1687 |
+
"rewards/margins": 34.37467956542969,
|
1688 |
+
"rewards/rejected": -46.48883819580078,
|
1689 |
+
"step": 1110
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8791208791208791,
|
1693 |
+
"grad_norm": 16.02405187464744,
|
1694 |
+
"learning_rate": 2.194937358247506e-08,
|
1695 |
+
"logits/chosen": 6450.017578125,
|
1696 |
+
"logits/rejected": 5275.9541015625,
|
1697 |
+
"logps/chosen": -259.4888610839844,
|
1698 |
+
"logps/rejected": -264.9927673339844,
|
1699 |
+
"loss": -0.5526,
|
1700 |
+
"rewards/accuracies": 0.7500000596046448,
|
1701 |
+
"rewards/chosen": -14.348428726196289,
|
1702 |
+
"rewards/margins": 33.87355422973633,
|
1703 |
+
"rewards/rejected": -48.22198486328125,
|
1704 |
+
"step": 1120
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.8869701726844584,
|
1708 |
+
"grad_norm": 16.718921795503945,
|
1709 |
+
"learning_rate": 1.9227305739481612e-08,
|
1710 |
+
"logits/chosen": 5868.09326171875,
|
1711 |
+
"logits/rejected": 4665.5556640625,
|
1712 |
+
"logps/chosen": -243.3276824951172,
|
1713 |
+
"logps/rejected": -224.7455291748047,
|
1714 |
+
"loss": -0.5524,
|
1715 |
+
"rewards/accuracies": 0.7416666150093079,
|
1716 |
+
"rewards/chosen": -8.54565143585205,
|
1717 |
+
"rewards/margins": 35.97431564331055,
|
1718 |
+
"rewards/rejected": -44.51996612548828,
|
1719 |
+
"step": 1130
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.8948194662480377,
|
1723 |
+
"grad_norm": 21.87301219927631,
|
1724 |
+
"learning_rate": 1.6678653324693787e-08,
|
1725 |
+
"logits/chosen": 6443.2421875,
|
1726 |
+
"logits/rejected": 5277.41650390625,
|
1727 |
+
"logps/chosen": -267.6515197753906,
|
1728 |
+
"logps/rejected": -263.9855651855469,
|
1729 |
+
"loss": -0.5556,
|
1730 |
+
"rewards/accuracies": 0.7666667103767395,
|
1731 |
+
"rewards/chosen": -10.030736923217773,
|
1732 |
+
"rewards/margins": 33.14179992675781,
|
1733 |
+
"rewards/rejected": -43.17253494262695,
|
1734 |
+
"step": 1140
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.902668759811617,
|
1738 |
+
"grad_norm": 16.394242263229533,
|
1739 |
+
"learning_rate": 1.4305331537183384e-08,
|
1740 |
+
"logits/chosen": 5703.8076171875,
|
1741 |
+
"logits/rejected": 5282.501953125,
|
1742 |
+
"logps/chosen": -237.505859375,
|
1743 |
+
"logps/rejected": -260.38348388671875,
|
1744 |
+
"loss": -0.5545,
|
1745 |
+
"rewards/accuracies": 0.708333432674408,
|
1746 |
+
"rewards/chosen": -10.52247142791748,
|
1747 |
+
"rewards/margins": 30.373050689697266,
|
1748 |
+
"rewards/rejected": -40.8955192565918,
|
1749 |
+
"step": 1150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.9105180533751962,
|
1753 |
+
"grad_norm": 15.137357364789535,
|
1754 |
+
"learning_rate": 1.2109123822844653e-08,
|
1755 |
+
"logits/chosen": 5874.21923828125,
|
1756 |
+
"logits/rejected": 4698.57373046875,
|
1757 |
+
"logps/chosen": -242.8210906982422,
|
1758 |
+
"logps/rejected": -237.9269561767578,
|
1759 |
+
"loss": -0.5498,
|
1760 |
+
"rewards/accuracies": 0.7583333849906921,
|
1761 |
+
"rewards/chosen": -14.264314651489258,
|
1762 |
+
"rewards/margins": 27.72454261779785,
|
1763 |
+
"rewards/rejected": -41.988861083984375,
|
1764 |
+
"step": 1160
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.9183673469387755,
|
1768 |
+
"grad_norm": 14.46432731958664,
|
1769 |
+
"learning_rate": 1.0091680534213387e-08,
|
1770 |
+
"logits/chosen": 6431.46875,
|
1771 |
+
"logits/rejected": 6211.9443359375,
|
1772 |
+
"logps/chosen": -255.26016235351562,
|
1773 |
+
"logps/rejected": -287.64178466796875,
|
1774 |
+
"loss": -0.5454,
|
1775 |
+
"rewards/accuracies": 0.6833333969116211,
|
1776 |
+
"rewards/chosen": -12.311790466308594,
|
1777 |
+
"rewards/margins": 28.583049774169922,
|
1778 |
+
"rewards/rejected": -40.89484405517578,
|
1779 |
+
"step": 1170
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.9262166405023547,
|
1783 |
+
"grad_norm": 17.64924306448341,
|
1784 |
+
"learning_rate": 8.254517690300944e-09,
|
1785 |
+
"logits/chosen": 5668.1728515625,
|
1786 |
+
"logits/rejected": 5178.52587890625,
|
1787 |
+
"logps/chosen": -250.7957000732422,
|
1788 |
+
"logps/rejected": -257.81732177734375,
|
1789 |
+
"loss": -0.5488,
|
1790 |
+
"rewards/accuracies": 0.7250000834465027,
|
1791 |
+
"rewards/chosen": -10.84972095489502,
|
1792 |
+
"rewards/margins": 30.14580726623535,
|
1793 |
+
"rewards/rejected": -40.99553680419922,
|
1794 |
+
"step": 1180
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.9340659340659341,
|
1798 |
+
"grad_norm": 18.427229973583398,
|
1799 |
+
"learning_rate": 6.599015837372907e-09,
|
1800 |
+
"logits/chosen": 6148.91015625,
|
1801 |
+
"logits/rejected": 5400.935546875,
|
1802 |
+
"logps/chosen": -267.8089904785156,
|
1803 |
+
"logps/rejected": -266.39111328125,
|
1804 |
+
"loss": -0.5519,
|
1805 |
+
"rewards/accuracies": 0.7333333492279053,
|
1806 |
+
"rewards/chosen": -18.923511505126953,
|
1807 |
+
"rewards/margins": 30.315160751342773,
|
1808 |
+
"rewards/rejected": -49.238670349121094,
|
1809 |
+
"step": 1190
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.9419152276295133,
|
1813 |
+
"grad_norm": 15.198909725849877,
|
1814 |
+
"learning_rate": 5.126419011529992e-09,
|
1815 |
+
"logits/chosen": 6354.642578125,
|
1816 |
+
"logits/rejected": 5444.1533203125,
|
1817 |
+
"logps/chosen": -264.5579528808594,
|
1818 |
+
"logps/rejected": -269.75518798828125,
|
1819 |
+
"loss": -0.5561,
|
1820 |
+
"rewards/accuracies": 0.8416666984558105,
|
1821 |
+
"rewards/chosen": -8.896267890930176,
|
1822 |
+
"rewards/margins": 42.1933479309082,
|
1823 |
+
"rewards/rejected": -51.0896110534668,
|
1824 |
+
"step": 1200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.9497645211930926,
|
1828 |
+
"grad_norm": 17.684751446194035,
|
1829 |
+
"learning_rate": 3.837833803870177e-09,
|
1830 |
+
"logits/chosen": 5944.4462890625,
|
1831 |
+
"logits/rejected": 5231.82958984375,
|
1832 |
+
"logps/chosen": -252.0420379638672,
|
1833 |
+
"logps/rejected": -267.1654968261719,
|
1834 |
+
"loss": -0.551,
|
1835 |
+
"rewards/accuracies": 0.7916667461395264,
|
1836 |
+
"rewards/chosen": -11.856538772583008,
|
1837 |
+
"rewards/margins": 37.107666015625,
|
1838 |
+
"rewards/rejected": -48.96420669555664,
|
1839 |
+
"step": 1210
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.957613814756672,
|
1843 |
+
"grad_norm": 15.438763360340188,
|
1844 |
+
"learning_rate": 2.734228528934679e-09,
|
1845 |
+
"logits/chosen": 7407.5537109375,
|
1846 |
+
"logits/rejected": 5488.259765625,
|
1847 |
+
"logps/chosen": -311.3385925292969,
|
1848 |
+
"logps/rejected": -292.863037109375,
|
1849 |
+
"loss": -0.5477,
|
1850 |
+
"rewards/accuracies": 0.7250000238418579,
|
1851 |
+
"rewards/chosen": -14.570196151733398,
|
1852 |
+
"rewards/margins": 33.09563064575195,
|
1853 |
+
"rewards/rejected": -47.66582489013672,
|
1854 |
+
"step": 1220
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.9654631083202512,
|
1858 |
+
"grad_norm": 14.94216025982471,
|
1859 |
+
"learning_rate": 1.8164324970625645e-09,
|
1860 |
+
"logits/chosen": 6597.4267578125,
|
1861 |
+
"logits/rejected": 5241.8212890625,
|
1862 |
+
"logps/chosen": -269.3259582519531,
|
1863 |
+
"logps/rejected": -258.00634765625,
|
1864 |
+
"loss": -0.5511,
|
1865 |
+
"rewards/accuracies": 0.7416666746139526,
|
1866 |
+
"rewards/chosen": -8.744241714477539,
|
1867 |
+
"rewards/margins": 36.2653694152832,
|
1868 |
+
"rewards/rejected": -45.009605407714844,
|
1869 |
+
"step": 1230
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.9733124018838305,
|
1873 |
+
"grad_norm": 14.89107007034069,
|
1874 |
+
"learning_rate": 1.0851353912008642e-09,
|
1875 |
+
"logits/chosen": 5685.677734375,
|
1876 |
+
"logits/rejected": 5243.69921875,
|
1877 |
+
"logps/chosen": -246.015869140625,
|
1878 |
+
"logps/rejected": -281.5025329589844,
|
1879 |
+
"loss": -0.5539,
|
1880 |
+
"rewards/accuracies": 0.6833333373069763,
|
1881 |
+
"rewards/chosen": -14.403498649597168,
|
1882 |
+
"rewards/margins": 31.941186904907227,
|
1883 |
+
"rewards/rejected": -46.34468460083008,
|
1884 |
+
"step": 1240
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.9811616954474097,
|
1888 |
+
"grad_norm": 15.076764546390999,
|
1889 |
+
"learning_rate": 5.408867486384471e-10,
|
1890 |
+
"logits/chosen": 5798.7353515625,
|
1891 |
+
"logits/rejected": 4921.08642578125,
|
1892 |
+
"logps/chosen": -240.26687622070312,
|
1893 |
+
"logps/rejected": -225.79238891601562,
|
1894 |
+
"loss": -0.5486,
|
1895 |
+
"rewards/accuracies": 0.7583333253860474,
|
1896 |
+
"rewards/chosen": -9.958760261535645,
|
1897 |
+
"rewards/margins": 26.4033203125,
|
1898 |
+
"rewards/rejected": -36.362083435058594,
|
1899 |
+
"step": 1250
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.989010989010989,
|
1903 |
+
"grad_norm": 21.445426738337094,
|
1904 |
+
"learning_rate": 1.840955480532924e-10,
|
1905 |
+
"logits/chosen": 5476.0166015625,
|
1906 |
+
"logits/rejected": 5215.1123046875,
|
1907 |
+
"logps/chosen": -244.2669219970703,
|
1908 |
+
"logps/rejected": -257.24847412109375,
|
1909 |
+
"loss": -0.5525,
|
1910 |
+
"rewards/accuracies": 0.7666666507720947,
|
1911 |
+
"rewards/chosen": -12.10632610321045,
|
1912 |
+
"rewards/margins": 28.817041397094727,
|
1913 |
+
"rewards/rejected": -40.923362731933594,
|
1914 |
+
"step": 1260
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.9968602825745683,
|
1918 |
+
"grad_norm": 15.790140219517752,
|
1919 |
+
"learning_rate": 1.502990218302247e-11,
|
1920 |
+
"logits/chosen": 5753.83544921875,
|
1921 |
+
"logits/rejected": 4702.4267578125,
|
1922 |
+
"logps/chosen": -235.7917938232422,
|
1923 |
+
"logps/rejected": -232.51882934570312,
|
1924 |
+
"loss": -0.5564,
|
1925 |
+
"rewards/accuracies": 0.7583333253860474,
|
1926 |
+
"rewards/chosen": -11.317852020263672,
|
1927 |
+
"rewards/margins": 34.89674377441406,
|
1928 |
+
"rewards/rejected": -46.214599609375,
|
1929 |
+
"step": 1270
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.0,
|
1933 |
+
"step": 1274,
|
1934 |
+
"total_flos": 0.0,
|
1935 |
+
"train_loss": -0.5441001898826946,
|
1936 |
+
"train_runtime": 14755.3414,
|
1937 |
+
"train_samples_per_second": 4.143,
|
1938 |
+
"train_steps_per_second": 0.086
|
1939 |
+
}
|
1940 |
+
],
|
1941 |
+
"logging_steps": 10,
|
1942 |
+
"max_steps": 1274,
|
1943 |
+
"num_input_tokens_seen": 0,
|
1944 |
+
"num_train_epochs": 1,
|
1945 |
+
"save_steps": 1000,
|
1946 |
+
"stateful_callbacks": {
|
1947 |
+
"TrainerControl": {
|
1948 |
+
"args": {
|
1949 |
+
"should_epoch_stop": false,
|
1950 |
+
"should_evaluate": false,
|
1951 |
+
"should_log": false,
|
1952 |
+
"should_save": true,
|
1953 |
+
"should_training_stop": false
|
1954 |
+
},
|
1955 |
+
"attributes": {}
|
1956 |
+
}
|
1957 |
+
},
|
1958 |
+
"total_flos": 0.0,
|
1959 |
+
"train_batch_size": 6,
|
1960 |
+
"trial_name": null,
|
1961 |
+
"trial_params": null
|
1962 |
+
}
|