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_ExponentialAll-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_ExponentialAll-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": 1.9640779633724146,
|
5 |
+
"train_runtime": 14760.7646,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.142,
|
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 sha256:7615ab5a171b70c63c62ca7cfe03895f7ba445cdd59b41f3bf041915ded243fc
|
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:dde887d137aa9090c8f858c7cca0c50ce9f22b2665d60a8c3b965f910e53bf99
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70f65009a074312800b22403cda0873fb77e6324dc332c553fcc3be51cf3c44e
|
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": 1.9640779633724146,
|
5 |
+
"train_runtime": 14760.7646,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.142,
|
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": 6.091750131963952,
|
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": 2.0,
|
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": 6.059369066138964,
|
29 |
+
"learning_rate": 3.9062499999999997e-08,
|
30 |
+
"logits/chosen": 4973.767578125,
|
31 |
+
"logits/rejected": 4328.24365234375,
|
32 |
+
"logps/chosen": -204.23040771484375,
|
33 |
+
"logps/rejected": -179.6959686279297,
|
34 |
+
"loss": 2.0,
|
35 |
+
"rewards/accuracies": 0.4351852238178253,
|
36 |
+
"rewards/chosen": 0.05348973721265793,
|
37 |
+
"rewards/margins": 0.04383070021867752,
|
38 |
+
"rewards/rejected": 0.009659038856625557,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015698587127158554,
|
43 |
+
"grad_norm": 6.2041398306498685,
|
44 |
+
"learning_rate": 7.812499999999999e-08,
|
45 |
+
"logits/chosen": 6084.0126953125,
|
46 |
+
"logits/rejected": 4834.15869140625,
|
47 |
+
"logps/chosen": -217.233642578125,
|
48 |
+
"logps/rejected": -196.76730346679688,
|
49 |
+
"loss": 2.0,
|
50 |
+
"rewards/accuracies": 0.4833333492279053,
|
51 |
+
"rewards/chosen": -0.02243190072476864,
|
52 |
+
"rewards/margins": 0.03131182864308357,
|
53 |
+
"rewards/rejected": -0.053743720054626465,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.023547880690737835,
|
58 |
+
"grad_norm": 5.475152737188952,
|
59 |
+
"learning_rate": 1.1718749999999999e-07,
|
60 |
+
"logits/chosen": 6084.05908203125,
|
61 |
+
"logits/rejected": 5104.91748046875,
|
62 |
+
"logps/chosen": -250.56375122070312,
|
63 |
+
"logps/rejected": -209.34457397460938,
|
64 |
+
"loss": 1.9999,
|
65 |
+
"rewards/accuracies": 0.5333333015441895,
|
66 |
+
"rewards/chosen": 0.008603035472333431,
|
67 |
+
"rewards/margins": 0.05558818578720093,
|
68 |
+
"rewards/rejected": -0.04698514938354492,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03139717425431711,
|
73 |
+
"grad_norm": 5.690781670053855,
|
74 |
+
"learning_rate": 1.5624999999999999e-07,
|
75 |
+
"logits/chosen": 5311.8642578125,
|
76 |
+
"logits/rejected": 4346.90673828125,
|
77 |
+
"logps/chosen": -211.9870147705078,
|
78 |
+
"logps/rejected": -181.72384643554688,
|
79 |
+
"loss": 1.9997,
|
80 |
+
"rewards/accuracies": 0.5333333015441895,
|
81 |
+
"rewards/chosen": 0.09225504100322723,
|
82 |
+
"rewards/margins": 0.12906396389007568,
|
83 |
+
"rewards/rejected": -0.036808937788009644,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.03924646781789639,
|
88 |
+
"grad_norm": 5.758835415832506,
|
89 |
+
"learning_rate": 1.9531249999999998e-07,
|
90 |
+
"logits/chosen": 6425.0869140625,
|
91 |
+
"logits/rejected": 5042.13916015625,
|
92 |
+
"logps/chosen": -265.3288879394531,
|
93 |
+
"logps/rejected": -206.8175048828125,
|
94 |
+
"loss": 1.9992,
|
95 |
+
"rewards/accuracies": 0.6666667461395264,
|
96 |
+
"rewards/chosen": 0.29770660400390625,
|
97 |
+
"rewards/margins": 0.4155918061733246,
|
98 |
+
"rewards/rejected": -0.11788525432348251,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04709576138147567,
|
103 |
+
"grad_norm": 5.552781734195383,
|
104 |
+
"learning_rate": 2.3437499999999998e-07,
|
105 |
+
"logits/chosen": 5484.19091796875,
|
106 |
+
"logits/rejected": 4559.71923828125,
|
107 |
+
"logps/chosen": -213.75491333007812,
|
108 |
+
"logps/rejected": -209.1690216064453,
|
109 |
+
"loss": 1.9986,
|
110 |
+
"rewards/accuracies": 0.6666666269302368,
|
111 |
+
"rewards/chosen": 0.24906444549560547,
|
112 |
+
"rewards/margins": 0.6179634928703308,
|
113 |
+
"rewards/rejected": -0.36889898777008057,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.054945054945054944,
|
118 |
+
"grad_norm": 5.377299650407647,
|
119 |
+
"learning_rate": 2.734375e-07,
|
120 |
+
"logits/chosen": 5194.39501953125,
|
121 |
+
"logits/rejected": 4918.55322265625,
|
122 |
+
"logps/chosen": -178.2979736328125,
|
123 |
+
"logps/rejected": -177.39535522460938,
|
124 |
+
"loss": 1.998,
|
125 |
+
"rewards/accuracies": 0.7000000476837158,
|
126 |
+
"rewards/chosen": 0.18295133113861084,
|
127 |
+
"rewards/margins": 0.8465949892997742,
|
128 |
+
"rewards/rejected": -0.6636435985565186,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.06279434850863422,
|
133 |
+
"grad_norm": 5.650017423938731,
|
134 |
+
"learning_rate": 3.1249999999999997e-07,
|
135 |
+
"logits/chosen": 5774.41748046875,
|
136 |
+
"logits/rejected": 5269.755859375,
|
137 |
+
"logps/chosen": -196.76974487304688,
|
138 |
+
"logps/rejected": -182.98446655273438,
|
139 |
+
"loss": 1.9959,
|
140 |
+
"rewards/accuracies": 0.6500000357627869,
|
141 |
+
"rewards/chosen": -0.20117223262786865,
|
142 |
+
"rewards/margins": 1.1927589178085327,
|
143 |
+
"rewards/rejected": -1.3939311504364014,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0706436420722135,
|
148 |
+
"grad_norm": 6.605265759829803,
|
149 |
+
"learning_rate": 3.5156249999999997e-07,
|
150 |
+
"logits/chosen": 6039.5634765625,
|
151 |
+
"logits/rejected": 5181.203125,
|
152 |
+
"logps/chosen": -220.1410675048828,
|
153 |
+
"logps/rejected": -190.4438934326172,
|
154 |
+
"loss": 1.9924,
|
155 |
+
"rewards/accuracies": 0.7583332657814026,
|
156 |
+
"rewards/chosen": -1.2588454484939575,
|
157 |
+
"rewards/margins": 4.741243362426758,
|
158 |
+
"rewards/rejected": -6.000088691711426,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07849293563579278,
|
163 |
+
"grad_norm": 7.213834973026546,
|
164 |
+
"learning_rate": 3.9062499999999997e-07,
|
165 |
+
"logits/chosen": 5967.2626953125,
|
166 |
+
"logits/rejected": 5745.4873046875,
|
167 |
+
"logps/chosen": -213.9269256591797,
|
168 |
+
"logps/rejected": -208.77261352539062,
|
169 |
+
"loss": 1.9932,
|
170 |
+
"rewards/accuracies": 0.6750000715255737,
|
171 |
+
"rewards/chosen": -3.696242094039917,
|
172 |
+
"rewards/margins": 5.634647369384766,
|
173 |
+
"rewards/rejected": -9.330889701843262,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08634222919937205,
|
178 |
+
"grad_norm": 6.156201133938342,
|
179 |
+
"learning_rate": 4.2968749999999996e-07,
|
180 |
+
"logits/chosen": 6470.56884765625,
|
181 |
+
"logits/rejected": 5289.95849609375,
|
182 |
+
"logps/chosen": -188.42457580566406,
|
183 |
+
"logps/rejected": -190.61293029785156,
|
184 |
+
"loss": 1.9887,
|
185 |
+
"rewards/accuracies": 0.6666666865348816,
|
186 |
+
"rewards/chosen": -5.309735298156738,
|
187 |
+
"rewards/margins": 6.310976982116699,
|
188 |
+
"rewards/rejected": -11.620712280273438,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.09419152276295134,
|
193 |
+
"grad_norm": 8.999184508333663,
|
194 |
+
"learning_rate": 4.6874999999999996e-07,
|
195 |
+
"logits/chosen": 6397.328125,
|
196 |
+
"logits/rejected": 5324.27587890625,
|
197 |
+
"logps/chosen": -210.2899169921875,
|
198 |
+
"logps/rejected": -212.7317657470703,
|
199 |
+
"loss": 1.9865,
|
200 |
+
"rewards/accuracies": 0.6666666865348816,
|
201 |
+
"rewards/chosen": -7.453166961669922,
|
202 |
+
"rewards/margins": 7.11349630355835,
|
203 |
+
"rewards/rejected": -14.56666374206543,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.10204081632653061,
|
208 |
+
"grad_norm": 6.546135911338803,
|
209 |
+
"learning_rate": 4.999962424962166e-07,
|
210 |
+
"logits/chosen": 6333.814453125,
|
211 |
+
"logits/rejected": 5863.9287109375,
|
212 |
+
"logps/chosen": -215.83139038085938,
|
213 |
+
"logps/rejected": -212.8985137939453,
|
214 |
+
"loss": 1.9843,
|
215 |
+
"rewards/accuracies": 0.7083333730697632,
|
216 |
+
"rewards/chosen": -6.0229082107543945,
|
217 |
+
"rewards/margins": 9.231057167053223,
|
218 |
+
"rewards/rejected": -15.2539644241333,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.10989010989010989,
|
223 |
+
"grad_norm": 7.874723764445264,
|
224 |
+
"learning_rate": 4.998647417232375e-07,
|
225 |
+
"logits/chosen": 6198.4814453125,
|
226 |
+
"logits/rejected": 5459.091796875,
|
227 |
+
"logps/chosen": -195.5287628173828,
|
228 |
+
"logps/rejected": -197.17437744140625,
|
229 |
+
"loss": 1.983,
|
230 |
+
"rewards/accuracies": 0.6333333849906921,
|
231 |
+
"rewards/chosen": -9.861322402954102,
|
232 |
+
"rewards/margins": 9.721135139465332,
|
233 |
+
"rewards/rejected": -19.582454681396484,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.11773940345368916,
|
238 |
+
"grad_norm": 9.20471530543848,
|
239 |
+
"learning_rate": 4.995454786965036e-07,
|
240 |
+
"logits/chosen": 6376.53857421875,
|
241 |
+
"logits/rejected": 5328.8974609375,
|
242 |
+
"logps/chosen": -210.15576171875,
|
243 |
+
"logps/rejected": -192.92373657226562,
|
244 |
+
"loss": 1.98,
|
245 |
+
"rewards/accuracies": 0.7250000238418579,
|
246 |
+
"rewards/chosen": -8.471376419067383,
|
247 |
+
"rewards/margins": 12.154645919799805,
|
248 |
+
"rewards/rejected": -20.626020431518555,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.12558869701726844,
|
253 |
+
"grad_norm": 7.461193923622369,
|
254 |
+
"learning_rate": 4.990386933279972e-07,
|
255 |
+
"logits/chosen": 6318.7490234375,
|
256 |
+
"logits/rejected": 5644.8623046875,
|
257 |
+
"logps/chosen": -207.67337036132812,
|
258 |
+
"logps/rejected": -219.74203491210938,
|
259 |
+
"loss": 1.9794,
|
260 |
+
"rewards/accuracies": 0.7083333730697632,
|
261 |
+
"rewards/chosen": -10.14518928527832,
|
262 |
+
"rewards/margins": 12.539278984069824,
|
263 |
+
"rewards/rejected": -22.684467315673828,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.13343799058084774,
|
268 |
+
"grad_norm": 6.508017494074614,
|
269 |
+
"learning_rate": 4.983447664444096e-07,
|
270 |
+
"logits/chosen": 6519.24169921875,
|
271 |
+
"logits/rejected": 5813.3642578125,
|
272 |
+
"logps/chosen": -220.01766967773438,
|
273 |
+
"logps/rejected": -216.58914184570312,
|
274 |
+
"loss": 1.9806,
|
275 |
+
"rewards/accuracies": 0.6583333611488342,
|
276 |
+
"rewards/chosen": -10.396989822387695,
|
277 |
+
"rewards/margins": 9.870583534240723,
|
278 |
+
"rewards/rejected": -20.267574310302734,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.141287284144427,
|
283 |
+
"grad_norm": 7.695429851231189,
|
284 |
+
"learning_rate": 4.97464219500968e-07,
|
285 |
+
"logits/chosen": 5723.25439453125,
|
286 |
+
"logits/rejected": 5001.2041015625,
|
287 |
+
"logps/chosen": -198.26637268066406,
|
288 |
+
"logps/rejected": -199.6933135986328,
|
289 |
+
"loss": 1.977,
|
290 |
+
"rewards/accuracies": 0.6500000357627869,
|
291 |
+
"rewards/chosen": -9.738619804382324,
|
292 |
+
"rewards/margins": 11.793425559997559,
|
293 |
+
"rewards/rejected": -21.532047271728516,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.14913657770800628,
|
298 |
+
"grad_norm": 8.229494993248766,
|
299 |
+
"learning_rate": 4.963977141895843e-07,
|
300 |
+
"logits/chosen": 5866.8330078125,
|
301 |
+
"logits/rejected": 5040.8291015625,
|
302 |
+
"logps/chosen": -214.79452514648438,
|
303 |
+
"logps/rejected": -226.88827514648438,
|
304 |
+
"loss": 1.9734,
|
305 |
+
"rewards/accuracies": 0.7250000238418579,
|
306 |
+
"rewards/chosen": -11.035551071166992,
|
307 |
+
"rewards/margins": 24.613243103027344,
|
308 |
+
"rewards/rejected": -35.6487922668457,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.15698587127158556,
|
313 |
+
"grad_norm": 8.986914548041765,
|
314 |
+
"learning_rate": 4.951460519416227e-07,
|
315 |
+
"logits/chosen": 5760.6181640625,
|
316 |
+
"logits/rejected": 5327.140625,
|
317 |
+
"logps/chosen": -192.12252807617188,
|
318 |
+
"logps/rejected": -224.0847930908203,
|
319 |
+
"loss": 1.9722,
|
320 |
+
"rewards/accuracies": 0.7666667103767395,
|
321 |
+
"rewards/chosen": -9.578254699707031,
|
322 |
+
"rewards/margins": 17.835506439208984,
|
323 |
+
"rewards/rejected": -27.413761138916016,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16483516483516483,
|
328 |
+
"grad_norm": 11.60946438594492,
|
329 |
+
"learning_rate": 4.937101733256606e-07,
|
330 |
+
"logits/chosen": 5221.634765625,
|
331 |
+
"logits/rejected": 4657.677734375,
|
332 |
+
"logps/chosen": -167.0458984375,
|
333 |
+
"logps/rejected": -188.22262573242188,
|
334 |
+
"loss": 1.9736,
|
335 |
+
"rewards/accuracies": 0.6666667461395264,
|
336 |
+
"rewards/chosen": -13.132657051086426,
|
337 |
+
"rewards/margins": 17.90899085998535,
|
338 |
+
"rewards/rejected": -31.041645050048828,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1726844583987441,
|
343 |
+
"grad_norm": 13.95805192206325,
|
344 |
+
"learning_rate": 4.920911573406924e-07,
|
345 |
+
"logits/chosen": 6353.7783203125,
|
346 |
+
"logits/rejected": 5411.5087890625,
|
347 |
+
"logps/chosen": -207.0021514892578,
|
348 |
+
"logps/rejected": -192.39125061035156,
|
349 |
+
"loss": 1.97,
|
350 |
+
"rewards/accuracies": 0.7250000238418579,
|
351 |
+
"rewards/chosen": -10.665520668029785,
|
352 |
+
"rewards/margins": 17.728992462158203,
|
353 |
+
"rewards/rejected": -28.39451026916504,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.18053375196232338,
|
358 |
+
"grad_norm": 7.164170611764204,
|
359 |
+
"learning_rate": 4.902902206053098e-07,
|
360 |
+
"logits/chosen": 5817.7529296875,
|
361 |
+
"logits/rejected": 5253.7822265625,
|
362 |
+
"logps/chosen": -201.00804138183594,
|
363 |
+
"logps/rejected": -212.4803924560547,
|
364 |
+
"loss": 1.9743,
|
365 |
+
"rewards/accuracies": 0.675000011920929,
|
366 |
+
"rewards/chosen": -13.669303894042969,
|
367 |
+
"rewards/margins": 19.043621063232422,
|
368 |
+
"rewards/rejected": -32.71292495727539,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.18838304552590268,
|
373 |
+
"grad_norm": 11.660382561338869,
|
374 |
+
"learning_rate": 4.883087164434672e-07,
|
375 |
+
"logits/chosen": 5308.75634765625,
|
376 |
+
"logits/rejected": 4242.29345703125,
|
377 |
+
"logps/chosen": -174.8252716064453,
|
378 |
+
"logps/rejected": -180.3127899169922,
|
379 |
+
"loss": 1.9672,
|
380 |
+
"rewards/accuracies": 0.7750000357627869,
|
381 |
+
"rewards/chosen": -7.196226596832275,
|
382 |
+
"rewards/margins": 18.427143096923828,
|
383 |
+
"rewards/rejected": -25.623367309570312,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.19623233908948196,
|
388 |
+
"grad_norm": 8.72617485657044,
|
389 |
+
"learning_rate": 4.861481338675183e-07,
|
390 |
+
"logits/chosen": 6269.2236328125,
|
391 |
+
"logits/rejected": 5571.205078125,
|
392 |
+
"logps/chosen": -180.53604125976562,
|
393 |
+
"logps/rejected": -221.07125854492188,
|
394 |
+
"loss": 1.9743,
|
395 |
+
"rewards/accuracies": 0.6916667222976685,
|
396 |
+
"rewards/chosen": -13.392184257507324,
|
397 |
+
"rewards/margins": 23.172420501708984,
|
398 |
+
"rewards/rejected": -36.564598083496094,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.20408163265306123,
|
403 |
+
"grad_norm": 10.038046373183738,
|
404 |
+
"learning_rate": 4.838100964592904e-07,
|
405 |
+
"logits/chosen": 6411.8017578125,
|
406 |
+
"logits/rejected": 5188.3544921875,
|
407 |
+
"logps/chosen": -212.73208618164062,
|
408 |
+
"logps/rejected": -196.77479553222656,
|
409 |
+
"loss": 1.9814,
|
410 |
+
"rewards/accuracies": 0.699999988079071,
|
411 |
+
"rewards/chosen": -13.01362419128418,
|
412 |
+
"rewards/margins": 17.537227630615234,
|
413 |
+
"rewards/rejected": -30.550851821899414,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2119309262166405,
|
418 |
+
"grad_norm": 7.978893418055898,
|
419 |
+
"learning_rate": 4.812963611500339e-07,
|
420 |
+
"logits/chosen": 6247.86376953125,
|
421 |
+
"logits/rejected": 6049.94140625,
|
422 |
+
"logps/chosen": -206.0583038330078,
|
423 |
+
"logps/rejected": -213.51162719726562,
|
424 |
+
"loss": 1.962,
|
425 |
+
"rewards/accuracies": 0.6666666865348816,
|
426 |
+
"rewards/chosen": -9.302484512329102,
|
427 |
+
"rewards/margins": 15.580082893371582,
|
428 |
+
"rewards/rejected": -24.882568359375,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21978021978021978,
|
433 |
+
"grad_norm": 18.46477187944741,
|
434 |
+
"learning_rate": 4.786088169001671e-07,
|
435 |
+
"logits/chosen": 5388.15673828125,
|
436 |
+
"logits/rejected": 4686.12939453125,
|
437 |
+
"logps/chosen": -176.19607543945312,
|
438 |
+
"logps/rejected": -213.16305541992188,
|
439 |
+
"loss": 1.9659,
|
440 |
+
"rewards/accuracies": 0.7583333849906921,
|
441 |
+
"rewards/chosen": -13.045190811157227,
|
442 |
+
"rewards/margins": 30.816421508789062,
|
443 |
+
"rewards/rejected": -43.861610412597656,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.22762951334379905,
|
448 |
+
"grad_norm": 16.83181121684455,
|
449 |
+
"learning_rate": 4.7574948327980567e-07,
|
450 |
+
"logits/chosen": 7499.02490234375,
|
451 |
+
"logits/rejected": 5559.24609375,
|
452 |
+
"logps/chosen": -246.99514770507812,
|
453 |
+
"logps/rejected": -226.33572387695312,
|
454 |
+
"loss": 1.9613,
|
455 |
+
"rewards/accuracies": 0.7749999761581421,
|
456 |
+
"rewards/chosen": -9.966670036315918,
|
457 |
+
"rewards/margins": 33.853336334228516,
|
458 |
+
"rewards/rejected": -43.81999969482422,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.23547880690737832,
|
463 |
+
"grad_norm": 10.713215982695514,
|
464 |
+
"learning_rate": 4.727205089511466e-07,
|
465 |
+
"logits/chosen": 5454.79150390625,
|
466 |
+
"logits/rejected": 5429.51171875,
|
467 |
+
"logps/chosen": -181.81573486328125,
|
468 |
+
"logps/rejected": -206.89437866210938,
|
469 |
+
"loss": 1.975,
|
470 |
+
"rewards/accuracies": 0.6833333969116211,
|
471 |
+
"rewards/chosen": -14.343295097351074,
|
472 |
+
"rewards/margins": 22.364656448364258,
|
473 |
+
"rewards/rejected": -36.707950592041016,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.24332810047095763,
|
478 |
+
"grad_norm": 10.320663018292882,
|
479 |
+
"learning_rate": 4.6952417005384247e-07,
|
480 |
+
"logits/chosen": 6112.76806640625,
|
481 |
+
"logits/rejected": 5453.38134765625,
|
482 |
+
"logps/chosen": -185.7081298828125,
|
483 |
+
"logps/rejected": -200.83535766601562,
|
484 |
+
"loss": 1.9697,
|
485 |
+
"rewards/accuracies": 0.7666667699813843,
|
486 |
+
"rewards/chosen": -8.127434730529785,
|
487 |
+
"rewards/margins": 17.2396297454834,
|
488 |
+
"rewards/rejected": -25.367061614990234,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.25117739403453687,
|
493 |
+
"grad_norm": 10.476570210269244,
|
494 |
+
"learning_rate": 4.661628684945851e-07,
|
495 |
+
"logits/chosen": 6115.5517578125,
|
496 |
+
"logits/rejected": 5302.81689453125,
|
497 |
+
"logps/chosen": -209.9392852783203,
|
498 |
+
"logps/rejected": -239.3898468017578,
|
499 |
+
"loss": 1.964,
|
500 |
+
"rewards/accuracies": 0.675000011920929,
|
501 |
+
"rewards/chosen": -8.882265090942383,
|
502 |
+
"rewards/margins": 28.489694595336914,
|
503 |
+
"rewards/rejected": -37.37196350097656,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.25902668759811615,
|
508 |
+
"grad_norm": 8.453410137621447,
|
509 |
+
"learning_rate": 4.626391301421782e-07,
|
510 |
+
"logits/chosen": 5915.05224609375,
|
511 |
+
"logits/rejected": 5387.32177734375,
|
512 |
+
"logps/chosen": -203.82455444335938,
|
513 |
+
"logps/rejected": -205.4024200439453,
|
514 |
+
"loss": 1.9754,
|
515 |
+
"rewards/accuracies": 0.6833333373069763,
|
516 |
+
"rewards/chosen": -9.371356964111328,
|
517 |
+
"rewards/margins": 18.708255767822266,
|
518 |
+
"rewards/rejected": -28.079614639282227,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.2668759811616955,
|
523 |
+
"grad_norm": 7.101482635499888,
|
524 |
+
"learning_rate": 4.5895560292945996e-07,
|
525 |
+
"logits/chosen": 6163.81689453125,
|
526 |
+
"logits/rejected": 6304.29736328125,
|
527 |
+
"logps/chosen": -200.20118713378906,
|
528 |
+
"logps/rejected": -244.84848022460938,
|
529 |
+
"loss": 1.9674,
|
530 |
+
"rewards/accuracies": 0.6916667222976685,
|
531 |
+
"rewards/chosen": -6.342929363250732,
|
532 |
+
"rewards/margins": 18.13802719116211,
|
533 |
+
"rewards/rejected": -24.480958938598633,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.27472527472527475,
|
538 |
+
"grad_norm": 22.517967387414878,
|
539 |
+
"learning_rate": 4.5511505486349865e-07,
|
540 |
+
"logits/chosen": 6512.6396484375,
|
541 |
+
"logits/rejected": 5911.80859375,
|
542 |
+
"logps/chosen": -203.82406616210938,
|
543 |
+
"logps/rejected": -247.0866241455078,
|
544 |
+
"loss": 1.9653,
|
545 |
+
"rewards/accuracies": 0.7750000357627869,
|
546 |
+
"rewards/chosen": -8.998370170593262,
|
547 |
+
"rewards/margins": 31.266225814819336,
|
548 |
+
"rewards/rejected": -40.26459503173828,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.282574568288854,
|
553 |
+
"grad_norm": 10.024372865307708,
|
554 |
+
"learning_rate": 4.5112037194555876e-07,
|
555 |
+
"logits/chosen": 5994.025390625,
|
556 |
+
"logits/rejected": 5905.3828125,
|
557 |
+
"logps/chosen": -195.99481201171875,
|
558 |
+
"logps/rejected": -248.48153686523438,
|
559 |
+
"loss": 1.9671,
|
560 |
+
"rewards/accuracies": 0.7249999642372131,
|
561 |
+
"rewards/chosen": -18.07135772705078,
|
562 |
+
"rewards/margins": 31.128345489501953,
|
563 |
+
"rewards/rejected": -49.199703216552734,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2904238618524333,
|
568 |
+
"grad_norm": 9.19113626070318,
|
569 |
+
"learning_rate": 4.4697455600239863e-07,
|
570 |
+
"logits/chosen": 5450.50537109375,
|
571 |
+
"logits/rejected": 5144.671875,
|
572 |
+
"logps/chosen": -196.91354370117188,
|
573 |
+
"logps/rejected": -200.369873046875,
|
574 |
+
"loss": 1.9767,
|
575 |
+
"rewards/accuracies": 0.675000011920929,
|
576 |
+
"rewards/chosen": -12.49148941040039,
|
577 |
+
"rewards/margins": 19.807308197021484,
|
578 |
+
"rewards/rejected": -32.29880142211914,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.29827315541601257,
|
583 |
+
"grad_norm": 16.222088593597523,
|
584 |
+
"learning_rate": 4.426807224305315e-07,
|
585 |
+
"logits/chosen": 6513.00927734375,
|
586 |
+
"logits/rejected": 5406.20361328125,
|
587 |
+
"logps/chosen": -236.3499298095703,
|
588 |
+
"logps/rejected": -216.02804565429688,
|
589 |
+
"loss": 1.9675,
|
590 |
+
"rewards/accuracies": 0.7250000238418579,
|
591 |
+
"rewards/chosen": -8.00889778137207,
|
592 |
+
"rewards/margins": 25.009592056274414,
|
593 |
+
"rewards/rejected": -33.01848602294922,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.30612244897959184,
|
598 |
+
"grad_norm": 16.753657487210614,
|
599 |
+
"learning_rate": 4.3824209785514326e-07,
|
600 |
+
"logits/chosen": 6674.41259765625,
|
601 |
+
"logits/rejected": 5131.07373046875,
|
602 |
+
"logps/chosen": -222.05276489257812,
|
603 |
+
"logps/rejected": -223.5919647216797,
|
604 |
+
"loss": 1.9553,
|
605 |
+
"rewards/accuracies": 0.7750000357627869,
|
606 |
+
"rewards/chosen": -6.559300899505615,
|
607 |
+
"rewards/margins": 37.17955780029297,
|
608 |
+
"rewards/rejected": -43.73885726928711,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3139717425431711,
|
613 |
+
"grad_norm": 9.085445983363275,
|
614 |
+
"learning_rate": 4.3366201770542687e-07,
|
615 |
+
"logits/chosen": 5777.0849609375,
|
616 |
+
"logits/rejected": 5671.5537109375,
|
617 |
+
"logps/chosen": -201.79702758789062,
|
618 |
+
"logps/rejected": -225.7125701904297,
|
619 |
+
"loss": 1.9761,
|
620 |
+
"rewards/accuracies": 0.7250000238418579,
|
621 |
+
"rewards/chosen": -11.008450508117676,
|
622 |
+
"rewards/margins": 25.964609146118164,
|
623 |
+
"rewards/rejected": -36.973060607910156,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.3218210361067504,
|
628 |
+
"grad_norm": 11.33832444227533,
|
629 |
+
"learning_rate": 4.2894392370815567e-07,
|
630 |
+
"logits/chosen": 6256.8134765625,
|
631 |
+
"logits/rejected": 5594.1708984375,
|
632 |
+
"logps/chosen": -223.0230712890625,
|
633 |
+
"logps/rejected": -257.01385498046875,
|
634 |
+
"loss": 1.9476,
|
635 |
+
"rewards/accuracies": 0.7500000596046448,
|
636 |
+
"rewards/chosen": -10.536191940307617,
|
637 |
+
"rewards/margins": 38.025299072265625,
|
638 |
+
"rewards/rejected": -48.561485290527344,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.32967032967032966,
|
643 |
+
"grad_norm": 16.273251635067584,
|
644 |
+
"learning_rate": 4.2409136130137845e-07,
|
645 |
+
"logits/chosen": 5923.02880859375,
|
646 |
+
"logits/rejected": 5376.9443359375,
|
647 |
+
"logps/chosen": -220.4603729248047,
|
648 |
+
"logps/rejected": -229.0534210205078,
|
649 |
+
"loss": 1.969,
|
650 |
+
"rewards/accuracies": 0.7333333492279053,
|
651 |
+
"rewards/chosen": -16.430438995361328,
|
652 |
+
"rewards/margins": 31.381549835205078,
|
653 |
+
"rewards/rejected": -47.81198501586914,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.33751962323390894,
|
658 |
+
"grad_norm": 11.151359651562395,
|
659 |
+
"learning_rate": 4.1910797697018017e-07,
|
660 |
+
"logits/chosen": 5696.1357421875,
|
661 |
+
"logits/rejected": 4776.5791015625,
|
662 |
+
"logps/chosen": -192.7012939453125,
|
663 |
+
"logps/rejected": -203.29515075683594,
|
664 |
+
"loss": 1.9619,
|
665 |
+
"rewards/accuracies": 0.7333333492279053,
|
666 |
+
"rewards/chosen": -12.956321716308594,
|
667 |
+
"rewards/margins": 29.105701446533203,
|
668 |
+
"rewards/rejected": -42.06201934814453,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3453689167974882,
|
673 |
+
"grad_norm": 15.676627010168398,
|
674 |
+
"learning_rate": 4.1399751550651084e-07,
|
675 |
+
"logits/chosen": 6032.6103515625,
|
676 |
+
"logits/rejected": 5975.65869140625,
|
677 |
+
"logps/chosen": -194.45022583007812,
|
678 |
+
"logps/rejected": -232.76809692382812,
|
679 |
+
"loss": 1.9601,
|
680 |
+
"rewards/accuracies": 0.75,
|
681 |
+
"rewards/chosen": -12.056891441345215,
|
682 |
+
"rewards/margins": 29.027606964111328,
|
683 |
+
"rewards/rejected": -41.08449935913086,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3532182103610675,
|
688 |
+
"grad_norm": 11.418135496524267,
|
689 |
+
"learning_rate": 4.087638171951401e-07,
|
690 |
+
"logits/chosen": 6920.4697265625,
|
691 |
+
"logits/rejected": 5017.2001953125,
|
692 |
+
"logps/chosen": -218.02651977539062,
|
693 |
+
"logps/rejected": -215.5140838623047,
|
694 |
+
"loss": 1.9654,
|
695 |
+
"rewards/accuracies": 0.7749999761581421,
|
696 |
+
"rewards/chosen": -9.257742881774902,
|
697 |
+
"rewards/margins": 43.26369857788086,
|
698 |
+
"rewards/rejected": -52.52144241333008,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.36106750392464676,
|
703 |
+
"grad_norm": 9.738474609851922,
|
704 |
+
"learning_rate": 4.034108149278543e-07,
|
705 |
+
"logits/chosen": 7102.1494140625,
|
706 |
+
"logits/rejected": 5567.33251953125,
|
707 |
+
"logps/chosen": -262.5325622558594,
|
708 |
+
"logps/rejected": -226.304931640625,
|
709 |
+
"loss": 1.9647,
|
710 |
+
"rewards/accuracies": 0.7166666388511658,
|
711 |
+
"rewards/chosen": -12.100336074829102,
|
712 |
+
"rewards/margins": 23.9965763092041,
|
713 |
+
"rewards/rejected": -36.09691619873047,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.36891679748822603,
|
718 |
+
"grad_norm": 16.944485993230334,
|
719 |
+
"learning_rate": 3.979425312480629e-07,
|
720 |
+
"logits/chosen": 6121.8251953125,
|
721 |
+
"logits/rejected": 5385.27978515625,
|
722 |
+
"logps/chosen": -226.22708129882812,
|
723 |
+
"logps/rejected": -247.5476531982422,
|
724 |
+
"loss": 1.961,
|
725 |
+
"rewards/accuracies": 0.7416666746139526,
|
726 |
+
"rewards/chosen": -13.962315559387207,
|
727 |
+
"rewards/margins": 31.019052505493164,
|
728 |
+
"rewards/rejected": -44.98136520385742,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.37676609105180536,
|
733 |
+
"grad_norm": 10.061154653659795,
|
734 |
+
"learning_rate": 3.923630753280357e-07,
|
735 |
+
"logits/chosen": 6582.51708984375,
|
736 |
+
"logits/rejected": 5718.14208984375,
|
737 |
+
"logps/chosen": -220.9097900390625,
|
738 |
+
"logps/rejected": -222.513916015625,
|
739 |
+
"loss": 1.9678,
|
740 |
+
"rewards/accuracies": 0.8000000715255737,
|
741 |
+
"rewards/chosen": -13.514605522155762,
|
742 |
+
"rewards/margins": 34.60355758666992,
|
743 |
+
"rewards/rejected": -48.118160247802734,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.38461538461538464,
|
748 |
+
"grad_norm": 9.952729544567205,
|
749 |
+
"learning_rate": 3.866766398810424e-07,
|
750 |
+
"logits/chosen": 6168.904296875,
|
751 |
+
"logits/rejected": 5932.04833984375,
|
752 |
+
"logps/chosen": -181.2738494873047,
|
753 |
+
"logps/rejected": -238.46578979492188,
|
754 |
+
"loss": 1.9539,
|
755 |
+
"rewards/accuracies": 0.7916666269302368,
|
756 |
+
"rewards/chosen": -4.665351390838623,
|
757 |
+
"rewards/margins": 31.776134490966797,
|
758 |
+
"rewards/rejected": -36.44148635864258,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3924646781789639,
|
763 |
+
"grad_norm": 10.886191142069716,
|
764 |
+
"learning_rate": 3.8088749801071496e-07,
|
765 |
+
"logits/chosen": 6751.1181640625,
|
766 |
+
"logits/rejected": 5237.1748046875,
|
767 |
+
"logps/chosen": -239.8447723388672,
|
768 |
+
"logps/rejected": -258.9305725097656,
|
769 |
+
"loss": 1.9645,
|
770 |
+
"rewards/accuracies": 0.6833333373069763,
|
771 |
+
"rewards/chosen": -17.89109230041504,
|
772 |
+
"rewards/margins": 38.52326202392578,
|
773 |
+
"rewards/rejected": -56.41435623168945,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4003139717425432,
|
778 |
+
"grad_norm": 12.12571996214556,
|
779 |
+
"learning_rate": 3.75e-07,
|
780 |
+
"logits/chosen": 5390.6787109375,
|
781 |
+
"logits/rejected": 4790.146484375,
|
782 |
+
"logps/chosen": -199.76528930664062,
|
783 |
+
"logps/rejected": -217.97457885742188,
|
784 |
+
"loss": 1.9639,
|
785 |
+
"rewards/accuracies": 0.8166666030883789,
|
786 |
+
"rewards/chosen": -10.282281875610352,
|
787 |
+
"rewards/margins": 41.32698440551758,
|
788 |
+
"rewards/rejected": -51.60927200317383,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.40816326530612246,
|
793 |
+
"grad_norm": 9.519450563259452,
|
794 |
+
"learning_rate": 3.6901857004211443e-07,
|
795 |
+
"logits/chosen": 5713.3515625,
|
796 |
+
"logits/rejected": 5326.962890625,
|
797 |
+
"logps/chosen": -212.322998046875,
|
798 |
+
"logps/rejected": -235.4215850830078,
|
799 |
+
"loss": 1.9753,
|
800 |
+
"rewards/accuracies": 0.6916667222976685,
|
801 |
+
"rewards/chosen": -13.85698127746582,
|
802 |
+
"rewards/margins": 25.776592254638672,
|
803 |
+
"rewards/rejected": -39.63357925415039,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.41601255886970173,
|
808 |
+
"grad_norm": 9.888104468321709,
|
809 |
+
"learning_rate": 3.6294770291596076e-07,
|
810 |
+
"logits/chosen": 6448.71337890625,
|
811 |
+
"logits/rejected": 5332.93701171875,
|
812 |
+
"logps/chosen": -219.8802947998047,
|
813 |
+
"logps/rejected": -227.52792358398438,
|
814 |
+
"loss": 1.9559,
|
815 |
+
"rewards/accuracies": 0.7250000238418579,
|
816 |
+
"rewards/chosen": -6.957555294036865,
|
817 |
+
"rewards/margins": 21.810047149658203,
|
818 |
+
"rewards/rejected": -28.767602920532227,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.423861852433281,
|
823 |
+
"grad_norm": 32.92673172258904,
|
824 |
+
"learning_rate": 3.5679196060850034e-07,
|
825 |
+
"logits/chosen": 6134.5771484375,
|
826 |
+
"logits/rejected": 5512.7548828125,
|
827 |
+
"logps/chosen": -224.2685089111328,
|
828 |
+
"logps/rejected": -235.88308715820312,
|
829 |
+
"loss": 1.9648,
|
830 |
+
"rewards/accuracies": 0.7416666746139526,
|
831 |
+
"rewards/chosen": -13.450671195983887,
|
832 |
+
"rewards/margins": 34.19359588623047,
|
833 |
+
"rewards/rejected": -47.64427185058594,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.4317111459968603,
|
838 |
+
"grad_norm": 10.505039462285955,
|
839 |
+
"learning_rate": 3.505559688866229e-07,
|
840 |
+
"logits/chosen": 5928.0751953125,
|
841 |
+
"logits/rejected": 5549.6640625,
|
842 |
+
"logps/chosen": -229.20504760742188,
|
843 |
+
"logps/rejected": -271.86517333984375,
|
844 |
+
"loss": 1.9554,
|
845 |
+
"rewards/accuracies": 0.7416666746139526,
|
846 |
+
"rewards/chosen": -14.464628219604492,
|
847 |
+
"rewards/margins": 32.33644485473633,
|
848 |
+
"rewards/rejected": -46.80107498168945,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.43956043956043955,
|
853 |
+
"grad_norm": 10.28700128076687,
|
854 |
+
"learning_rate": 3.4424441382108826e-07,
|
855 |
+
"logits/chosen": 5985.54833984375,
|
856 |
+
"logits/rejected": 5623.6748046875,
|
857 |
+
"logps/chosen": -218.4139862060547,
|
858 |
+
"logps/rejected": -238.92288208007812,
|
859 |
+
"loss": 1.9712,
|
860 |
+
"rewards/accuracies": 0.6833333373069763,
|
861 |
+
"rewards/chosen": -15.138700485229492,
|
862 |
+
"rewards/margins": 30.574970245361328,
|
863 |
+
"rewards/rejected": -45.71367263793945,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.4474097331240188,
|
868 |
+
"grad_norm": 15.423527438178777,
|
869 |
+
"learning_rate": 3.378620382651523e-07,
|
870 |
+
"logits/chosen": 6308.0498046875,
|
871 |
+
"logits/rejected": 5838.08056640625,
|
872 |
+
"logps/chosen": -258.34332275390625,
|
873 |
+
"logps/rejected": -273.0830383300781,
|
874 |
+
"loss": 1.9588,
|
875 |
+
"rewards/accuracies": 0.7583333253860474,
|
876 |
+
"rewards/chosen": -15.38349437713623,
|
877 |
+
"rewards/margins": 33.929012298583984,
|
878 |
+
"rewards/rejected": -49.3125114440918,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4552590266875981,
|
883 |
+
"grad_norm": 14.611083089156338,
|
884 |
+
"learning_rate": 3.314136382905234e-07,
|
885 |
+
"logits/chosen": 6261.64453125,
|
886 |
+
"logits/rejected": 5689.3505859375,
|
887 |
+
"logps/chosen": -222.60165405273438,
|
888 |
+
"logps/rejected": -264.10699462890625,
|
889 |
+
"loss": 1.9673,
|
890 |
+
"rewards/accuracies": 0.7666666507720947,
|
891 |
+
"rewards/chosen": -10.186196327209473,
|
892 |
+
"rewards/margins": 40.609474182128906,
|
893 |
+
"rewards/rejected": -50.79567337036133,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.4631083202511774,
|
898 |
+
"grad_norm": 14.179147587086423,
|
899 |
+
"learning_rate": 3.249040595833274e-07,
|
900 |
+
"logits/chosen": 6810.31884765625,
|
901 |
+
"logits/rejected": 5779.87451171875,
|
902 |
+
"logps/chosen": -244.0528564453125,
|
903 |
+
"logps/rejected": -228.9059600830078,
|
904 |
+
"loss": 1.9497,
|
905 |
+
"rewards/accuracies": 0.7749999761581421,
|
906 |
+
"rewards/chosen": -12.326987266540527,
|
907 |
+
"rewards/margins": 37.720115661621094,
|
908 |
+
"rewards/rejected": -50.0471076965332,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.47095761381475665,
|
913 |
+
"grad_norm": 19.155016516986336,
|
914 |
+
"learning_rate": 3.1833819380279023e-07,
|
915 |
+
"logits/chosen": 6452.5693359375,
|
916 |
+
"logits/rejected": 5529.4580078125,
|
917 |
+
"logps/chosen": -190.16168212890625,
|
918 |
+
"logps/rejected": -239.14492797851562,
|
919 |
+
"loss": 1.9536,
|
920 |
+
"rewards/accuracies": 0.7750000357627869,
|
921 |
+
"rewards/chosen": -12.613371849060059,
|
922 |
+
"rewards/margins": 36.84527587890625,
|
923 |
+
"rewards/rejected": -49.458648681640625,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.478806907378336,
|
928 |
+
"grad_norm": 13.224856834760333,
|
929 |
+
"learning_rate": 3.11720974905373e-07,
|
930 |
+
"logits/chosen": 6204.62841796875,
|
931 |
+
"logits/rejected": 5447.55419921875,
|
932 |
+
"logps/chosen": -216.75570678710938,
|
933 |
+
"logps/rejected": -233.86032104492188,
|
934 |
+
"loss": 1.9449,
|
935 |
+
"rewards/accuracies": 0.7416666746139526,
|
936 |
+
"rewards/chosen": -10.637582778930664,
|
937 |
+
"rewards/margins": 37.80018997192383,
|
938 |
+
"rewards/rejected": -48.437767028808594,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.48665620094191525,
|
943 |
+
"grad_norm": 17.52069876117691,
|
944 |
+
"learning_rate": 3.0505737543712275e-07,
|
945 |
+
"logits/chosen": 5294.59375,
|
946 |
+
"logits/rejected": 4387.63818359375,
|
947 |
+
"logps/chosen": -196.4014129638672,
|
948 |
+
"logps/rejected": -210.00869750976562,
|
949 |
+
"loss": 1.9549,
|
950 |
+
"rewards/accuracies": 0.7916666269302368,
|
951 |
+
"rewards/chosen": -12.642759323120117,
|
952 |
+
"rewards/margins": 36.267051696777344,
|
953 |
+
"rewards/rejected": -48.909812927246094,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4945054945054945,
|
958 |
+
"grad_norm": 33.05264787102616,
|
959 |
+
"learning_rate": 2.9835240279702513e-07,
|
960 |
+
"logits/chosen": 6885.4189453125,
|
961 |
+
"logits/rejected": 5920.83056640625,
|
962 |
+
"logps/chosen": -251.9607696533203,
|
963 |
+
"logps/rejected": -256.430908203125,
|
964 |
+
"loss": 1.9577,
|
965 |
+
"rewards/accuracies": 0.7916666269302368,
|
966 |
+
"rewards/chosen": -9.144782066345215,
|
967 |
+
"rewards/margins": 53.038055419921875,
|
968 |
+
"rewards/rejected": -62.182838439941406,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.5023547880690737,
|
973 |
+
"grad_norm": 13.271843782155607,
|
974 |
+
"learning_rate": 2.9161109547416667e-07,
|
975 |
+
"logits/chosen": 6548.42822265625,
|
976 |
+
"logits/rejected": 5635.82861328125,
|
977 |
+
"logps/chosen": -226.5624542236328,
|
978 |
+
"logps/rejected": -251.34622192382812,
|
979 |
+
"loss": 1.9503,
|
980 |
+
"rewards/accuracies": 0.6916666626930237,
|
981 |
+
"rewards/chosen": -15.800863265991211,
|
982 |
+
"rewards/margins": 21.036413192749023,
|
983 |
+
"rewards/rejected": -36.837284088134766,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.5102040816326531,
|
988 |
+
"grad_norm": 15.831220822034595,
|
989 |
+
"learning_rate": 2.848385192615339e-07,
|
990 |
+
"logits/chosen": 5647.466796875,
|
991 |
+
"logits/rejected": 4650.84326171875,
|
992 |
+
"logps/chosen": -208.1371612548828,
|
993 |
+
"logps/rejected": -215.1590118408203,
|
994 |
+
"loss": 1.9581,
|
995 |
+
"rewards/accuracies": 0.800000011920929,
|
996 |
+
"rewards/chosen": -11.797808647155762,
|
997 |
+
"rewards/margins": 34.633445739746094,
|
998 |
+
"rewards/rejected": -46.431251525878906,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5180533751962323,
|
1003 |
+
"grad_norm": 11.97405793704744,
|
1004 |
+
"learning_rate": 2.780397634492949e-07,
|
1005 |
+
"logits/chosen": 6318.73193359375,
|
1006 |
+
"logits/rejected": 5105.6806640625,
|
1007 |
+
"logps/chosen": -228.73629760742188,
|
1008 |
+
"logps/rejected": -247.58203125,
|
1009 |
+
"loss": 1.9628,
|
1010 |
+
"rewards/accuracies": 0.8166667222976685,
|
1011 |
+
"rewards/chosen": -11.349790573120117,
|
1012 |
+
"rewards/margins": 48.284786224365234,
|
1013 |
+
"rewards/rejected": -59.63458251953125,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5259026687598116,
|
1018 |
+
"grad_norm": 15.694525160199404,
|
1019 |
+
"learning_rate": 2.71219937000424e-07,
|
1020 |
+
"logits/chosen": 6305.85546875,
|
1021 |
+
"logits/rejected": 5219.8154296875,
|
1022 |
+
"logps/chosen": -218.81637573242188,
|
1023 |
+
"logps/rejected": -233.28933715820312,
|
1024 |
+
"loss": 1.9636,
|
1025 |
+
"rewards/accuracies": 0.7583333253860474,
|
1026 |
+
"rewards/chosen": -12.056918144226074,
|
1027 |
+
"rewards/margins": 32.37800216674805,
|
1028 |
+
"rewards/rejected": -44.4349250793457,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.533751962323391,
|
1033 |
+
"grad_norm": 12.2450633413355,
|
1034 |
+
"learning_rate": 2.6438416471154273e-07,
|
1035 |
+
"logits/chosen": 6118.7060546875,
|
1036 |
+
"logits/rejected": 5147.07470703125,
|
1037 |
+
"logps/chosen": -223.75503540039062,
|
1038 |
+
"logps/rejected": -228.0189971923828,
|
1039 |
+
"loss": 1.9541,
|
1040 |
+
"rewards/accuracies": 0.75,
|
1041 |
+
"rewards/chosen": -10.093757629394531,
|
1042 |
+
"rewards/margins": 38.698543548583984,
|
1043 |
+
"rewards/rejected": -48.79230499267578,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.5416012558869702,
|
1048 |
+
"grad_norm": 13.662534533205077,
|
1049 |
+
"learning_rate": 2.5753758336186326e-07,
|
1050 |
+
"logits/chosen": 6057.73046875,
|
1051 |
+
"logits/rejected": 5582.77783203125,
|
1052 |
+
"logps/chosen": -225.1211700439453,
|
1053 |
+
"logps/rejected": -271.24847412109375,
|
1054 |
+
"loss": 1.9559,
|
1055 |
+
"rewards/accuracies": 0.7583333849906921,
|
1056 |
+
"rewards/chosen": -16.014719009399414,
|
1057 |
+
"rewards/margins": 39.03708267211914,
|
1058 |
+
"rewards/rejected": -55.051795959472656,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5494505494505495,
|
1063 |
+
"grad_norm": 20.150978172477505,
|
1064 |
+
"learning_rate": 2.5068533785312666e-07,
|
1065 |
+
"logits/chosen": 5760.0908203125,
|
1066 |
+
"logits/rejected": 5564.3642578125,
|
1067 |
+
"logps/chosen": -206.0763702392578,
|
1068 |
+
"logps/rejected": -243.00936889648438,
|
1069 |
+
"loss": 1.9826,
|
1070 |
+
"rewards/accuracies": 0.7333332896232605,
|
1071 |
+
"rewards/chosen": -16.816057205200195,
|
1072 |
+
"rewards/margins": 39.219337463378906,
|
1073 |
+
"rewards/rejected": -56.03539276123047,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.5572998430141287,
|
1078 |
+
"grad_norm": 13.452123278177462,
|
1079 |
+
"learning_rate": 2.4383257734343794e-07,
|
1080 |
+
"logits/chosen": 5708.1435546875,
|
1081 |
+
"logits/rejected": 5760.40869140625,
|
1082 |
+
"logps/chosen": -205.77761840820312,
|
1083 |
+
"logps/rejected": -244.1310577392578,
|
1084 |
+
"loss": 1.956,
|
1085 |
+
"rewards/accuracies": 0.7916666269302368,
|
1086 |
+
"rewards/chosen": -11.866220474243164,
|
1087 |
+
"rewards/margins": 29.644180297851562,
|
1088 |
+
"rewards/rejected": -41.510398864746094,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.565149136577708,
|
1093 |
+
"grad_norm": 9.709598082836985,
|
1094 |
+
"learning_rate": 2.3698445137790258e-07,
|
1095 |
+
"logits/chosen": 6114.9091796875,
|
1096 |
+
"logits/rejected": 5311.08251953125,
|
1097 |
+
"logps/chosen": -227.6648406982422,
|
1098 |
+
"logps/rejected": -236.38330078125,
|
1099 |
+
"loss": 1.9662,
|
1100 |
+
"rewards/accuracies": 0.7666666507720947,
|
1101 |
+
"rewards/chosen": -8.66163158416748,
|
1102 |
+
"rewards/margins": 27.956518173217773,
|
1103 |
+
"rewards/rejected": -36.61814880371094,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5729984301412873,
|
1108 |
+
"grad_norm": 12.868770235170873,
|
1109 |
+
"learning_rate": 2.3014610601897157e-07,
|
1110 |
+
"logits/chosen": 6644.2060546875,
|
1111 |
+
"logits/rejected": 5136.859375,
|
1112 |
+
"logps/chosen": -238.3865966796875,
|
1113 |
+
"logps/rejected": -222.13784790039062,
|
1114 |
+
"loss": 1.9514,
|
1115 |
+
"rewards/accuracies": 0.7250000238418579,
|
1116 |
+
"rewards/chosen": -13.240676879882812,
|
1117 |
+
"rewards/margins": 33.82345199584961,
|
1118 |
+
"rewards/rejected": -47.06413650512695,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5808477237048666,
|
1123 |
+
"grad_norm": 15.41698862667205,
|
1124 |
+
"learning_rate": 2.2332267997940513e-07,
|
1125 |
+
"logits/chosen": 5527.283203125,
|
1126 |
+
"logits/rejected": 4719.14013671875,
|
1127 |
+
"logps/chosen": -203.3306427001953,
|
1128 |
+
"logps/rejected": -216.73959350585938,
|
1129 |
+
"loss": 1.9527,
|
1130 |
+
"rewards/accuracies": 0.7749999761581421,
|
1131 |
+
"rewards/chosen": -10.906192779541016,
|
1132 |
+
"rewards/margins": 43.1873664855957,
|
1133 |
+
"rewards/rejected": -54.09355545043945,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5886970172684458,
|
1138 |
+
"grad_norm": 13.318035652689497,
|
1139 |
+
"learning_rate": 2.1651930076075723e-07,
|
1140 |
+
"logits/chosen": 6021.62890625,
|
1141 |
+
"logits/rejected": 5484.7626953125,
|
1142 |
+
"logps/chosen": -193.93162536621094,
|
1143 |
+
"logps/rejected": -213.35128784179688,
|
1144 |
+
"loss": 1.9612,
|
1145 |
+
"rewards/accuracies": 0.7000000476837158,
|
1146 |
+
"rewards/chosen": -13.50567626953125,
|
1147 |
+
"rewards/margins": 32.751338958740234,
|
1148 |
+
"rewards/rejected": -46.25701141357422,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.5965463108320251,
|
1153 |
+
"grad_norm": 17.96255248447627,
|
1154 |
+
"learning_rate": 2.0974108080028692e-07,
|
1155 |
+
"logits/chosen": 6310.85986328125,
|
1156 |
+
"logits/rejected": 5030.54736328125,
|
1157 |
+
"logps/chosen": -213.32278442382812,
|
1158 |
+
"logps/rejected": -214.3714599609375,
|
1159 |
+
"loss": 1.9636,
|
1160 |
+
"rewards/accuracies": 0.7000000476837158,
|
1161 |
+
"rewards/chosen": -10.071836471557617,
|
1162 |
+
"rewards/margins": 29.769107818603516,
|
1163 |
+
"rewards/rejected": -39.8409423828125,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6043956043956044,
|
1168 |
+
"grad_norm": 22.574869511207616,
|
1169 |
+
"learning_rate": 2.0299311362918773e-07,
|
1170 |
+
"logits/chosen": 6518.14404296875,
|
1171 |
+
"logits/rejected": 5643.26220703125,
|
1172 |
+
"logps/chosen": -245.22970581054688,
|
1173 |
+
"logps/rejected": -276.74285888671875,
|
1174 |
+
"loss": 1.9681,
|
1175 |
+
"rewards/accuracies": 0.7166666984558105,
|
1176 |
+
"rewards/chosen": -15.496047973632812,
|
1177 |
+
"rewards/margins": 37.38671112060547,
|
1178 |
+
"rewards/rejected": -52.88275909423828,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6122448979591837,
|
1183 |
+
"grad_norm": 31.521005261418978,
|
1184 |
+
"learning_rate": 1.962804700450265e-07,
|
1185 |
+
"logits/chosen": 6350.6767578125,
|
1186 |
+
"logits/rejected": 6074.388671875,
|
1187 |
+
"logps/chosen": -227.0453643798828,
|
1188 |
+
"logps/rejected": -277.8321838378906,
|
1189 |
+
"loss": 1.9662,
|
1190 |
+
"rewards/accuracies": 0.7416666746139526,
|
1191 |
+
"rewards/chosen": -10.940030097961426,
|
1192 |
+
"rewards/margins": 29.504467010498047,
|
1193 |
+
"rewards/rejected": -40.44449996948242,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.6200941915227629,
|
1198 |
+
"grad_norm": 19.737346143715538,
|
1199 |
+
"learning_rate": 1.8960819430126334e-07,
|
1200 |
+
"logits/chosen": 5919.3037109375,
|
1201 |
+
"logits/rejected": 5263.5703125,
|
1202 |
+
"logps/chosen": -215.43441772460938,
|
1203 |
+
"logps/rejected": -249.7850799560547,
|
1204 |
+
"loss": 1.9556,
|
1205 |
+
"rewards/accuracies": 0.7333333492279053,
|
1206 |
+
"rewards/chosen": -17.30341148376465,
|
1207 |
+
"rewards/margins": 43.883941650390625,
|
1208 |
+
"rewards/rejected": -61.187347412109375,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.6279434850863422,
|
1213 |
+
"grad_norm": 18.29038936836771,
|
1214 |
+
"learning_rate": 1.8298130031671972e-07,
|
1215 |
+
"logits/chosen": 5920.49365234375,
|
1216 |
+
"logits/rejected": 5215.0712890625,
|
1217 |
+
"logps/chosen": -233.1874542236328,
|
1218 |
+
"logps/rejected": -261.2085266113281,
|
1219 |
+
"loss": 1.9726,
|
1220 |
+
"rewards/accuracies": 0.7416666746139526,
|
1221 |
+
"rewards/chosen": -16.46460723876953,
|
1222 |
+
"rewards/margins": 32.04566192626953,
|
1223 |
+
"rewards/rejected": -48.5102653503418,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6357927786499215,
|
1228 |
+
"grad_norm": 12.137685601024057,
|
1229 |
+
"learning_rate": 1.7640476790784075e-07,
|
1230 |
+
"logits/chosen": 5467.83251953125,
|
1231 |
+
"logits/rejected": 4939.65087890625,
|
1232 |
+
"logps/chosen": -212.20767211914062,
|
1233 |
+
"logps/rejected": -267.3034973144531,
|
1234 |
+
"loss": 1.9569,
|
1235 |
+
"rewards/accuracies": 0.7583333253860474,
|
1236 |
+
"rewards/chosen": -9.752274513244629,
|
1237 |
+
"rewards/margins": 36.25393295288086,
|
1238 |
+
"rewards/rejected": -46.00621032714844,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.6436420722135008,
|
1243 |
+
"grad_norm": 13.63770692303666,
|
1244 |
+
"learning_rate": 1.6988353904658492e-07,
|
1245 |
+
"logits/chosen": 5939.91552734375,
|
1246 |
+
"logits/rejected": 4631.35205078125,
|
1247 |
+
"logps/chosen": -229.2455291748047,
|
1248 |
+
"logps/rejected": -209.6826629638672,
|
1249 |
+
"loss": 1.9476,
|
1250 |
+
"rewards/accuracies": 0.7916666269302368,
|
1251 |
+
"rewards/chosen": -8.030985832214355,
|
1252 |
+
"rewards/margins": 32.963321685791016,
|
1253 |
+
"rewards/rejected": -40.99430465698242,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.6514913657770801,
|
1258 |
+
"grad_norm": 35.3592513671855,
|
1259 |
+
"learning_rate": 1.634225141467513e-07,
|
1260 |
+
"logits/chosen": 5885.0146484375,
|
1261 |
+
"logits/rejected": 5291.1865234375,
|
1262 |
+
"logps/chosen": -221.3533172607422,
|
1263 |
+
"logps/rejected": -254.42501831054688,
|
1264 |
+
"loss": 1.9561,
|
1265 |
+
"rewards/accuracies": 0.73333340883255,
|
1266 |
+
"rewards/chosen": -17.167299270629883,
|
1267 |
+
"rewards/margins": 44.80288314819336,
|
1268 |
+
"rewards/rejected": -61.97017288208008,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6593406593406593,
|
1273 |
+
"grad_norm": 10.761005849291488,
|
1274 |
+
"learning_rate": 1.570265483815364e-07,
|
1275 |
+
"logits/chosen": 6429.474609375,
|
1276 |
+
"logits/rejected": 5307.4501953125,
|
1277 |
+
"logps/chosen": -245.8719024658203,
|
1278 |
+
"logps/rejected": -261.5577087402344,
|
1279 |
+
"loss": 1.9591,
|
1280 |
+
"rewards/accuracies": 0.6833333373069763,
|
1281 |
+
"rewards/chosen": -18.54207420349121,
|
1282 |
+
"rewards/margins": 30.222482681274414,
|
1283 |
+
"rewards/rejected": -48.764556884765625,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.6671899529042387,
|
1288 |
+
"grad_norm": 16.29666584290201,
|
1289 |
+
"learning_rate": 1.5070044803508691e-07,
|
1290 |
+
"logits/chosen": 5947.8916015625,
|
1291 |
+
"logits/rejected": 5381.05810546875,
|
1292 |
+
"logps/chosen": -227.6597900390625,
|
1293 |
+
"logps/rejected": -256.93426513671875,
|
1294 |
+
"loss": 1.9444,
|
1295 |
+
"rewards/accuracies": 0.7750000357627869,
|
1296 |
+
"rewards/chosen": -12.182321548461914,
|
1297 |
+
"rewards/margins": 44.29661560058594,
|
1298 |
+
"rewards/rejected": -56.47894287109375,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.6750392464678179,
|
1303 |
+
"grad_norm": 14.229262245757536,
|
1304 |
+
"learning_rate": 1.444489668907914e-07,
|
1305 |
+
"logits/chosen": 6413.134765625,
|
1306 |
+
"logits/rejected": 5485.0712890625,
|
1307 |
+
"logps/chosen": -259.97039794921875,
|
1308 |
+
"logps/rejected": -254.68661499023438,
|
1309 |
+
"loss": 1.9651,
|
1310 |
+
"rewards/accuracies": 0.7666667103767395,
|
1311 |
+
"rewards/chosen": -12.199740409851074,
|
1312 |
+
"rewards/margins": 39.80502700805664,
|
1313 |
+
"rewards/rejected": -52.00476837158203,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6828885400313972,
|
1318 |
+
"grad_norm": 14.985139051030577,
|
1319 |
+
"learning_rate": 1.3827680265902232e-07,
|
1320 |
+
"logits/chosen": 6375.4150390625,
|
1321 |
+
"logits/rejected": 5318.18603515625,
|
1322 |
+
"logps/chosen": -241.5561065673828,
|
1323 |
+
"logps/rejected": -245.6100616455078,
|
1324 |
+
"loss": 1.9577,
|
1325 |
+
"rewards/accuracies": 0.7750000357627869,
|
1326 |
+
"rewards/chosen": -11.459368705749512,
|
1327 |
+
"rewards/margins": 33.461753845214844,
|
1328 |
+
"rewards/rejected": -44.92112731933594,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6907378335949764,
|
1333 |
+
"grad_norm": 21.012999888781128,
|
1334 |
+
"learning_rate": 1.3218859344701632e-07,
|
1335 |
+
"logits/chosen": 5609.716796875,
|
1336 |
+
"logits/rejected": 5388.8818359375,
|
1337 |
+
"logps/chosen": -221.8362579345703,
|
1338 |
+
"logps/rejected": -279.399658203125,
|
1339 |
+
"loss": 1.9613,
|
1340 |
+
"rewards/accuracies": 0.7666666507720947,
|
1341 |
+
"rewards/chosen": -11.325273513793945,
|
1342 |
+
"rewards/margins": 36.48521423339844,
|
1343 |
+
"rewards/rejected": -47.81048583984375,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6985871271585558,
|
1348 |
+
"grad_norm": 16.069902059846896,
|
1349 |
+
"learning_rate": 1.2618891427354172e-07,
|
1350 |
+
"logits/chosen": 6615.9248046875,
|
1351 |
+
"logits/rejected": 5418.08447265625,
|
1352 |
+
"logps/chosen": -268.32244873046875,
|
1353 |
+
"logps/rejected": -266.2985534667969,
|
1354 |
+
"loss": 1.9596,
|
1355 |
+
"rewards/accuracies": 0.7999999523162842,
|
1356 |
+
"rewards/chosen": -10.72636890411377,
|
1357 |
+
"rewards/margins": 43.791648864746094,
|
1358 |
+
"rewards/rejected": -54.51801681518555,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.706436420722135,
|
1363 |
+
"grad_norm": 14.83296947009343,
|
1364 |
+
"learning_rate": 1.202822736309758e-07,
|
1365 |
+
"logits/chosen": 5605.28662109375,
|
1366 |
+
"logits/rejected": 5226.92236328125,
|
1367 |
+
"logps/chosen": -214.8007049560547,
|
1368 |
+
"logps/rejected": -256.61541748046875,
|
1369 |
+
"loss": 1.9601,
|
1370 |
+
"rewards/accuracies": 0.7583333253860474,
|
1371 |
+
"rewards/chosen": -10.451518058776855,
|
1372 |
+
"rewards/margins": 35.73381805419922,
|
1373 |
+
"rewards/rejected": -46.185333251953125,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7142857142857143,
|
1378 |
+
"grad_norm": 16.04357761307859,
|
1379 |
+
"learning_rate": 1.1447311009737299e-07,
|
1380 |
+
"logits/chosen": 5512.8681640625,
|
1381 |
+
"logits/rejected": 5264.71142578125,
|
1382 |
+
"logps/chosen": -220.86276245117188,
|
1383 |
+
"logps/rejected": -260.4016418457031,
|
1384 |
+
"loss": 1.9546,
|
1385 |
+
"rewards/accuracies": 0.7666667103767395,
|
1386 |
+
"rewards/chosen": -12.636472702026367,
|
1387 |
+
"rewards/margins": 39.836666107177734,
|
1388 |
+
"rewards/rejected": -52.47313690185547,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.7221350078492935,
|
1393 |
+
"grad_norm": 11.14000447509858,
|
1394 |
+
"learning_rate": 1.0876578900107053e-07,
|
1395 |
+
"logits/chosen": 6096.97314453125,
|
1396 |
+
"logits/rejected": 5090.04052734375,
|
1397 |
+
"logps/chosen": -245.5460968017578,
|
1398 |
+
"logps/rejected": -248.48770141601562,
|
1399 |
+
"loss": 1.9524,
|
1400 |
+
"rewards/accuracies": 0.800000011920929,
|
1401 |
+
"rewards/chosen": -13.124479293823242,
|
1402 |
+
"rewards/margins": 37.220909118652344,
|
1403 |
+
"rewards/rejected": -50.34539031982422,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.7299843014128728,
|
1408 |
+
"grad_norm": 15.02248631232516,
|
1409 |
+
"learning_rate": 1.0316459914033793e-07,
|
1410 |
+
"logits/chosen": 6012.04833984375,
|
1411 |
+
"logits/rejected": 4572.67333984375,
|
1412 |
+
"logps/chosen": -253.6759796142578,
|
1413 |
+
"logps/rejected": -244.62939453125,
|
1414 |
+
"loss": 1.9584,
|
1415 |
+
"rewards/accuracies": 0.7499999403953552,
|
1416 |
+
"rewards/chosen": -17.687047958374023,
|
1417 |
+
"rewards/margins": 41.01814651489258,
|
1418 |
+
"rewards/rejected": -58.70519256591797,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.7378335949764521,
|
1423 |
+
"grad_norm": 14.78768614756301,
|
1424 |
+
"learning_rate": 9.767374956053584e-08,
|
1425 |
+
"logits/chosen": 5824.52392578125,
|
1426 |
+
"logits/rejected": 5130.29150390625,
|
1427 |
+
"logps/chosen": -231.50732421875,
|
1428 |
+
"logps/rejected": -265.863525390625,
|
1429 |
+
"loss": 1.9506,
|
1430 |
+
"rewards/accuracies": 0.75,
|
1431 |
+
"rewards/chosen": -13.213656425476074,
|
1432 |
+
"rewards/margins": 47.669952392578125,
|
1433 |
+
"rewards/rejected": -60.88360595703125,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7456828885400314,
|
1438 |
+
"grad_norm": 22.1690955607781,
|
1439 |
+
"learning_rate": 9.229736639120561e-08,
|
1440 |
+
"logits/chosen": 5999.9892578125,
|
1441 |
+
"logits/rejected": 5568.5703125,
|
1442 |
+
"logps/chosen": -230.053955078125,
|
1443 |
+
"logps/rejected": -253.02633666992188,
|
1444 |
+
"loss": 1.9589,
|
1445 |
+
"rewards/accuracies": 0.7833333015441895,
|
1446 |
+
"rewards/chosen": -12.252751350402832,
|
1447 |
+
"rewards/margins": 26.61910057067871,
|
1448 |
+
"rewards/rejected": -38.871849060058594,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.7535321821036107,
|
1453 |
+
"grad_norm": 17.03053961858823,
|
1454 |
+
"learning_rate": 8.70394897454659e-08,
|
1455 |
+
"logits/chosen": 5853.4912109375,
|
1456 |
+
"logits/rejected": 5239.51708984375,
|
1457 |
+
"logps/chosen": -227.2183380126953,
|
1458 |
+
"logps/rejected": -253.36898803710938,
|
1459 |
+
"loss": 1.9478,
|
1460 |
+
"rewards/accuracies": 0.7916666865348816,
|
1461 |
+
"rewards/chosen": -8.789916038513184,
|
1462 |
+
"rewards/margins": 42.10274887084961,
|
1463 |
+
"rewards/rejected": -50.892677307128906,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7613814756671899,
|
1468 |
+
"grad_norm": 24.752863800000334,
|
1469 |
+
"learning_rate": 8.19040706840472e-08,
|
1470 |
+
"logits/chosen": 5959.28515625,
|
1471 |
+
"logits/rejected": 5025.02099609375,
|
1472 |
+
"logps/chosen": -251.1478729248047,
|
1473 |
+
"logps/rejected": -268.1574401855469,
|
1474 |
+
"loss": 1.9401,
|
1475 |
+
"rewards/accuracies": 0.800000011920929,
|
1476 |
+
"rewards/chosen": -10.927900314331055,
|
1477 |
+
"rewards/margins": 50.53899383544922,
|
1478 |
+
"rewards/rejected": -61.46689987182617,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7692307692307693,
|
1483 |
+
"grad_norm": 16.610566886947357,
|
1484 |
+
"learning_rate": 7.689496824624525e-08,
|
1485 |
+
"logits/chosen": 5662.68359375,
|
1486 |
+
"logits/rejected": 4593.669921875,
|
1487 |
+
"logps/chosen": -239.620849609375,
|
1488 |
+
"logps/rejected": -265.27178955078125,
|
1489 |
+
"loss": 1.9424,
|
1490 |
+
"rewards/accuracies": 0.8083332777023315,
|
1491 |
+
"rewards/chosen": -10.80424690246582,
|
1492 |
+
"rewards/margins": 63.973960876464844,
|
1493 |
+
"rewards/rejected": -74.77821350097656,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.7770800627943485,
|
1498 |
+
"grad_norm": 36.937457019710536,
|
1499 |
+
"learning_rate": 7.201594655002458e-08,
|
1500 |
+
"logits/chosen": 5990.30712890625,
|
1501 |
+
"logits/rejected": 5043.2490234375,
|
1502 |
+
"logps/chosen": -240.4677734375,
|
1503 |
+
"logps/rejected": -260.95574951171875,
|
1504 |
+
"loss": 1.9499,
|
1505 |
+
"rewards/accuracies": 0.7166666984558105,
|
1506 |
+
"rewards/chosen": -14.572827339172363,
|
1507 |
+
"rewards/margins": 52.31321334838867,
|
1508 |
+
"rewards/rejected": -66.88603973388672,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.7849293563579278,
|
1513 |
+
"grad_norm": 23.03062466270963,
|
1514 |
+
"learning_rate": 6.727067196345099e-08,
|
1515 |
+
"logits/chosen": 5678.6806640625,
|
1516 |
+
"logits/rejected": 4839.29931640625,
|
1517 |
+
"logps/chosen": -227.02432250976562,
|
1518 |
+
"logps/rejected": -228.1048126220703,
|
1519 |
+
"loss": 1.9563,
|
1520 |
+
"rewards/accuracies": 0.6916666626930237,
|
1521 |
+
"rewards/chosen": -13.268468856811523,
|
1522 |
+
"rewards/margins": 34.491050720214844,
|
1523 |
+
"rewards/rejected": -47.759521484375,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.792778649921507,
|
1528 |
+
"grad_norm": 14.87512248096038,
|
1529 |
+
"learning_rate": 6.26627103495786e-08,
|
1530 |
+
"logits/chosen": 5860.2373046875,
|
1531 |
+
"logits/rejected": 4920.7861328125,
|
1532 |
+
"logps/chosen": -224.3702850341797,
|
1533 |
+
"logps/rejected": -244.62551879882812,
|
1534 |
+
"loss": 1.9538,
|
1535 |
+
"rewards/accuracies": 0.7250000238418579,
|
1536 |
+
"rewards/chosen": -9.661078453063965,
|
1537 |
+
"rewards/margins": 43.53081512451172,
|
1538 |
+
"rewards/rejected": -53.19189453125,
|
1539 |
+
"step": 1010
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.8006279434850864,
|
1543 |
+
"grad_norm": 14.748532824208521,
|
1544 |
+
"learning_rate": 5.8195524386862374e-08,
|
1545 |
+
"logits/chosen": 5948.0859375,
|
1546 |
+
"logits/rejected": 5325.62939453125,
|
1547 |
+
"logps/chosen": -256.8372802734375,
|
1548 |
+
"logps/rejected": -279.39373779296875,
|
1549 |
+
"loss": 1.9608,
|
1550 |
+
"rewards/accuracies": 0.8083333969116211,
|
1551 |
+
"rewards/chosen": -8.658674240112305,
|
1552 |
+
"rewards/margins": 44.65437316894531,
|
1553 |
+
"rewards/rejected": -53.31304931640625,
|
1554 |
+
"step": 1020
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.8084772370486656,
|
1558 |
+
"grad_norm": 13.111496123331063,
|
1559 |
+
"learning_rate": 5.38724709671092e-08,
|
1560 |
+
"logits/chosen": 6350.22802734375,
|
1561 |
+
"logits/rejected": 6027.82177734375,
|
1562 |
+
"logps/chosen": -243.10403442382812,
|
1563 |
+
"logps/rejected": -286.2555847167969,
|
1564 |
+
"loss": 1.95,
|
1565 |
+
"rewards/accuracies": 0.7666667103767395,
|
1566 |
+
"rewards/chosen": -11.635639190673828,
|
1567 |
+
"rewards/margins": 41.500667572021484,
|
1568 |
+
"rewards/rejected": -53.13630294799805,
|
1569 |
+
"step": 1030
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8163265306122449,
|
1573 |
+
"grad_norm": 13.785799458642654,
|
1574 |
+
"learning_rate": 4.969679867292276e-08,
|
1575 |
+
"logits/chosen": 5649.2197265625,
|
1576 |
+
"logits/rejected": 5181.4765625,
|
1577 |
+
"logps/chosen": -237.51126098632812,
|
1578 |
+
"logps/rejected": -271.2793273925781,
|
1579 |
+
"loss": 1.95,
|
1580 |
+
"rewards/accuracies": 0.7000000476837158,
|
1581 |
+
"rewards/chosen": -17.409549713134766,
|
1582 |
+
"rewards/margins": 44.685813903808594,
|
1583 |
+
"rewards/rejected": -62.095359802246094,
|
1584 |
+
"step": 1040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8241758241758241,
|
1588 |
+
"grad_norm": 18.785044476818584,
|
1589 |
+
"learning_rate": 4.5671645336537416e-08,
|
1590 |
+
"logits/chosen": 5704.8623046875,
|
1591 |
+
"logits/rejected": 5225.52587890625,
|
1592 |
+
"logps/chosen": -251.41500854492188,
|
1593 |
+
"logps/rejected": -279.2231750488281,
|
1594 |
+
"loss": 1.9535,
|
1595 |
+
"rewards/accuracies": 0.73333340883255,
|
1596 |
+
"rewards/chosen": -13.934377670288086,
|
1597 |
+
"rewards/margins": 49.494422912597656,
|
1598 |
+
"rewards/rejected": -63.428802490234375,
|
1599 |
+
"step": 1050
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.8320251177394035,
|
1603 |
+
"grad_norm": 26.490352891661313,
|
1604 |
+
"learning_rate": 4.180003568187776e-08,
|
1605 |
+
"logits/chosen": 7039.8828125,
|
1606 |
+
"logits/rejected": 5571.68212890625,
|
1607 |
+
"logps/chosen": -277.3167419433594,
|
1608 |
+
"logps/rejected": -269.80999755859375,
|
1609 |
+
"loss": 1.9639,
|
1610 |
+
"rewards/accuracies": 0.6666666865348816,
|
1611 |
+
"rewards/chosen": -16.329357147216797,
|
1612 |
+
"rewards/margins": 33.44147491455078,
|
1613 |
+
"rewards/rejected": -49.770835876464844,
|
1614 |
+
"step": 1060
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.8398744113029827,
|
1618 |
+
"grad_norm": 22.94047462012029,
|
1619 |
+
"learning_rate": 3.8084879051612144e-08,
|
1620 |
+
"logits/chosen": 5870.64013671875,
|
1621 |
+
"logits/rejected": 5412.8837890625,
|
1622 |
+
"logps/chosen": -234.2925262451172,
|
1623 |
+
"logps/rejected": -246.66885375976562,
|
1624 |
+
"loss": 1.953,
|
1625 |
+
"rewards/accuracies": 0.7166666984558105,
|
1626 |
+
"rewards/chosen": -9.04952335357666,
|
1627 |
+
"rewards/margins": 44.45494842529297,
|
1628 |
+
"rewards/rejected": -53.50446701049805,
|
1629 |
+
"step": 1070
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.847723704866562,
|
1633 |
+
"grad_norm": 15.970389728332213,
|
1634 |
+
"learning_rate": 3.452896722091128e-08,
|
1635 |
+
"logits/chosen": 6428.0244140625,
|
1636 |
+
"logits/rejected": 5009.7216796875,
|
1637 |
+
"logps/chosen": -274.9081726074219,
|
1638 |
+
"logps/rejected": -264.4786376953125,
|
1639 |
+
"loss": 1.9422,
|
1640 |
+
"rewards/accuracies": 0.8083333969116211,
|
1641 |
+
"rewards/chosen": -8.338837623596191,
|
1642 |
+
"rewards/margins": 55.159873962402344,
|
1643 |
+
"rewards/rejected": -63.49870681762695,
|
1644 |
+
"step": 1080
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.8555729984301413,
|
1648 |
+
"grad_norm": 18.198254677065798,
|
1649 |
+
"learning_rate": 3.11349722995527e-08,
|
1650 |
+
"logits/chosen": 6511.92822265625,
|
1651 |
+
"logits/rejected": 4918.216796875,
|
1652 |
+
"logps/chosen": -242.1095733642578,
|
1653 |
+
"logps/rejected": -269.7752990722656,
|
1654 |
+
"loss": 1.9586,
|
1655 |
+
"rewards/accuracies": 0.7333333492279053,
|
1656 |
+
"rewards/chosen": -14.634966850280762,
|
1657 |
+
"rewards/margins": 42.25577926635742,
|
1658 |
+
"rewards/rejected": -56.8907470703125,
|
1659 |
+
"step": 1090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.8634222919937206,
|
1663 |
+
"grad_norm": 16.804338867644905,
|
1664 |
+
"learning_rate": 2.7905444723949762e-08,
|
1665 |
+
"logits/chosen": 6285.3818359375,
|
1666 |
+
"logits/rejected": 5230.830078125,
|
1667 |
+
"logps/chosen": -252.6708526611328,
|
1668 |
+
"logps/rejected": -250.3868408203125,
|
1669 |
+
"loss": 1.9605,
|
1670 |
+
"rewards/accuracies": 0.7416666746139526,
|
1671 |
+
"rewards/chosen": -14.134493827819824,
|
1672 |
+
"rewards/margins": 46.755001068115234,
|
1673 |
+
"rewards/rejected": -60.889495849609375,
|
1674 |
+
"step": 1100
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8712715855572999,
|
1678 |
+
"grad_norm": 16.045778309961047,
|
1679 |
+
"learning_rate": 2.484281134061142e-08,
|
1680 |
+
"logits/chosen": 6644.92041015625,
|
1681 |
+
"logits/rejected": 5396.99462890625,
|
1682 |
+
"logps/chosen": -279.4850158691406,
|
1683 |
+
"logps/rejected": -281.66839599609375,
|
1684 |
+
"loss": 1.9534,
|
1685 |
+
"rewards/accuracies": 0.7916666269302368,
|
1686 |
+
"rewards/chosen": -14.871435165405273,
|
1687 |
+
"rewards/margins": 44.52893829345703,
|
1688 |
+
"rewards/rejected": -59.40037155151367,
|
1689 |
+
"step": 1110
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8791208791208791,
|
1693 |
+
"grad_norm": 25.938670718923635,
|
1694 |
+
"learning_rate": 2.194937358247506e-08,
|
1695 |
+
"logits/chosen": 6502.3291015625,
|
1696 |
+
"logits/rejected": 5317.71044921875,
|
1697 |
+
"logps/chosen": -260.4866638183594,
|
1698 |
+
"logps/rejected": -276.68133544921875,
|
1699 |
+
"loss": 1.9533,
|
1700 |
+
"rewards/accuracies": 0.7583333849906921,
|
1701 |
+
"rewards/chosen": -15.346229553222656,
|
1702 |
+
"rewards/margins": 44.5643310546875,
|
1703 |
+
"rewards/rejected": -59.910552978515625,
|
1704 |
+
"step": 1120
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.8869701726844584,
|
1708 |
+
"grad_norm": 24.916434094111068,
|
1709 |
+
"learning_rate": 1.9227305739481612e-08,
|
1710 |
+
"logits/chosen": 5917.8349609375,
|
1711 |
+
"logits/rejected": 4701.77978515625,
|
1712 |
+
"logps/chosen": -244.61825561523438,
|
1713 |
+
"logps/rejected": -235.84878540039062,
|
1714 |
+
"loss": 1.9449,
|
1715 |
+
"rewards/accuracies": 0.7416666746139526,
|
1716 |
+
"rewards/chosen": -9.836224555969238,
|
1717 |
+
"rewards/margins": 45.78696823120117,
|
1718 |
+
"rewards/rejected": -55.623199462890625,
|
1719 |
+
"step": 1130
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.8948194662480377,
|
1723 |
+
"grad_norm": 14.382726209860957,
|
1724 |
+
"learning_rate": 1.6678653324693787e-08,
|
1725 |
+
"logits/chosen": 6504.939453125,
|
1726 |
+
"logits/rejected": 5327.1845703125,
|
1727 |
+
"logps/chosen": -270.0257873535156,
|
1728 |
+
"logps/rejected": -271.5950622558594,
|
1729 |
+
"loss": 1.9525,
|
1730 |
+
"rewards/accuracies": 0.7333333492279053,
|
1731 |
+
"rewards/chosen": -12.405012130737305,
|
1732 |
+
"rewards/margins": 38.37703323364258,
|
1733 |
+
"rewards/rejected": -50.78205108642578,
|
1734 |
+
"step": 1140
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.902668759811617,
|
1738 |
+
"grad_norm": 14.78835811924378,
|
1739 |
+
"learning_rate": 1.4305331537183384e-08,
|
1740 |
+
"logits/chosen": 5756.44970703125,
|
1741 |
+
"logits/rejected": 5324.578125,
|
1742 |
+
"logps/chosen": -238.2313690185547,
|
1743 |
+
"logps/rejected": -266.89166259765625,
|
1744 |
+
"loss": 1.9446,
|
1745 |
+
"rewards/accuracies": 0.7500000596046448,
|
1746 |
+
"rewards/chosen": -11.247991561889648,
|
1747 |
+
"rewards/margins": 36.155738830566406,
|
1748 |
+
"rewards/rejected": -47.40373229980469,
|
1749 |
+
"step": 1150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.9105180533751962,
|
1753 |
+
"grad_norm": 23.21802503519393,
|
1754 |
+
"learning_rate": 1.2109123822844653e-08,
|
1755 |
+
"logits/chosen": 5926.2421875,
|
1756 |
+
"logits/rejected": 4742.0224609375,
|
1757 |
+
"logps/chosen": -244.4608917236328,
|
1758 |
+
"logps/rejected": -248.4634552001953,
|
1759 |
+
"loss": 1.9544,
|
1760 |
+
"rewards/accuracies": 0.7333333492279053,
|
1761 |
+
"rewards/chosen": -15.904090881347656,
|
1762 |
+
"rewards/margins": 36.621253967285156,
|
1763 |
+
"rewards/rejected": -52.52534103393555,
|
1764 |
+
"step": 1160
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.9183673469387755,
|
1768 |
+
"grad_norm": 22.422532860536233,
|
1769 |
+
"learning_rate": 1.0091680534213387e-08,
|
1770 |
+
"logits/chosen": 6495.7001953125,
|
1771 |
+
"logits/rejected": 6269.51904296875,
|
1772 |
+
"logps/chosen": -256.6058654785156,
|
1773 |
+
"logps/rejected": -297.3378601074219,
|
1774 |
+
"loss": 1.9577,
|
1775 |
+
"rewards/accuracies": 0.7499999403953552,
|
1776 |
+
"rewards/chosen": -13.657504081726074,
|
1777 |
+
"rewards/margins": 36.93338394165039,
|
1778 |
+
"rewards/rejected": -50.59088897705078,
|
1779 |
+
"step": 1170
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.9262166405023547,
|
1783 |
+
"grad_norm": 19.603883456580654,
|
1784 |
+
"learning_rate": 8.254517690300944e-09,
|
1785 |
+
"logits/chosen": 5720.74365234375,
|
1786 |
+
"logits/rejected": 5222.8046875,
|
1787 |
+
"logps/chosen": -253.0874786376953,
|
1788 |
+
"logps/rejected": -268.9738464355469,
|
1789 |
+
"loss": 1.9593,
|
1790 |
+
"rewards/accuracies": 0.7666666507720947,
|
1791 |
+
"rewards/chosen": -13.141489028930664,
|
1792 |
+
"rewards/margins": 39.01056671142578,
|
1793 |
+
"rewards/rejected": -52.152061462402344,
|
1794 |
+
"step": 1180
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.9340659340659341,
|
1798 |
+
"grad_norm": 17.033230362077003,
|
1799 |
+
"learning_rate": 6.599015837372907e-09,
|
1800 |
+
"logits/chosen": 6205.9697265625,
|
1801 |
+
"logits/rejected": 5447.80859375,
|
1802 |
+
"logps/chosen": -269.47576904296875,
|
1803 |
+
"logps/rejected": -276.09552001953125,
|
1804 |
+
"loss": 1.949,
|
1805 |
+
"rewards/accuracies": 0.7083333730697632,
|
1806 |
+
"rewards/chosen": -20.590267181396484,
|
1807 |
+
"rewards/margins": 38.352821350097656,
|
1808 |
+
"rewards/rejected": -58.943084716796875,
|
1809 |
+
"step": 1190
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.9419152276295133,
|
1813 |
+
"grad_norm": 16.90413077812471,
|
1814 |
+
"learning_rate": 5.126419011529992e-09,
|
1815 |
+
"logits/chosen": 6419.7333984375,
|
1816 |
+
"logits/rejected": 5498.9658203125,
|
1817 |
+
"logps/chosen": -267.5433044433594,
|
1818 |
+
"logps/rejected": -279.40057373046875,
|
1819 |
+
"loss": 1.9507,
|
1820 |
+
"rewards/accuracies": 0.800000011920929,
|
1821 |
+
"rewards/chosen": -11.881638526916504,
|
1822 |
+
"rewards/margins": 48.85334014892578,
|
1823 |
+
"rewards/rejected": -60.7349853515625,
|
1824 |
+
"step": 1200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.9497645211930926,
|
1828 |
+
"grad_norm": 36.17870464463534,
|
1829 |
+
"learning_rate": 3.837833803870177e-09,
|
1830 |
+
"logits/chosen": 6007.43603515625,
|
1831 |
+
"logits/rejected": 5288.4658203125,
|
1832 |
+
"logps/chosen": -252.74148559570312,
|
1833 |
+
"logps/rejected": -278.2850646972656,
|
1834 |
+
"loss": 1.9559,
|
1835 |
+
"rewards/accuracies": 0.7583333253860474,
|
1836 |
+
"rewards/chosen": -12.555973052978516,
|
1837 |
+
"rewards/margins": 47.52782440185547,
|
1838 |
+
"rewards/rejected": -60.08379364013672,
|
1839 |
+
"step": 1210
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.957613814756672,
|
1843 |
+
"grad_norm": 16.61938883168565,
|
1844 |
+
"learning_rate": 2.734228528934679e-09,
|
1845 |
+
"logits/chosen": 7483.11962890625,
|
1846 |
+
"logits/rejected": 5542.7509765625,
|
1847 |
+
"logps/chosen": -313.7238464355469,
|
1848 |
+
"logps/rejected": -300.87921142578125,
|
1849 |
+
"loss": 1.9611,
|
1850 |
+
"rewards/accuracies": 0.6833333969116211,
|
1851 |
+
"rewards/chosen": -16.955432891845703,
|
1852 |
+
"rewards/margins": 38.72659683227539,
|
1853 |
+
"rewards/rejected": -55.682029724121094,
|
1854 |
+
"step": 1220
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.9654631083202512,
|
1858 |
+
"grad_norm": 16.700922559123722,
|
1859 |
+
"learning_rate": 1.8164324970625645e-09,
|
1860 |
+
"logits/chosen": 6656.83984375,
|
1861 |
+
"logits/rejected": 5284.20751953125,
|
1862 |
+
"logps/chosen": -271.3492431640625,
|
1863 |
+
"logps/rejected": -268.39617919921875,
|
1864 |
+
"loss": 1.9547,
|
1865 |
+
"rewards/accuracies": 0.7583333253860474,
|
1866 |
+
"rewards/chosen": -10.767581939697266,
|
1867 |
+
"rewards/margins": 44.63188171386719,
|
1868 |
+
"rewards/rejected": -55.39946746826172,
|
1869 |
+
"step": 1230
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.9733124018838305,
|
1873 |
+
"grad_norm": 14.035772074810767,
|
1874 |
+
"learning_rate": 1.0851353912008642e-09,
|
1875 |
+
"logits/chosen": 5738.1884765625,
|
1876 |
+
"logits/rejected": 5294.599609375,
|
1877 |
+
"logps/chosen": -250.1355438232422,
|
1878 |
+
"logps/rejected": -292.23736572265625,
|
1879 |
+
"loss": 1.9484,
|
1880 |
+
"rewards/accuracies": 0.7250000238418579,
|
1881 |
+
"rewards/chosen": -18.523162841796875,
|
1882 |
+
"rewards/margins": 38.556339263916016,
|
1883 |
+
"rewards/rejected": -57.079505920410156,
|
1884 |
+
"step": 1240
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.9811616954474097,
|
1888 |
+
"grad_norm": 14.793452380633976,
|
1889 |
+
"learning_rate": 5.408867486384471e-10,
|
1890 |
+
"logits/chosen": 5854.9208984375,
|
1891 |
+
"logits/rejected": 4967.2197265625,
|
1892 |
+
"logps/chosen": -241.21725463867188,
|
1893 |
+
"logps/rejected": -235.61495971679688,
|
1894 |
+
"loss": 1.9573,
|
1895 |
+
"rewards/accuracies": 0.7666666507720947,
|
1896 |
+
"rewards/chosen": -10.9091215133667,
|
1897 |
+
"rewards/margins": 35.27557373046875,
|
1898 |
+
"rewards/rejected": -46.184696197509766,
|
1899 |
+
"step": 1250
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.989010989010989,
|
1903 |
+
"grad_norm": 16.612160087002778,
|
1904 |
+
"learning_rate": 1.840955480532924e-10,
|
1905 |
+
"logits/chosen": 5532.6669921875,
|
1906 |
+
"logits/rejected": 5269.6572265625,
|
1907 |
+
"logps/chosen": -246.49185180664062,
|
1908 |
+
"logps/rejected": -263.04144287109375,
|
1909 |
+
"loss": 1.9554,
|
1910 |
+
"rewards/accuracies": 0.8083333969116211,
|
1911 |
+
"rewards/chosen": -14.331242561340332,
|
1912 |
+
"rewards/margins": 32.38512420654297,
|
1913 |
+
"rewards/rejected": -46.71636962890625,
|
1914 |
+
"step": 1260
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.9968602825745683,
|
1918 |
+
"grad_norm": 21.26616020403944,
|
1919 |
+
"learning_rate": 1.502990218302247e-11,
|
1920 |
+
"logits/chosen": 5808.15283203125,
|
1921 |
+
"logits/rejected": 4749.75537109375,
|
1922 |
+
"logps/chosen": -237.1238555908203,
|
1923 |
+
"logps/rejected": -240.21200561523438,
|
1924 |
+
"loss": 1.9474,
|
1925 |
+
"rewards/accuracies": 0.7416666746139526,
|
1926 |
+
"rewards/chosen": -12.649885177612305,
|
1927 |
+
"rewards/margins": 41.257911682128906,
|
1928 |
+
"rewards/rejected": -53.907798767089844,
|
1929 |
+
"step": 1270
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.0,
|
1933 |
+
"step": 1274,
|
1934 |
+
"total_flos": 0.0,
|
1935 |
+
"train_loss": 1.9640779633724146,
|
1936 |
+
"train_runtime": 14760.7646,
|
1937 |
+
"train_samples_per_second": 4.142,
|
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 |
+
}
|