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_SquareAll-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_SquareAll-7b-sft-full
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [TTTXXX01/All_like-zephyr-7b-sft-full](https://huggingface.co/TTTXXX01/All_like-zephyr-7b-sft-full) on an unknown dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 6
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 4
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 48
|
45 |
+
- total_eval_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.41.2
|
58 |
+
- Pytorch 2.3.0+cu121
|
59 |
+
- Datasets 2.19.1
|
60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.7359606589028375,
|
5 |
+
"train_runtime": 14766.5572,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.14,
|
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 sha256:6bff33e01b79f46af67f5c8cb82434dad2f28a4cce51901d082f9ffdd0679700
|
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:f56514bfa465d22ca89fe1b3870eee91dbf0d3dfaec8b651f3e945b43c2de4d7
|
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:fce993bfc7bbbf46648fb9f53025d16d61602c931fdf5ac022a2865113e60f6b
|
3 |
+
size 4540516344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.7359606589028375,
|
5 |
+
"train_runtime": 14766.5572,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.14,
|
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": 7.21583952854038,
|
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": 1.3611,
|
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": 7.250440323853339,
|
29 |
+
"learning_rate": 3.9062499999999997e-08,
|
30 |
+
"logits/chosen": 4974.06640625,
|
31 |
+
"logits/rejected": 4328.462890625,
|
32 |
+
"logps/chosen": -204.18780517578125,
|
33 |
+
"logps/rejected": -179.7210693359375,
|
34 |
+
"loss": 1.3611,
|
35 |
+
"rewards/accuracies": 0.5462963581085205,
|
36 |
+
"rewards/chosen": 0.09606336802244186,
|
37 |
+
"rewards/margins": 0.11150993406772614,
|
38 |
+
"rewards/rejected": -0.015446568839251995,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015698587127158554,
|
43 |
+
"grad_norm": 7.101196143379034,
|
44 |
+
"learning_rate": 7.812499999999999e-08,
|
45 |
+
"logits/chosen": 6083.6796875,
|
46 |
+
"logits/rejected": 4833.9912109375,
|
47 |
+
"logps/chosen": -217.20980834960938,
|
48 |
+
"logps/rejected": -196.7445831298828,
|
49 |
+
"loss": 1.361,
|
50 |
+
"rewards/accuracies": 0.5583332777023315,
|
51 |
+
"rewards/chosen": 0.001381927402690053,
|
52 |
+
"rewards/margins": 0.03239595144987106,
|
53 |
+
"rewards/rejected": -0.031014028936624527,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.023547880690737835,
|
58 |
+
"grad_norm": 6.6022522261600285,
|
59 |
+
"learning_rate": 1.1718749999999999e-07,
|
60 |
+
"logits/chosen": 6079.79736328125,
|
61 |
+
"logits/rejected": 5101.44482421875,
|
62 |
+
"logps/chosen": -250.5417938232422,
|
63 |
+
"logps/rejected": -209.3507080078125,
|
64 |
+
"loss": 1.3611,
|
65 |
+
"rewards/accuracies": 0.6083333492279053,
|
66 |
+
"rewards/chosen": 0.03053979016840458,
|
67 |
+
"rewards/margins": 0.08365341275930405,
|
68 |
+
"rewards/rejected": -0.05311363935470581,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03139717425431711,
|
73 |
+
"grad_norm": 6.651029235705796,
|
74 |
+
"learning_rate": 1.5624999999999999e-07,
|
75 |
+
"logits/chosen": 5290.8310546875,
|
76 |
+
"logits/rejected": 4330.50439453125,
|
77 |
+
"logps/chosen": -212.19906616210938,
|
78 |
+
"logps/rejected": -181.70709228515625,
|
79 |
+
"loss": 1.3605,
|
80 |
+
"rewards/accuracies": 0.44999998807907104,
|
81 |
+
"rewards/chosen": -0.11981513351202011,
|
82 |
+
"rewards/margins": -0.09974738210439682,
|
83 |
+
"rewards/rejected": -0.020067747682332993,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.03924646781789639,
|
88 |
+
"grad_norm": 8.194672586151817,
|
89 |
+
"learning_rate": 1.9531249999999998e-07,
|
90 |
+
"logits/chosen": 6344.0693359375,
|
91 |
+
"logits/rejected": 4979.76123046875,
|
92 |
+
"logps/chosen": -266.24810791015625,
|
93 |
+
"logps/rejected": -207.02828979492188,
|
94 |
+
"loss": 1.3583,
|
95 |
+
"rewards/accuracies": 0.3749999701976776,
|
96 |
+
"rewards/chosen": -0.6214836239814758,
|
97 |
+
"rewards/margins": -0.29282474517822266,
|
98 |
+
"rewards/rejected": -0.3286588788032532,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04709576138147567,
|
103 |
+
"grad_norm": 11.446322704538849,
|
104 |
+
"learning_rate": 2.3437499999999998e-07,
|
105 |
+
"logits/chosen": 5300.9951171875,
|
106 |
+
"logits/rejected": 4405.18017578125,
|
107 |
+
"logps/chosen": -216.7227325439453,
|
108 |
+
"logps/rejected": -210.4974822998047,
|
109 |
+
"loss": 1.3477,
|
110 |
+
"rewards/accuracies": 0.3499999940395355,
|
111 |
+
"rewards/chosen": -2.7187533378601074,
|
112 |
+
"rewards/margins": -1.0213677883148193,
|
113 |
+
"rewards/rejected": -1.6973854303359985,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.054945054945054944,
|
118 |
+
"grad_norm": 19.538858672981345,
|
119 |
+
"learning_rate": 2.734375e-07,
|
120 |
+
"logits/chosen": 4725.4267578125,
|
121 |
+
"logits/rejected": 4486.5966796875,
|
122 |
+
"logps/chosen": -191.88389587402344,
|
123 |
+
"logps/rejected": -188.22422790527344,
|
124 |
+
"loss": 1.2939,
|
125 |
+
"rewards/accuracies": 0.38333338499069214,
|
126 |
+
"rewards/chosen": -13.402986526489258,
|
127 |
+
"rewards/margins": -1.9104820489883423,
|
128 |
+
"rewards/rejected": -11.492505073547363,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.06279434850863422,
|
133 |
+
"grad_norm": 15.091021164111524,
|
134 |
+
"learning_rate": 3.1249999999999997e-07,
|
135 |
+
"logits/chosen": 4773.61181640625,
|
136 |
+
"logits/rejected": 4373.45947265625,
|
137 |
+
"logps/chosen": -246.6728973388672,
|
138 |
+
"logps/rejected": -227.4425048828125,
|
139 |
+
"loss": 1.1407,
|
140 |
+
"rewards/accuracies": 0.4000000059604645,
|
141 |
+
"rewards/chosen": -50.10432815551758,
|
142 |
+
"rewards/margins": -4.2523627281188965,
|
143 |
+
"rewards/rejected": -45.851966857910156,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0706436420722135,
|
148 |
+
"grad_norm": 12.74258111169898,
|
149 |
+
"learning_rate": 3.5156249999999997e-07,
|
150 |
+
"logits/chosen": 4061.00244140625,
|
151 |
+
"logits/rejected": 3487.479248046875,
|
152 |
+
"logps/chosen": -445.48590087890625,
|
153 |
+
"logps/rejected": -380.95623779296875,
|
154 |
+
"loss": 0.9196,
|
155 |
+
"rewards/accuracies": 0.3583333492279053,
|
156 |
+
"rewards/chosen": -226.60366821289062,
|
157 |
+
"rewards/margins": -30.091236114501953,
|
158 |
+
"rewards/rejected": -196.5124053955078,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07849293563579278,
|
163 |
+
"grad_norm": 0.6594127545492917,
|
164 |
+
"learning_rate": 3.9062499999999997e-07,
|
165 |
+
"logits/chosen": 1796.354248046875,
|
166 |
+
"logits/rejected": 1736.423583984375,
|
167 |
+
"logps/chosen": -1689.5208740234375,
|
168 |
+
"logps/rejected": -1636.62158203125,
|
169 |
+
"loss": 0.7246,
|
170 |
+
"rewards/accuracies": 0.4583333432674408,
|
171 |
+
"rewards/chosen": -1479.2900390625,
|
172 |
+
"rewards/margins": -42.110374450683594,
|
173 |
+
"rewards/rejected": -1437.179931640625,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08634222919937205,
|
178 |
+
"grad_norm": 0.07200474368710162,
|
179 |
+
"learning_rate": 4.2968749999999996e-07,
|
180 |
+
"logits/chosen": 992.4479370117188,
|
181 |
+
"logits/rejected": 837.40087890625,
|
182 |
+
"logps/chosen": -3747.5078125,
|
183 |
+
"logps/rejected": -3181.522216796875,
|
184 |
+
"loss": 0.697,
|
185 |
+
"rewards/accuracies": 0.4583333432674408,
|
186 |
+
"rewards/chosen": -3564.392578125,
|
187 |
+
"rewards/margins": -561.8626098632812,
|
188 |
+
"rewards/rejected": -3002.5302734375,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.09419152276295134,
|
193 |
+
"grad_norm": 0.017698020360709873,
|
194 |
+
"learning_rate": 4.6874999999999996e-07,
|
195 |
+
"logits/chosen": 864.0091552734375,
|
196 |
+
"logits/rejected": 803.8848876953125,
|
197 |
+
"logps/chosen": -4694.90478515625,
|
198 |
+
"logps/rejected": -4021.72216796875,
|
199 |
+
"loss": 0.695,
|
200 |
+
"rewards/accuracies": 0.4166666865348816,
|
201 |
+
"rewards/chosen": -4492.0673828125,
|
202 |
+
"rewards/margins": -668.5100708007812,
|
203 |
+
"rewards/rejected": -3823.557373046875,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.10204081632653061,
|
208 |
+
"grad_norm": 0.015776874764385673,
|
209 |
+
"learning_rate": 4.999962424962166e-07,
|
210 |
+
"logits/chosen": 675.6439819335938,
|
211 |
+
"logits/rejected": 709.3082275390625,
|
212 |
+
"logps/chosen": -5338.3056640625,
|
213 |
+
"logps/rejected": -4936.4189453125,
|
214 |
+
"loss": 0.6948,
|
215 |
+
"rewards/accuracies": 0.46666663885116577,
|
216 |
+
"rewards/chosen": -5128.4970703125,
|
217 |
+
"rewards/margins": -389.72308349609375,
|
218 |
+
"rewards/rejected": -4738.7744140625,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.10989010989010989,
|
223 |
+
"grad_norm": 0.01684332265893427,
|
224 |
+
"learning_rate": 4.998647417232375e-07,
|
225 |
+
"logits/chosen": 550.5469970703125,
|
226 |
+
"logits/rejected": 620.0813598632812,
|
227 |
+
"logps/chosen": -5882.72998046875,
|
228 |
+
"logps/rejected": -5161.9072265625,
|
229 |
+
"loss": 0.6946,
|
230 |
+
"rewards/accuracies": 0.4333333373069763,
|
231 |
+
"rewards/chosen": -5697.06298828125,
|
232 |
+
"rewards/margins": -712.7469482421875,
|
233 |
+
"rewards/rejected": -4984.3154296875,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.11773940345368916,
|
238 |
+
"grad_norm": 0.038418008430490494,
|
239 |
+
"learning_rate": 4.995454786965036e-07,
|
240 |
+
"logits/chosen": 543.4015502929688,
|
241 |
+
"logits/rejected": 561.3269653320312,
|
242 |
+
"logps/chosen": -6591.6357421875,
|
243 |
+
"logps/rejected": -5493.3583984375,
|
244 |
+
"loss": 0.6946,
|
245 |
+
"rewards/accuracies": 0.4166666865348816,
|
246 |
+
"rewards/chosen": -6389.9521484375,
|
247 |
+
"rewards/margins": -1068.891357421875,
|
248 |
+
"rewards/rejected": -5321.06103515625,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.12558869701726844,
|
253 |
+
"grad_norm": 0.006107357900924098,
|
254 |
+
"learning_rate": 4.990386933279972e-07,
|
255 |
+
"logits/chosen": 570.4808349609375,
|
256 |
+
"logits/rejected": 570.5257568359375,
|
257 |
+
"logps/chosen": -6998.73583984375,
|
258 |
+
"logps/rejected": -6497.4736328125,
|
259 |
+
"loss": 0.6945,
|
260 |
+
"rewards/accuracies": 0.44166669249534607,
|
261 |
+
"rewards/chosen": -6801.20703125,
|
262 |
+
"rewards/margins": -500.7915954589844,
|
263 |
+
"rewards/rejected": -6300.41552734375,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.13343799058084774,
|
268 |
+
"grad_norm": 0.017235831589250027,
|
269 |
+
"learning_rate": 4.983447664444096e-07,
|
270 |
+
"logits/chosen": 655.1981201171875,
|
271 |
+
"logits/rejected": 689.1236572265625,
|
272 |
+
"logps/chosen": -7807.98291015625,
|
273 |
+
"logps/rejected": -7047.0390625,
|
274 |
+
"loss": 0.6945,
|
275 |
+
"rewards/accuracies": 0.40833336114883423,
|
276 |
+
"rewards/chosen": -7598.36181640625,
|
277 |
+
"rewards/margins": -747.6442260742188,
|
278 |
+
"rewards/rejected": -6850.71728515625,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.141287284144427,
|
283 |
+
"grad_norm": 0.006581257523228928,
|
284 |
+
"learning_rate": 4.97464219500968e-07,
|
285 |
+
"logits/chosen": 607.44287109375,
|
286 |
+
"logits/rejected": 628.7760009765625,
|
287 |
+
"logps/chosen": -7429.20068359375,
|
288 |
+
"logps/rejected": -6579.3798828125,
|
289 |
+
"loss": 0.6945,
|
290 |
+
"rewards/accuracies": 0.5249999761581421,
|
291 |
+
"rewards/chosen": -7240.6728515625,
|
292 |
+
"rewards/margins": -839.4552612304688,
|
293 |
+
"rewards/rejected": -6401.21826171875,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.14913657770800628,
|
298 |
+
"grad_norm": 0.004199166098585641,
|
299 |
+
"learning_rate": 4.963977141895843e-07,
|
300 |
+
"logits/chosen": 503.93402099609375,
|
301 |
+
"logits/rejected": 599.97412109375,
|
302 |
+
"logps/chosen": -8052.12255859375,
|
303 |
+
"logps/rejected": -7054.7041015625,
|
304 |
+
"loss": 0.6945,
|
305 |
+
"rewards/accuracies": 0.38333335518836975,
|
306 |
+
"rewards/chosen": -7848.3642578125,
|
307 |
+
"rewards/margins": -984.8982543945312,
|
308 |
+
"rewards/rejected": -6863.4658203125,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.15698587127158556,
|
313 |
+
"grad_norm": 0.004354813694410577,
|
314 |
+
"learning_rate": 4.951460519416227e-07,
|
315 |
+
"logits/chosen": 621.1477661132812,
|
316 |
+
"logits/rejected": 538.1853637695312,
|
317 |
+
"logps/chosen": -8098.0732421875,
|
318 |
+
"logps/rejected": -7754.7119140625,
|
319 |
+
"loss": 0.6945,
|
320 |
+
"rewards/accuracies": 0.46666669845581055,
|
321 |
+
"rewards/chosen": -7915.5283203125,
|
322 |
+
"rewards/margins": -357.48858642578125,
|
323 |
+
"rewards/rejected": -7558.0400390625,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16483516483516483,
|
328 |
+
"grad_norm": 0.009380186214322453,
|
329 |
+
"learning_rate": 4.937101733256606e-07,
|
330 |
+
"logits/chosen": 325.4959716796875,
|
331 |
+
"logits/rejected": 409.53607177734375,
|
332 |
+
"logps/chosen": -7732.62353515625,
|
333 |
+
"logps/rejected": -7081.75634765625,
|
334 |
+
"loss": 0.6945,
|
335 |
+
"rewards/accuracies": 0.4749999940395355,
|
336 |
+
"rewards/chosen": -7578.7099609375,
|
337 |
+
"rewards/margins": -654.1348266601562,
|
338 |
+
"rewards/rejected": -6924.57568359375,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1726844583987441,
|
343 |
+
"grad_norm": 0.0026320208691028484,
|
344 |
+
"learning_rate": 4.920911573406924e-07,
|
345 |
+
"logits/chosen": 467.2705078125,
|
346 |
+
"logits/rejected": 420.5731506347656,
|
347 |
+
"logps/chosen": -9338.3125,
|
348 |
+
"logps/rejected": -8117.6083984375,
|
349 |
+
"loss": 0.6945,
|
350 |
+
"rewards/accuracies": 0.40833336114883423,
|
351 |
+
"rewards/chosen": -9141.974609375,
|
352 |
+
"rewards/margins": -1188.3638916015625,
|
353 |
+
"rewards/rejected": -7953.61181640625,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.18053375196232338,
|
358 |
+
"grad_norm": 0.0015911643887604168,
|
359 |
+
"learning_rate": 4.902902206053098e-07,
|
360 |
+
"logits/chosen": 487.3170471191406,
|
361 |
+
"logits/rejected": 419.96014404296875,
|
362 |
+
"logps/chosen": -8749.359375,
|
363 |
+
"logps/rejected": -8256.490234375,
|
364 |
+
"loss": 0.6945,
|
365 |
+
"rewards/accuracies": 0.5583333373069763,
|
366 |
+
"rewards/chosen": -8562.0205078125,
|
367 |
+
"rewards/margins": -485.2974548339844,
|
368 |
+
"rewards/rejected": -8076.7236328125,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.18838304552590268,
|
373 |
+
"grad_norm": 0.0014238534648916966,
|
374 |
+
"learning_rate": 4.883087164434672e-07,
|
375 |
+
"logits/chosen": 599.5636596679688,
|
376 |
+
"logits/rejected": 433.95379638671875,
|
377 |
+
"logps/chosen": -7963.13671875,
|
378 |
+
"logps/rejected": -6745.1474609375,
|
379 |
+
"loss": 0.6945,
|
380 |
+
"rewards/accuracies": 0.4583333432674408,
|
381 |
+
"rewards/chosen": -7795.5078125,
|
382 |
+
"rewards/margins": -1205.0496826171875,
|
383 |
+
"rewards/rejected": -6590.45703125,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.19623233908948196,
|
388 |
+
"grad_norm": 0.0011220905101507928,
|
389 |
+
"learning_rate": 4.861481338675183e-07,
|
390 |
+
"logits/chosen": 429.65631103515625,
|
391 |
+
"logits/rejected": 408.43914794921875,
|
392 |
+
"logps/chosen": -9243.3759765625,
|
393 |
+
"logps/rejected": -8726.2060546875,
|
394 |
+
"loss": 0.6945,
|
395 |
+
"rewards/accuracies": 0.5083333253860474,
|
396 |
+
"rewards/chosen": -9076.232421875,
|
397 |
+
"rewards/margins": -534.5325317382812,
|
398 |
+
"rewards/rejected": -8541.7001953125,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.20408163265306123,
|
403 |
+
"grad_norm": 0.0003814804492906571,
|
404 |
+
"learning_rate": 4.838100964592904e-07,
|
405 |
+
"logits/chosen": 448.19342041015625,
|
406 |
+
"logits/rejected": 390.24542236328125,
|
407 |
+
"logps/chosen": -9954.365234375,
|
408 |
+
"logps/rejected": -8276.337890625,
|
409 |
+
"loss": 0.6945,
|
410 |
+
"rewards/accuracies": 0.4166666865348816,
|
411 |
+
"rewards/chosen": -9754.646484375,
|
412 |
+
"rewards/margins": -1644.5335693359375,
|
413 |
+
"rewards/rejected": -8110.11328125,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2119309262166405,
|
418 |
+
"grad_norm": 0.00021334165898926726,
|
419 |
+
"learning_rate": 4.812963611500339e-07,
|
420 |
+
"logits/chosen": 729.0921630859375,
|
421 |
+
"logits/rejected": 629.4249877929688,
|
422 |
+
"logps/chosen": -9477.98046875,
|
423 |
+
"logps/rejected": -9332.41015625,
|
424 |
+
"loss": 0.6945,
|
425 |
+
"rewards/accuracies": 0.5083333253860474,
|
426 |
+
"rewards/chosen": -9281.224609375,
|
427 |
+
"rewards/margins": -137.44529724121094,
|
428 |
+
"rewards/rejected": -9143.779296875,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21978021978021978,
|
433 |
+
"grad_norm": 0.001957333999343426,
|
434 |
+
"learning_rate": 4.786088169001671e-07,
|
435 |
+
"logits/chosen": 485.05133056640625,
|
436 |
+
"logits/rejected": 364.7899475097656,
|
437 |
+
"logps/chosen": -8338.849609375,
|
438 |
+
"logps/rejected": -7758.9248046875,
|
439 |
+
"loss": 0.6945,
|
440 |
+
"rewards/accuracies": 0.46666669845581055,
|
441 |
+
"rewards/chosen": -8175.6982421875,
|
442 |
+
"rewards/margins": -586.074951171875,
|
443 |
+
"rewards/rejected": -7589.62353515625,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.22762951334379905,
|
448 |
+
"grad_norm": 0.0019067056234537022,
|
449 |
+
"learning_rate": 4.7574948327980567e-07,
|
450 |
+
"logits/chosen": 633.2568359375,
|
451 |
+
"logits/rejected": 568.8843994140625,
|
452 |
+
"logps/chosen": -11425.986328125,
|
453 |
+
"logps/rejected": -8694.7080078125,
|
454 |
+
"loss": 0.6945,
|
455 |
+
"rewards/accuracies": 0.3333333432674408,
|
456 |
+
"rewards/chosen": -11188.95703125,
|
457 |
+
"rewards/margins": -2676.765625,
|
458 |
+
"rewards/rejected": -8512.1923828125,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.23547880690737832,
|
463 |
+
"grad_norm": 0.0007137610008725143,
|
464 |
+
"learning_rate": 4.727205089511466e-07,
|
465 |
+
"logits/chosen": 443.945068359375,
|
466 |
+
"logits/rejected": 464.84844970703125,
|
467 |
+
"logps/chosen": -8716.529296875,
|
468 |
+
"logps/rejected": -8945.1943359375,
|
469 |
+
"loss": 0.6944,
|
470 |
+
"rewards/accuracies": 0.533333420753479,
|
471 |
+
"rewards/chosen": -8549.056640625,
|
472 |
+
"rewards/margins": 225.9518585205078,
|
473 |
+
"rewards/rejected": -8775.009765625,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.24332810047095763,
|
478 |
+
"grad_norm": 0.00242148784073435,
|
479 |
+
"learning_rate": 4.6952417005384247e-07,
|
480 |
+
"logits/chosen": 475.70001220703125,
|
481 |
+
"logits/rejected": 436.1145935058594,
|
482 |
+
"logps/chosen": -9641.552734375,
|
483 |
+
"logps/rejected": -8915.654296875,
|
484 |
+
"loss": 0.6945,
|
485 |
+
"rewards/accuracies": 0.44999998807907104,
|
486 |
+
"rewards/chosen": -9463.9716796875,
|
487 |
+
"rewards/margins": -723.7852783203125,
|
488 |
+
"rewards/rejected": -8740.1875,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.25117739403453687,
|
493 |
+
"grad_norm": 0.001561325165725142,
|
494 |
+
"learning_rate": 4.661628684945851e-07,
|
495 |
+
"logits/chosen": 559.2214965820312,
|
496 |
+
"logits/rejected": 500.6468811035156,
|
497 |
+
"logps/chosen": -9699.0966796875,
|
498 |
+
"logps/rejected": -8847.6376953125,
|
499 |
+
"loss": 0.6945,
|
500 |
+
"rewards/accuracies": 0.44166669249534607,
|
501 |
+
"rewards/chosen": -9498.0400390625,
|
502 |
+
"rewards/margins": -852.41845703125,
|
503 |
+
"rewards/rejected": -8645.6220703125,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.25902668759811615,
|
508 |
+
"grad_norm": 0.016139043709451042,
|
509 |
+
"learning_rate": 4.626391301421782e-07,
|
510 |
+
"logits/chosen": 609.8659057617188,
|
511 |
+
"logits/rejected": 474.7484436035156,
|
512 |
+
"logps/chosen": -9566.7265625,
|
513 |
+
"logps/rejected": -8918.560546875,
|
514 |
+
"loss": 0.6945,
|
515 |
+
"rewards/accuracies": 0.4416666626930237,
|
516 |
+
"rewards/chosen": -9372.2734375,
|
517 |
+
"rewards/margins": -631.0362548828125,
|
518 |
+
"rewards/rejected": -8741.2373046875,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.2668759811616955,
|
523 |
+
"grad_norm": 0.0010302004756725745,
|
524 |
+
"learning_rate": 4.5895560292945996e-07,
|
525 |
+
"logits/chosen": 548.1551513671875,
|
526 |
+
"logits/rejected": 537.958984375,
|
527 |
+
"logps/chosen": -9928.501953125,
|
528 |
+
"logps/rejected": -10640.470703125,
|
529 |
+
"loss": 0.6945,
|
530 |
+
"rewards/accuracies": 0.5750000476837158,
|
531 |
+
"rewards/chosen": -9734.6435546875,
|
532 |
+
"rewards/margins": 685.4605712890625,
|
533 |
+
"rewards/rejected": -10420.1044921875,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.27472527472527475,
|
538 |
+
"grad_norm": 0.006445284513914828,
|
539 |
+
"learning_rate": 4.5511505486349865e-07,
|
540 |
+
"logits/chosen": 604.7824096679688,
|
541 |
+
"logits/rejected": 522.2452392578125,
|
542 |
+
"logps/chosen": -10464.3125,
|
543 |
+
"logps/rejected": -9905.189453125,
|
544 |
+
"loss": 0.6944,
|
545 |
+
"rewards/accuracies": 0.5000000596046448,
|
546 |
+
"rewards/chosen": -10269.486328125,
|
547 |
+
"rewards/margins": -571.1192626953125,
|
548 |
+
"rewards/rejected": -9698.369140625,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.282574568288854,
|
553 |
+
"grad_norm": 0.0012301299433899874,
|
554 |
+
"learning_rate": 4.5112037194555876e-07,
|
555 |
+
"logits/chosen": 376.46502685546875,
|
556 |
+
"logits/rejected": 502.958740234375,
|
557 |
+
"logps/chosen": -9755.0048828125,
|
558 |
+
"logps/rejected": -10040.54296875,
|
559 |
+
"loss": 0.6945,
|
560 |
+
"rewards/accuracies": 0.5333333611488342,
|
561 |
+
"rewards/chosen": -9577.0810546875,
|
562 |
+
"rewards/margins": 264.18084716796875,
|
563 |
+
"rewards/rejected": -9841.26171875,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2904238618524333,
|
568 |
+
"grad_norm": 0.00021146370226041996,
|
569 |
+
"learning_rate": 4.4697455600239863e-07,
|
570 |
+
"logits/chosen": 545.6077880859375,
|
571 |
+
"logits/rejected": 587.63916015625,
|
572 |
+
"logps/chosen": -9203.572265625,
|
573 |
+
"logps/rejected": -8875.9814453125,
|
574 |
+
"loss": 0.6944,
|
575 |
+
"rewards/accuracies": 0.49166664481163025,
|
576 |
+
"rewards/chosen": -9019.150390625,
|
577 |
+
"rewards/margins": -311.24102783203125,
|
578 |
+
"rewards/rejected": -8707.91015625,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.29827315541601257,
|
583 |
+
"grad_norm": 0.0011735615277733223,
|
584 |
+
"learning_rate": 4.426807224305315e-07,
|
585 |
+
"logits/chosen": 516.1826171875,
|
586 |
+
"logits/rejected": 511.04052734375,
|
587 |
+
"logps/chosen": -10854.4208984375,
|
588 |
+
"logps/rejected": -9300.3759765625,
|
589 |
+
"loss": 0.6944,
|
590 |
+
"rewards/accuracies": 0.38333335518836975,
|
591 |
+
"rewards/chosen": -10626.080078125,
|
592 |
+
"rewards/margins": -1508.713623046875,
|
593 |
+
"rewards/rejected": -9117.3662109375,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.30612244897959184,
|
598 |
+
"grad_norm": 0.0022171606075063687,
|
599 |
+
"learning_rate": 4.3824209785514326e-07,
|
600 |
+
"logits/chosen": 506.26513671875,
|
601 |
+
"logits/rejected": 493.7334899902344,
|
602 |
+
"logps/chosen": -11133.5224609375,
|
603 |
+
"logps/rejected": -8884.3017578125,
|
604 |
+
"loss": 0.6944,
|
605 |
+
"rewards/accuracies": 0.4000000059604645,
|
606 |
+
"rewards/chosen": -10918.0302734375,
|
607 |
+
"rewards/margins": -2213.581787109375,
|
608 |
+
"rewards/rejected": -8704.4482421875,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3139717425431711,
|
613 |
+
"grad_norm": 0.00023374097945210665,
|
614 |
+
"learning_rate": 4.3366201770542687e-07,
|
615 |
+
"logits/chosen": 508.15655517578125,
|
616 |
+
"logits/rejected": 496.728271484375,
|
617 |
+
"logps/chosen": -9687.2529296875,
|
618 |
+
"logps/rejected": -9643.234375,
|
619 |
+
"loss": 0.6945,
|
620 |
+
"rewards/accuracies": 0.46666663885116577,
|
621 |
+
"rewards/chosen": -9496.4658203125,
|
622 |
+
"rewards/margins": -41.97016143798828,
|
623 |
+
"rewards/rejected": -9454.4951171875,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.3218210361067504,
|
628 |
+
"grad_norm": 0.001203764010050171,
|
629 |
+
"learning_rate": 4.2894392370815567e-07,
|
630 |
+
"logits/chosen": 618.2146606445312,
|
631 |
+
"logits/rejected": 611.4668579101562,
|
632 |
+
"logps/chosen": -10374.201171875,
|
633 |
+
"logps/rejected": -9531.54296875,
|
634 |
+
"loss": 0.6944,
|
635 |
+
"rewards/accuracies": 0.42500004172325134,
|
636 |
+
"rewards/chosen": -10161.7138671875,
|
637 |
+
"rewards/margins": -838.6236572265625,
|
638 |
+
"rewards/rejected": -9323.0908203125,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.32967032967032966,
|
643 |
+
"grad_norm": 0.0008040915447573037,
|
644 |
+
"learning_rate": 4.2409136130137845e-07,
|
645 |
+
"logits/chosen": 474.4013671875,
|
646 |
+
"logits/rejected": 573.8902587890625,
|
647 |
+
"logps/chosen": -9800.27734375,
|
648 |
+
"logps/rejected": -8966.046875,
|
649 |
+
"loss": 0.6944,
|
650 |
+
"rewards/accuracies": 0.4416666626930237,
|
651 |
+
"rewards/chosen": -9596.248046875,
|
652 |
+
"rewards/margins": -811.4415283203125,
|
653 |
+
"rewards/rejected": -8784.8056640625,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.33751962323390894,
|
658 |
+
"grad_norm": 0.0032741111209748735,
|
659 |
+
"learning_rate": 4.1910797697018017e-07,
|
660 |
+
"logits/chosen": 426.7384338378906,
|
661 |
+
"logits/rejected": 273.4219665527344,
|
662 |
+
"logps/chosen": -9522.728515625,
|
663 |
+
"logps/rejected": -8452.818359375,
|
664 |
+
"loss": 0.6944,
|
665 |
+
"rewards/accuracies": 0.38333335518836975,
|
666 |
+
"rewards/chosen": -9342.9833984375,
|
667 |
+
"rewards/margins": -1051.3973388671875,
|
668 |
+
"rewards/rejected": -8291.5859375,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3453689167974882,
|
673 |
+
"grad_norm": 0.0012517374589376031,
|
674 |
+
"learning_rate": 4.1399751550651084e-07,
|
675 |
+
"logits/chosen": 582.216796875,
|
676 |
+
"logits/rejected": 551.5579833984375,
|
677 |
+
"logps/chosen": -9716.650390625,
|
678 |
+
"logps/rejected": -9910.478515625,
|
679 |
+
"loss": 0.6945,
|
680 |
+
"rewards/accuracies": 0.45833340287208557,
|
681 |
+
"rewards/chosen": -9534.2568359375,
|
682 |
+
"rewards/margins": 184.53692626953125,
|
683 |
+
"rewards/rejected": -9718.794921875,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3532182103610675,
|
688 |
+
"grad_norm": 0.001267385614262214,
|
689 |
+
"learning_rate": 4.087638171951401e-07,
|
690 |
+
"logits/chosen": 542.8116455078125,
|
691 |
+
"logits/rejected": 322.68206787109375,
|
692 |
+
"logps/chosen": -11353.0361328125,
|
693 |
+
"logps/rejected": -8831.9453125,
|
694 |
+
"loss": 0.6945,
|
695 |
+
"rewards/accuracies": 0.3750000298023224,
|
696 |
+
"rewards/chosen": -11144.2685546875,
|
697 |
+
"rewards/margins": -2475.314697265625,
|
698 |
+
"rewards/rejected": -8668.953125,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.36106750392464676,
|
703 |
+
"grad_norm": 0.000739065140338407,
|
704 |
+
"learning_rate": 4.034108149278543e-07,
|
705 |
+
"logits/chosen": 580.6771850585938,
|
706 |
+
"logits/rejected": 625.329833984375,
|
707 |
+
"logps/chosen": -12085.8525390625,
|
708 |
+
"logps/rejected": -9598.5498046875,
|
709 |
+
"loss": 0.6944,
|
710 |
+
"rewards/accuracies": 0.35833337903022766,
|
711 |
+
"rewards/chosen": -11835.419921875,
|
712 |
+
"rewards/margins": -2427.078369140625,
|
713 |
+
"rewards/rejected": -9408.341796875,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.36891679748822603,
|
718 |
+
"grad_norm": 0.0004433808575629704,
|
719 |
+
"learning_rate": 3.979425312480629e-07,
|
720 |
+
"logits/chosen": 469.94207763671875,
|
721 |
+
"logits/rejected": 505.85650634765625,
|
722 |
+
"logps/chosen": -10658.087890625,
|
723 |
+
"logps/rejected": -9693.3017578125,
|
724 |
+
"loss": 0.6944,
|
725 |
+
"rewards/accuracies": 0.44166669249534607,
|
726 |
+
"rewards/chosen": -10445.822265625,
|
727 |
+
"rewards/margins": -955.0867309570312,
|
728 |
+
"rewards/rejected": -9490.736328125,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.37676609105180536,
|
733 |
+
"grad_norm": 0.0025329886800627066,
|
734 |
+
"learning_rate": 3.923630753280357e-07,
|
735 |
+
"logits/chosen": 434.8932189941406,
|
736 |
+
"logits/rejected": 503.2549743652344,
|
737 |
+
"logps/chosen": -11348.947265625,
|
738 |
+
"logps/rejected": -9960.654296875,
|
739 |
+
"loss": 0.6945,
|
740 |
+
"rewards/accuracies": 0.4166666865348816,
|
741 |
+
"rewards/chosen": -11141.552734375,
|
742 |
+
"rewards/margins": -1355.29443359375,
|
743 |
+
"rewards/rejected": -9786.2578125,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.38461538461538464,
|
748 |
+
"grad_norm": 0.0010205898557466677,
|
749 |
+
"learning_rate": 3.866766398810424e-07,
|
750 |
+
"logits/chosen": 308.83660888671875,
|
751 |
+
"logits/rejected": 506.587158203125,
|
752 |
+
"logps/chosen": -10585.296875,
|
753 |
+
"logps/rejected": -10477.8291015625,
|
754 |
+
"loss": 0.6944,
|
755 |
+
"rewards/accuracies": 0.5333333611488342,
|
756 |
+
"rewards/chosen": -10408.689453125,
|
757 |
+
"rewards/margins": -132.885009765625,
|
758 |
+
"rewards/rejected": -10275.802734375,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3924646781789639,
|
763 |
+
"grad_norm": 0.002583908861114826,
|
764 |
+
"learning_rate": 3.8088749801071496e-07,
|
765 |
+
"logits/chosen": 642.0178833007812,
|
766 |
+
"logits/rejected": 534.6312866210938,
|
767 |
+
"logps/chosen": -11370.619140625,
|
768 |
+
"logps/rejected": -9348.8134765625,
|
769 |
+
"loss": 0.6945,
|
770 |
+
"rewards/accuracies": 0.42500001192092896,
|
771 |
+
"rewards/chosen": -11148.666015625,
|
772 |
+
"rewards/margins": -2002.3675537109375,
|
773 |
+
"rewards/rejected": -9146.296875,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4003139717425432,
|
778 |
+
"grad_norm": 0.0005946839058806162,
|
779 |
+
"learning_rate": 3.75e-07,
|
780 |
+
"logits/chosen": 381.1919860839844,
|
781 |
+
"logits/rejected": 432.2389221191406,
|
782 |
+
"logps/chosen": -9434.353515625,
|
783 |
+
"logps/rejected": -8624.7890625,
|
784 |
+
"loss": 0.6945,
|
785 |
+
"rewards/accuracies": 0.4416666626930237,
|
786 |
+
"rewards/chosen": -9244.8701171875,
|
787 |
+
"rewards/margins": -786.4471435546875,
|
788 |
+
"rewards/rejected": -8458.4228515625,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.40816326530612246,
|
793 |
+
"grad_norm": 0.0009481081985350053,
|
794 |
+
"learning_rate": 3.6901857004211443e-07,
|
795 |
+
"logits/chosen": 533.3642578125,
|
796 |
+
"logits/rejected": 495.35711669921875,
|
797 |
+
"logps/chosen": -9859.2314453125,
|
798 |
+
"logps/rejected": -9604.912109375,
|
799 |
+
"loss": 0.6945,
|
800 |
+
"rewards/accuracies": 0.5250000357627869,
|
801 |
+
"rewards/chosen": -9660.765625,
|
802 |
+
"rewards/margins": -251.6417999267578,
|
803 |
+
"rewards/rejected": -9409.125,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.41601255886970173,
|
808 |
+
"grad_norm": 0.0021459710993465323,
|
809 |
+
"learning_rate": 3.6294770291596076e-07,
|
810 |
+
"logits/chosen": 534.8011474609375,
|
811 |
+
"logits/rejected": 582.2864379882812,
|
812 |
+
"logps/chosen": -11175.54296875,
|
813 |
+
"logps/rejected": -9463.5615234375,
|
814 |
+
"loss": 0.6944,
|
815 |
+
"rewards/accuracies": 0.38333332538604736,
|
816 |
+
"rewards/chosen": -10962.6201171875,
|
817 |
+
"rewards/margins": -1697.818115234375,
|
818 |
+
"rewards/rejected": -9264.802734375,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.423861852433281,
|
823 |
+
"grad_norm": 0.002362326062720146,
|
824 |
+
"learning_rate": 3.5679196060850034e-07,
|
825 |
+
"logits/chosen": 563.3406372070312,
|
826 |
+
"logits/rejected": 534.1571044921875,
|
827 |
+
"logps/chosen": -10592.9794921875,
|
828 |
+
"logps/rejected": -9686.8466796875,
|
829 |
+
"loss": 0.6945,
|
830 |
+
"rewards/accuracies": 0.44166669249534607,
|
831 |
+
"rewards/chosen": -10382.162109375,
|
832 |
+
"rewards/margins": -883.5538330078125,
|
833 |
+
"rewards/rejected": -9498.607421875,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.4317111459968603,
|
838 |
+
"grad_norm": 0.0006598179965538966,
|
839 |
+
"learning_rate": 3.505559688866229e-07,
|
840 |
+
"logits/chosen": 525.2164916992188,
|
841 |
+
"logits/rejected": 597.19384765625,
|
842 |
+
"logps/chosen": -10372.4970703125,
|
843 |
+
"logps/rejected": -10030.5712890625,
|
844 |
+
"loss": 0.6944,
|
845 |
+
"rewards/accuracies": 0.42500001192092896,
|
846 |
+
"rewards/chosen": -10157.755859375,
|
847 |
+
"rewards/margins": -352.24920654296875,
|
848 |
+
"rewards/rejected": -9805.5068359375,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.43956043956043955,
|
853 |
+
"grad_norm": 0.0019021639748611691,
|
854 |
+
"learning_rate": 3.4424441382108826e-07,
|
855 |
+
"logits/chosen": 477.6744689941406,
|
856 |
+
"logits/rejected": 351.56585693359375,
|
857 |
+
"logps/chosen": -10582.34765625,
|
858 |
+
"logps/rejected": -10212.2646484375,
|
859 |
+
"loss": 0.6944,
|
860 |
+
"rewards/accuracies": 0.5166666507720947,
|
861 |
+
"rewards/chosen": -10379.072265625,
|
862 |
+
"rewards/margins": -360.01824951171875,
|
863 |
+
"rewards/rejected": -10019.0546875,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.4474097331240188,
|
868 |
+
"grad_norm": 0.0020283240343375282,
|
869 |
+
"learning_rate": 3.378620382651523e-07,
|
870 |
+
"logits/chosen": 652.3689575195312,
|
871 |
+
"logits/rejected": 540.5253295898438,
|
872 |
+
"logps/chosen": -11030.5693359375,
|
873 |
+
"logps/rejected": -10400.912109375,
|
874 |
+
"loss": 0.6945,
|
875 |
+
"rewards/accuracies": 0.42500001192092896,
|
876 |
+
"rewards/chosen": -10787.609375,
|
877 |
+
"rewards/margins": -610.4671630859375,
|
878 |
+
"rewards/rejected": -10177.142578125,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4552590266875981,
|
883 |
+
"grad_norm": 0.0011743520654221532,
|
884 |
+
"learning_rate": 3.314136382905234e-07,
|
885 |
+
"logits/chosen": 415.26837158203125,
|
886 |
+
"logits/rejected": 544.0094604492188,
|
887 |
+
"logps/chosen": -11010.978515625,
|
888 |
+
"logps/rejected": -10206.412109375,
|
889 |
+
"loss": 0.6944,
|
890 |
+
"rewards/accuracies": 0.42500004172325134,
|
891 |
+
"rewards/chosen": -10798.5625,
|
892 |
+
"rewards/margins": -805.4620361328125,
|
893 |
+
"rewards/rejected": -9993.099609375,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.4631083202511774,
|
898 |
+
"grad_norm": 0.0007190533185071401,
|
899 |
+
"learning_rate": 3.249040595833274e-07,
|
900 |
+
"logits/chosen": 532.3883056640625,
|
901 |
+
"logits/rejected": 512.3326416015625,
|
902 |
+
"logps/chosen": -11925.1640625,
|
903 |
+
"logps/rejected": -10241.1181640625,
|
904 |
+
"loss": 0.6944,
|
905 |
+
"rewards/accuracies": 0.44999998807907104,
|
906 |
+
"rewards/chosen": -11693.439453125,
|
907 |
+
"rewards/margins": -1631.1793212890625,
|
908 |
+
"rewards/rejected": -10062.2587890625,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.47095761381475665,
|
913 |
+
"grad_norm": 0.00010262811846556397,
|
914 |
+
"learning_rate": 3.1833819380279023e-07,
|
915 |
+
"logits/chosen": 452.8245544433594,
|
916 |
+
"logits/rejected": 421.19256591796875,
|
917 |
+
"logps/chosen": -11195.3623046875,
|
918 |
+
"logps/rejected": -10164.623046875,
|
919 |
+
"loss": 0.6945,
|
920 |
+
"rewards/accuracies": 0.4833333492279053,
|
921 |
+
"rewards/chosen": -11017.814453125,
|
922 |
+
"rewards/margins": -1042.8782958984375,
|
923 |
+
"rewards/rejected": -9974.935546875,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.478806907378336,
|
928 |
+
"grad_norm": 0.0002983478101059786,
|
929 |
+
"learning_rate": 3.11720974905373e-07,
|
930 |
+
"logits/chosen": 496.3247985839844,
|
931 |
+
"logits/rejected": 534.28564453125,
|
932 |
+
"logps/chosen": -10881.5830078125,
|
933 |
+
"logps/rejected": -9769.900390625,
|
934 |
+
"loss": 0.6944,
|
935 |
+
"rewards/accuracies": 0.42500001192092896,
|
936 |
+
"rewards/chosen": -10675.4658203125,
|
937 |
+
"rewards/margins": -1090.9879150390625,
|
938 |
+
"rewards/rejected": -9584.4775390625,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.48665620094191525,
|
943 |
+
"grad_norm": 0.00101252108820539,
|
944 |
+
"learning_rate": 3.0505737543712275e-07,
|
945 |
+
"logits/chosen": 380.66571044921875,
|
946 |
+
"logits/rejected": 452.74505615234375,
|
947 |
+
"logps/chosen": -9639.6396484375,
|
948 |
+
"logps/rejected": -8211.8359375,
|
949 |
+
"loss": 0.6945,
|
950 |
+
"rewards/accuracies": 0.4000000059604645,
|
951 |
+
"rewards/chosen": -9455.880859375,
|
952 |
+
"rewards/margins": -1405.1441650390625,
|
953 |
+
"rewards/rejected": -8050.73681640625,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4945054945054945,
|
958 |
+
"grad_norm": 0.006400668125732286,
|
959 |
+
"learning_rate": 2.9835240279702513e-07,
|
960 |
+
"logits/chosen": 720.4910278320312,
|
961 |
+
"logits/rejected": 706.498046875,
|
962 |
+
"logps/chosen": -11893.275390625,
|
963 |
+
"logps/rejected": -10403.083984375,
|
964 |
+
"loss": 0.6944,
|
965 |
+
"rewards/accuracies": 0.38333338499069214,
|
966 |
+
"rewards/chosen": -11650.458984375,
|
967 |
+
"rewards/margins": -1441.623779296875,
|
968 |
+
"rewards/rejected": -10208.8349609375,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.5023547880690737,
|
973 |
+
"grad_norm": 0.006141630657512915,
|
974 |
+
"learning_rate": 2.9161109547416667e-07,
|
975 |
+
"logits/chosen": 582.9979248046875,
|
976 |
+
"logits/rejected": 497.1927795410156,
|
977 |
+
"logps/chosen": -11451.755859375,
|
978 |
+
"logps/rejected": -10217.904296875,
|
979 |
+
"loss": 0.6944,
|
980 |
+
"rewards/accuracies": 0.4083333909511566,
|
981 |
+
"rewards/chosen": -11240.994140625,
|
982 |
+
"rewards/margins": -1237.598876953125,
|
983 |
+
"rewards/rejected": -10003.3955078125,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.5102040816326531,
|
988 |
+
"grad_norm": 0.00025863304722455687,
|
989 |
+
"learning_rate": 2.848385192615339e-07,
|
990 |
+
"logits/chosen": 556.7777099609375,
|
991 |
+
"logits/rejected": 490.5819396972656,
|
992 |
+
"logps/chosen": -10025.822265625,
|
993 |
+
"logps/rejected": -8551.1728515625,
|
994 |
+
"loss": 0.6948,
|
995 |
+
"rewards/accuracies": 0.4000000059604645,
|
996 |
+
"rewards/chosen": -9829.482421875,
|
997 |
+
"rewards/margins": -1447.03662109375,
|
998 |
+
"rewards/rejected": -8382.4453125,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5180533751962323,
|
1003 |
+
"grad_norm": 0.0005278461920808727,
|
1004 |
+
"learning_rate": 2.780397634492949e-07,
|
1005 |
+
"logits/chosen": 569.379638671875,
|
1006 |
+
"logits/rejected": 464.354248046875,
|
1007 |
+
"logps/chosen": -11049.357421875,
|
1008 |
+
"logps/rejected": -9395.771484375,
|
1009 |
+
"loss": 0.6944,
|
1010 |
+
"rewards/accuracies": 0.38333335518836975,
|
1011 |
+
"rewards/chosen": -10831.970703125,
|
1012 |
+
"rewards/margins": -1624.146240234375,
|
1013 |
+
"rewards/rejected": -9207.8251953125,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5259026687598116,
|
1018 |
+
"grad_norm": 0.0016308010126626566,
|
1019 |
+
"learning_rate": 2.71219937000424e-07,
|
1020 |
+
"logits/chosen": 596.8631591796875,
|
1021 |
+
"logits/rejected": 429.16033935546875,
|
1022 |
+
"logps/chosen": -11016.8818359375,
|
1023 |
+
"logps/rejected": -9547.1630859375,
|
1024 |
+
"loss": 0.6944,
|
1025 |
+
"rewards/accuracies": 0.38333335518836975,
|
1026 |
+
"rewards/chosen": -10810.1220703125,
|
1027 |
+
"rewards/margins": -1451.813232421875,
|
1028 |
+
"rewards/rejected": -9358.3095703125,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.533751962323391,
|
1033 |
+
"grad_norm": 0.0002343973569786191,
|
1034 |
+
"learning_rate": 2.6438416471154273e-07,
|
1035 |
+
"logits/chosen": 512.0562744140625,
|
1036 |
+
"logits/rejected": 428.00152587890625,
|
1037 |
+
"logps/chosen": -10903.138671875,
|
1038 |
+
"logps/rejected": -9482.482421875,
|
1039 |
+
"loss": 0.6944,
|
1040 |
+
"rewards/accuracies": 0.4416666626930237,
|
1041 |
+
"rewards/chosen": -10689.478515625,
|
1042 |
+
"rewards/margins": -1386.2215576171875,
|
1043 |
+
"rewards/rejected": -9303.255859375,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.5416012558869702,
|
1048 |
+
"grad_norm": 0.0003518441184716535,
|
1049 |
+
"learning_rate": 2.5753758336186326e-07,
|
1050 |
+
"logits/chosen": 450.0887756347656,
|
1051 |
+
"logits/rejected": 649.3826904296875,
|
1052 |
+
"logps/chosen": -10758.783203125,
|
1053 |
+
"logps/rejected": -10088.453125,
|
1054 |
+
"loss": 0.6944,
|
1055 |
+
"rewards/accuracies": 0.4833333492279053,
|
1056 |
+
"rewards/chosen": -10549.6767578125,
|
1057 |
+
"rewards/margins": -677.419921875,
|
1058 |
+
"rewards/rejected": -9872.255859375,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5494505494505495,
|
1063 |
+
"grad_norm": 0.0034656839712573543,
|
1064 |
+
"learning_rate": 2.5068533785312666e-07,
|
1065 |
+
"logits/chosen": 410.7701721191406,
|
1066 |
+
"logits/rejected": 457.66015625,
|
1067 |
+
"logps/chosen": -10351.4404296875,
|
1068 |
+
"logps/rejected": -10264.9072265625,
|
1069 |
+
"loss": 0.6945,
|
1070 |
+
"rewards/accuracies": 0.4833333492279053,
|
1071 |
+
"rewards/chosen": -10162.1796875,
|
1072 |
+
"rewards/margins": -84.24781799316406,
|
1073 |
+
"rewards/rejected": -10077.93359375,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.5572998430141287,
|
1078 |
+
"grad_norm": 0.0003336925053790682,
|
1079 |
+
"learning_rate": 2.4383257734343794e-07,
|
1080 |
+
"logits/chosen": 521.080078125,
|
1081 |
+
"logits/rejected": 515.5257568359375,
|
1082 |
+
"logps/chosen": -10283.4560546875,
|
1083 |
+
"logps/rejected": -10653.884765625,
|
1084 |
+
"loss": 0.6944,
|
1085 |
+
"rewards/accuracies": 0.4999999403953552,
|
1086 |
+
"rewards/chosen": -10089.544921875,
|
1087 |
+
"rewards/margins": 361.7181701660156,
|
1088 |
+
"rewards/rejected": -10451.2626953125,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.565149136577708,
|
1093 |
+
"grad_norm": 0.0026677539813701255,
|
1094 |
+
"learning_rate": 2.3698445137790258e-07,
|
1095 |
+
"logits/chosen": 502.305908203125,
|
1096 |
+
"logits/rejected": 500.286376953125,
|
1097 |
+
"logps/chosen": -11090.75390625,
|
1098 |
+
"logps/rejected": -9903.01953125,
|
1099 |
+
"loss": 0.6945,
|
1100 |
+
"rewards/accuracies": 0.35833337903022766,
|
1101 |
+
"rewards/chosen": -10871.75,
|
1102 |
+
"rewards/margins": -1168.49609375,
|
1103 |
+
"rewards/rejected": -9703.2529296875,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5729984301412873,
|
1108 |
+
"grad_norm": 0.0004985921946052606,
|
1109 |
+
"learning_rate": 2.3014610601897157e-07,
|
1110 |
+
"logits/chosen": 483.7727966308594,
|
1111 |
+
"logits/rejected": 401.9848327636719,
|
1112 |
+
"logps/chosen": -12027.9130859375,
|
1113 |
+
"logps/rejected": -9711.83203125,
|
1114 |
+
"loss": 0.6944,
|
1115 |
+
"rewards/accuracies": 0.3916666507720947,
|
1116 |
+
"rewards/chosen": -11802.767578125,
|
1117 |
+
"rewards/margins": -2266.010009765625,
|
1118 |
+
"rewards/rejected": -9536.7578125,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5808477237048666,
|
1123 |
+
"grad_norm": 0.0006625971741926073,
|
1124 |
+
"learning_rate": 2.2332267997940513e-07,
|
1125 |
+
"logits/chosen": 509.74871826171875,
|
1126 |
+
"logits/rejected": 394.54791259765625,
|
1127 |
+
"logps/chosen": -10014.029296875,
|
1128 |
+
"logps/rejected": -8989.1533203125,
|
1129 |
+
"loss": 0.6945,
|
1130 |
+
"rewards/accuracies": 0.491666704416275,
|
1131 |
+
"rewards/chosen": -9821.6044921875,
|
1132 |
+
"rewards/margins": -995.0965576171875,
|
1133 |
+
"rewards/rejected": -8826.505859375,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5886970172684458,
|
1138 |
+
"grad_norm": 0.0005006783918768109,
|
1139 |
+
"learning_rate": 2.1651930076075723e-07,
|
1140 |
+
"logits/chosen": 326.0789489746094,
|
1141 |
+
"logits/rejected": 323.6217956542969,
|
1142 |
+
"logps/chosen": -11039.0478515625,
|
1143 |
+
"logps/rejected": -10318.177734375,
|
1144 |
+
"loss": 0.6944,
|
1145 |
+
"rewards/accuracies": 0.4166666567325592,
|
1146 |
+
"rewards/chosen": -10858.6220703125,
|
1147 |
+
"rewards/margins": -707.5388793945312,
|
1148 |
+
"rewards/rejected": -10151.0830078125,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.5965463108320251,
|
1153 |
+
"grad_norm": 0.00029775808523041525,
|
1154 |
+
"learning_rate": 2.0974108080028692e-07,
|
1155 |
+
"logits/chosen": 484.8963317871094,
|
1156 |
+
"logits/rejected": 345.1195068359375,
|
1157 |
+
"logps/chosen": -11451.5283203125,
|
1158 |
+
"logps/rejected": -9524.697265625,
|
1159 |
+
"loss": 0.6945,
|
1160 |
+
"rewards/accuracies": 0.3500000536441803,
|
1161 |
+
"rewards/chosen": -11248.279296875,
|
1162 |
+
"rewards/margins": -1898.110595703125,
|
1163 |
+
"rewards/rejected": -9350.166015625,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6043956043956044,
|
1168 |
+
"grad_norm": 0.000363602944445742,
|
1169 |
+
"learning_rate": 2.0299311362918773e-07,
|
1170 |
+
"logits/chosen": 456.2711486816406,
|
1171 |
+
"logits/rejected": 465.47869873046875,
|
1172 |
+
"logps/chosen": -12091.4501953125,
|
1173 |
+
"logps/rejected": -10765.958984375,
|
1174 |
+
"loss": 0.6944,
|
1175 |
+
"rewards/accuracies": 0.4416666626930237,
|
1176 |
+
"rewards/chosen": -11861.7158203125,
|
1177 |
+
"rewards/margins": -1319.616455078125,
|
1178 |
+
"rewards/rejected": -10542.099609375,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6122448979591837,
|
1183 |
+
"grad_norm": 0.0003616112714064354,
|
1184 |
+
"learning_rate": 1.962804700450265e-07,
|
1185 |
+
"logits/chosen": 644.1038818359375,
|
1186 |
+
"logits/rejected": 607.6719970703125,
|
1187 |
+
"logps/chosen": -11279.4140625,
|
1188 |
+
"logps/rejected": -11286.236328125,
|
1189 |
+
"loss": 0.6944,
|
1190 |
+
"rewards/accuracies": 0.491666704416275,
|
1191 |
+
"rewards/chosen": -11063.3095703125,
|
1192 |
+
"rewards/margins": -14.460107803344727,
|
1193 |
+
"rewards/rejected": -11048.849609375,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.6200941915227629,
|
1198 |
+
"grad_norm": 0.00044028490625225996,
|
1199 |
+
"learning_rate": 1.8960819430126334e-07,
|
1200 |
+
"logits/chosen": 377.1701965332031,
|
1201 |
+
"logits/rejected": 342.3818359375,
|
1202 |
+
"logps/chosen": -11099.810546875,
|
1203 |
+
"logps/rejected": -10203.8212890625,
|
1204 |
+
"loss": 0.6944,
|
1205 |
+
"rewards/accuracies": 0.46666669845581055,
|
1206 |
+
"rewards/chosen": -10901.6796875,
|
1207 |
+
"rewards/margins": -886.4556884765625,
|
1208 |
+
"rewards/rejected": -10015.224609375,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.6279434850863422,
|
1213 |
+
"grad_norm": 0.005357622654444911,
|
1214 |
+
"learning_rate": 1.8298130031671972e-07,
|
1215 |
+
"logits/chosen": 550.1544799804688,
|
1216 |
+
"logits/rejected": 495.3414611816406,
|
1217 |
+
"logps/chosen": -10878.4814453125,
|
1218 |
+
"logps/rejected": -9992.93359375,
|
1219 |
+
"loss": 0.6944,
|
1220 |
+
"rewards/accuracies": 0.4500000476837158,
|
1221 |
+
"rewards/chosen": -10661.7587890625,
|
1222 |
+
"rewards/margins": -881.5245971679688,
|
1223 |
+
"rewards/rejected": -9780.2333984375,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6357927786499215,
|
1228 |
+
"grad_norm": 0.000805097508736943,
|
1229 |
+
"learning_rate": 1.7640476790784075e-07,
|
1230 |
+
"logits/chosen": 371.45465087890625,
|
1231 |
+
"logits/rejected": 396.21429443359375,
|
1232 |
+
"logps/chosen": -10371.6611328125,
|
1233 |
+
"logps/rejected": -9846.5078125,
|
1234 |
+
"loss": 0.6944,
|
1235 |
+
"rewards/accuracies": 0.44166669249534607,
|
1236 |
+
"rewards/chosen": -10169.205078125,
|
1237 |
+
"rewards/margins": -543.99462890625,
|
1238 |
+
"rewards/rejected": -9625.2109375,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.6436420722135008,
|
1243 |
+
"grad_norm": 0.004693810777668788,
|
1244 |
+
"learning_rate": 1.6988353904658492e-07,
|
1245 |
+
"logits/chosen": 315.043212890625,
|
1246 |
+
"logits/rejected": 400.67559814453125,
|
1247 |
+
"logps/chosen": -11178.794921875,
|
1248 |
+
"logps/rejected": -8904.158203125,
|
1249 |
+
"loss": 0.6944,
|
1250 |
+
"rewards/accuracies": 0.3750000298023224,
|
1251 |
+
"rewards/chosen": -10957.580078125,
|
1252 |
+
"rewards/margins": -2222.112060546875,
|
1253 |
+
"rewards/rejected": -8735.470703125,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.6514913657770801,
|
1258 |
+
"grad_norm": 0.0010885556542559263,
|
1259 |
+
"learning_rate": 1.634225141467513e-07,
|
1260 |
+
"logits/chosen": 429.1761169433594,
|
1261 |
+
"logits/rejected": 422.4315490722656,
|
1262 |
+
"logps/chosen": -11035.6904296875,
|
1263 |
+
"logps/rejected": -10288.4482421875,
|
1264 |
+
"loss": 0.6944,
|
1265 |
+
"rewards/accuracies": 0.44999998807907104,
|
1266 |
+
"rewards/chosen": -10831.50390625,
|
1267 |
+
"rewards/margins": -735.5105590820312,
|
1268 |
+
"rewards/rejected": -10095.994140625,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6593406593406593,
|
1273 |
+
"grad_norm": 0.0012791510584133318,
|
1274 |
+
"learning_rate": 1.570265483815364e-07,
|
1275 |
+
"logits/chosen": 470.92156982421875,
|
1276 |
+
"logits/rejected": 462.15985107421875,
|
1277 |
+
"logps/chosen": -11918.072265625,
|
1278 |
+
"logps/rejected": -10374.5302734375,
|
1279 |
+
"loss": 0.6944,
|
1280 |
+
"rewards/accuracies": 0.3583333492279053,
|
1281 |
+
"rewards/chosen": -11690.7412109375,
|
1282 |
+
"rewards/margins": -1529.003173828125,
|
1283 |
+
"rewards/rejected": -10161.73828125,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.6671899529042387,
|
1288 |
+
"grad_norm": 0.0005945542833698765,
|
1289 |
+
"learning_rate": 1.5070044803508691e-07,
|
1290 |
+
"logits/chosen": 571.09765625,
|
1291 |
+
"logits/rejected": 574.0386962890625,
|
1292 |
+
"logps/chosen": -10925.759765625,
|
1293 |
+
"logps/rejected": -10105.3671875,
|
1294 |
+
"loss": 0.6944,
|
1295 |
+
"rewards/accuracies": 0.4000000059604645,
|
1296 |
+
"rewards/chosen": -10710.2822265625,
|
1297 |
+
"rewards/margins": -805.3693237304688,
|
1298 |
+
"rewards/rejected": -9904.912109375,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.6750392464678179,
|
1303 |
+
"grad_norm": 0.016505752953715463,
|
1304 |
+
"learning_rate": 1.444489668907914e-07,
|
1305 |
+
"logits/chosen": 713.1834106445312,
|
1306 |
+
"logits/rejected": 583.1593017578125,
|
1307 |
+
"logps/chosen": -11648.771484375,
|
1308 |
+
"logps/rejected": -10224.966796875,
|
1309 |
+
"loss": 0.6945,
|
1310 |
+
"rewards/accuracies": 0.46666669845581055,
|
1311 |
+
"rewards/chosen": -11401.0,
|
1312 |
+
"rewards/margins": -1378.7158203125,
|
1313 |
+
"rewards/rejected": -10022.2841796875,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6828885400313972,
|
1318 |
+
"grad_norm": 0.0008005280036489723,
|
1319 |
+
"learning_rate": 1.3827680265902232e-07,
|
1320 |
+
"logits/chosen": 574.0198974609375,
|
1321 |
+
"logits/rejected": 531.7598876953125,
|
1322 |
+
"logps/chosen": -11879.4306640625,
|
1323 |
+
"logps/rejected": -10229.916015625,
|
1324 |
+
"loss": 0.6944,
|
1325 |
+
"rewards/accuracies": 0.4750000536441803,
|
1326 |
+
"rewards/chosen": -11649.333984375,
|
1327 |
+
"rewards/margins": -1620.1064453125,
|
1328 |
+
"rewards/rejected": -10029.2265625,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6907378335949764,
|
1333 |
+
"grad_norm": 0.0003804149709393164,
|
1334 |
+
"learning_rate": 1.3218859344701632e-07,
|
1335 |
+
"logits/chosen": 561.2614135742188,
|
1336 |
+
"logits/rejected": 561.1036376953125,
|
1337 |
+
"logps/chosen": -10448.341796875,
|
1338 |
+
"logps/rejected": -10479.4130859375,
|
1339 |
+
"loss": 0.6944,
|
1340 |
+
"rewards/accuracies": 0.5666667222976685,
|
1341 |
+
"rewards/chosen": -10237.830078125,
|
1342 |
+
"rewards/margins": 9.993700981140137,
|
1343 |
+
"rewards/rejected": -10247.8251953125,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6985871271585558,
|
1348 |
+
"grad_norm": 0.0001534716417740244,
|
1349 |
+
"learning_rate": 1.2618891427354172e-07,
|
1350 |
+
"logits/chosen": 686.5509033203125,
|
1351 |
+
"logits/rejected": 529.2532958984375,
|
1352 |
+
"logps/chosen": -12045.03515625,
|
1353 |
+
"logps/rejected": -10437.076171875,
|
1354 |
+
"loss": 0.6944,
|
1355 |
+
"rewards/accuracies": 0.4166666865348816,
|
1356 |
+
"rewards/chosen": -11787.4404296875,
|
1357 |
+
"rewards/margins": -1562.1439208984375,
|
1358 |
+
"rewards/rejected": -10225.294921875,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.706436420722135,
|
1363 |
+
"grad_norm": 0.0010127199015733139,
|
1364 |
+
"learning_rate": 1.202822736309758e-07,
|
1365 |
+
"logits/chosen": 499.6285095214844,
|
1366 |
+
"logits/rejected": 601.0958862304688,
|
1367 |
+
"logps/chosen": -10409.6845703125,
|
1368 |
+
"logps/rejected": -10087.666015625,
|
1369 |
+
"loss": 0.6944,
|
1370 |
+
"rewards/accuracies": 0.46666669845581055,
|
1371 |
+
"rewards/chosen": -10205.333984375,
|
1372 |
+
"rewards/margins": -328.0994567871094,
|
1373 |
+
"rewards/rejected": -9877.236328125,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7142857142857143,
|
1378 |
+
"grad_norm": 0.0002216596019617402,
|
1379 |
+
"learning_rate": 1.1447311009737299e-07,
|
1380 |
+
"logits/chosen": 517.1658935546875,
|
1381 |
+
"logits/rejected": 596.5044555664062,
|
1382 |
+
"logps/chosen": -10285.78125,
|
1383 |
+
"logps/rejected": -10152.029296875,
|
1384 |
+
"loss": 0.6944,
|
1385 |
+
"rewards/accuracies": 0.533333420753479,
|
1386 |
+
"rewards/chosen": -10077.556640625,
|
1387 |
+
"rewards/margins": -133.45657348632812,
|
1388 |
+
"rewards/rejected": -9944.099609375,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.7221350078492935,
|
1393 |
+
"grad_norm": 0.00023808742474268642,
|
1394 |
+
"learning_rate": 1.0876578900107053e-07,
|
1395 |
+
"logits/chosen": 626.1790161132812,
|
1396 |
+
"logits/rejected": 471.45172119140625,
|
1397 |
+
"logps/chosen": -11441.62109375,
|
1398 |
+
"logps/rejected": -9792.45703125,
|
1399 |
+
"loss": 0.6944,
|
1400 |
+
"rewards/accuracies": 0.3749999701976776,
|
1401 |
+
"rewards/chosen": -11209.2001953125,
|
1402 |
+
"rewards/margins": -1614.8851318359375,
|
1403 |
+
"rewards/rejected": -9594.3154296875,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.7299843014128728,
|
1408 |
+
"grad_norm": 0.00047469806423056587,
|
1409 |
+
"learning_rate": 1.0316459914033793e-07,
|
1410 |
+
"logits/chosen": 530.0946655273438,
|
1411 |
+
"logits/rejected": 513.5704345703125,
|
1412 |
+
"logps/chosen": -11292.869140625,
|
1413 |
+
"logps/rejected": -8902.419921875,
|
1414 |
+
"loss": 0.6945,
|
1415 |
+
"rewards/accuracies": 0.3750000298023224,
|
1416 |
+
"rewards/chosen": -11056.87890625,
|
1417 |
+
"rewards/margins": -2340.38232421875,
|
1418 |
+
"rewards/rejected": -8716.4970703125,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.7378335949764521,
|
1423 |
+
"grad_norm": 0.0006332868699013036,
|
1424 |
+
"learning_rate": 9.767374956053584e-08,
|
1425 |
+
"logits/chosen": 504.7762756347656,
|
1426 |
+
"logits/rejected": 429.9141540527344,
|
1427 |
+
"logps/chosen": -10969.6884765625,
|
1428 |
+
"logps/rejected": -10032.423828125,
|
1429 |
+
"loss": 0.6945,
|
1430 |
+
"rewards/accuracies": 0.4750000536441803,
|
1431 |
+
"rewards/chosen": -10751.392578125,
|
1432 |
+
"rewards/margins": -923.9509887695312,
|
1433 |
+
"rewards/rejected": -9827.4423828125,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7456828885400314,
|
1438 |
+
"grad_norm": 0.0005963470709798749,
|
1439 |
+
"learning_rate": 9.229736639120561e-08,
|
1440 |
+
"logits/chosen": 526.2850952148438,
|
1441 |
+
"logits/rejected": 545.1388549804688,
|
1442 |
+
"logps/chosen": -11055.03125,
|
1443 |
+
"logps/rejected": -10669.08203125,
|
1444 |
+
"loss": 0.6944,
|
1445 |
+
"rewards/accuracies": 0.5166666507720947,
|
1446 |
+
"rewards/chosen": -10837.23046875,
|
1447 |
+
"rewards/margins": -382.30279541015625,
|
1448 |
+
"rewards/rejected": -10454.9267578125,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.7535321821036107,
|
1453 |
+
"grad_norm": 0.0006939197374970369,
|
1454 |
+
"learning_rate": 8.70394897454659e-08,
|
1455 |
+
"logits/chosen": 528.6098022460938,
|
1456 |
+
"logits/rejected": 517.1777954101562,
|
1457 |
+
"logps/chosen": -10959.4619140625,
|
1458 |
+
"logps/rejected": -10072.0302734375,
|
1459 |
+
"loss": 0.6944,
|
1460 |
+
"rewards/accuracies": 0.3916666805744171,
|
1461 |
+
"rewards/chosen": -10741.033203125,
|
1462 |
+
"rewards/margins": -871.4791870117188,
|
1463 |
+
"rewards/rejected": -9869.552734375,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7613814756671899,
|
1468 |
+
"grad_norm": 0.0007296030856672226,
|
1469 |
+
"learning_rate": 8.19040706840472e-08,
|
1470 |
+
"logits/chosen": 584.8048706054688,
|
1471 |
+
"logits/rejected": 536.4219360351562,
|
1472 |
+
"logps/chosen": -11178.66015625,
|
1473 |
+
"logps/rejected": -9755.2314453125,
|
1474 |
+
"loss": 0.6944,
|
1475 |
+
"rewards/accuracies": 0.4000000059604645,
|
1476 |
+
"rewards/chosen": -10938.4404296875,
|
1477 |
+
"rewards/margins": -1389.900634765625,
|
1478 |
+
"rewards/rejected": -9548.5400390625,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7692307692307693,
|
1483 |
+
"grad_norm": 0.00023802143900857867,
|
1484 |
+
"learning_rate": 7.689496824624525e-08,
|
1485 |
+
"logits/chosen": 404.8477783203125,
|
1486 |
+
"logits/rejected": 342.9325866699219,
|
1487 |
+
"logps/chosen": -10674.650390625,
|
1488 |
+
"logps/rejected": -9277.875,
|
1489 |
+
"loss": 0.6944,
|
1490 |
+
"rewards/accuracies": 0.4749999940395355,
|
1491 |
+
"rewards/chosen": -10445.833984375,
|
1492 |
+
"rewards/margins": -1358.45263671875,
|
1493 |
+
"rewards/rejected": -9087.380859375,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.7770800627943485,
|
1498 |
+
"grad_norm": 0.0013929764018688865,
|
1499 |
+
"learning_rate": 7.201594655002458e-08,
|
1500 |
+
"logits/chosen": 494.68701171875,
|
1501 |
+
"logits/rejected": 510.9247131347656,
|
1502 |
+
"logps/chosen": -11169.6572265625,
|
1503 |
+
"logps/rejected": -9497.7294921875,
|
1504 |
+
"loss": 0.6945,
|
1505 |
+
"rewards/accuracies": 0.4833333492279053,
|
1506 |
+
"rewards/chosen": -10943.76171875,
|
1507 |
+
"rewards/margins": -1640.102783203125,
|
1508 |
+
"rewards/rejected": -9303.6591796875,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.7849293563579278,
|
1513 |
+
"grad_norm": 0.00030992582390807383,
|
1514 |
+
"learning_rate": 6.727067196345099e-08,
|
1515 |
+
"logits/chosen": 484.021240234375,
|
1516 |
+
"logits/rejected": 429.843505859375,
|
1517 |
+
"logps/chosen": -10762.0595703125,
|
1518 |
+
"logps/rejected": -9416.263671875,
|
1519 |
+
"loss": 0.6944,
|
1520 |
+
"rewards/accuracies": 0.42500001192092896,
|
1521 |
+
"rewards/chosen": -10548.3046875,
|
1522 |
+
"rewards/margins": -1312.38671875,
|
1523 |
+
"rewards/rejected": -9235.9189453125,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.792778649921507,
|
1528 |
+
"grad_norm": 0.0007414681340839939,
|
1529 |
+
"learning_rate": 6.26627103495786e-08,
|
1530 |
+
"logits/chosen": 505.01483154296875,
|
1531 |
+
"logits/rejected": 517.8411254882812,
|
1532 |
+
"logps/chosen": -11052.3828125,
|
1533 |
+
"logps/rejected": -9386.2392578125,
|
1534 |
+
"loss": 0.6944,
|
1535 |
+
"rewards/accuracies": 0.44166669249534607,
|
1536 |
+
"rewards/chosen": -10837.673828125,
|
1537 |
+
"rewards/margins": -1642.868408203125,
|
1538 |
+
"rewards/rejected": -9194.8046875,
|
1539 |
+
"step": 1010
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.8006279434850864,
|
1543 |
+
"grad_norm": 0.0003687874816117168,
|
1544 |
+
"learning_rate": 5.8195524386862374e-08,
|
1545 |
+
"logits/chosen": 562.7574462890625,
|
1546 |
+
"logits/rejected": 544.7307739257812,
|
1547 |
+
"logps/chosen": -11268.1689453125,
|
1548 |
+
"logps/rejected": -10319.515625,
|
1549 |
+
"loss": 0.6944,
|
1550 |
+
"rewards/accuracies": 0.4416666626930237,
|
1551 |
+
"rewards/chosen": -11019.990234375,
|
1552 |
+
"rewards/margins": -926.55419921875,
|
1553 |
+
"rewards/rejected": -10093.435546875,
|
1554 |
+
"step": 1020
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.8084772370486656,
|
1558 |
+
"grad_norm": 0.005760798367996112,
|
1559 |
+
"learning_rate": 5.38724709671092e-08,
|
1560 |
+
"logits/chosen": 474.04486083984375,
|
1561 |
+
"logits/rejected": 475.46295166015625,
|
1562 |
+
"logps/chosen": -11839.8818359375,
|
1563 |
+
"logps/rejected": -11526.0009765625,
|
1564 |
+
"loss": 0.6944,
|
1565 |
+
"rewards/accuracies": 0.44166669249534607,
|
1566 |
+
"rewards/chosen": -11608.4130859375,
|
1567 |
+
"rewards/margins": -315.5327453613281,
|
1568 |
+
"rewards/rejected": -11292.8798828125,
|
1569 |
+
"step": 1030
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8163265306122449,
|
1573 |
+
"grad_norm": 0.00037781549278870523,
|
1574 |
+
"learning_rate": 4.969679867292276e-08,
|
1575 |
+
"logits/chosen": 521.4114990234375,
|
1576 |
+
"logits/rejected": 587.4351196289062,
|
1577 |
+
"logps/chosen": -10636.8388671875,
|
1578 |
+
"logps/rejected": -9961.1240234375,
|
1579 |
+
"loss": 0.6945,
|
1580 |
+
"rewards/accuracies": 0.44999998807907104,
|
1581 |
+
"rewards/chosen": -10416.7373046875,
|
1582 |
+
"rewards/margins": -664.7984619140625,
|
1583 |
+
"rewards/rejected": -9751.939453125,
|
1584 |
+
"step": 1040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8241758241758241,
|
1588 |
+
"grad_norm": 0.006793223367431191,
|
1589 |
+
"learning_rate": 4.5671645336537416e-08,
|
1590 |
+
"logits/chosen": 514.43994140625,
|
1591 |
+
"logits/rejected": 551.023681640625,
|
1592 |
+
"logps/chosen": -10938.4794921875,
|
1593 |
+
"logps/rejected": -10230.494140625,
|
1594 |
+
"loss": 0.6944,
|
1595 |
+
"rewards/accuracies": 0.4749999940395355,
|
1596 |
+
"rewards/chosen": -10700.9990234375,
|
1597 |
+
"rewards/margins": -686.2994384765625,
|
1598 |
+
"rewards/rejected": -10014.7001953125,
|
1599 |
+
"step": 1050
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.8320251177394035,
|
1603 |
+
"grad_norm": 0.00045900227188746113,
|
1604 |
+
"learning_rate": 4.180003568187776e-08,
|
1605 |
+
"logits/chosen": 524.1320190429688,
|
1606 |
+
"logits/rejected": 552.4287719726562,
|
1607 |
+
"logps/chosen": -13095.03125,
|
1608 |
+
"logps/rejected": -10694.0908203125,
|
1609 |
+
"loss": 0.6944,
|
1610 |
+
"rewards/accuracies": 0.4166666567325592,
|
1611 |
+
"rewards/chosen": -12834.0439453125,
|
1612 |
+
"rewards/margins": -2359.99267578125,
|
1613 |
+
"rewards/rejected": -10474.0517578125,
|
1614 |
+
"step": 1060
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.8398744113029827,
|
1618 |
+
"grad_norm": 0.00034521122588735233,
|
1619 |
+
"learning_rate": 3.8084879051612144e-08,
|
1620 |
+
"logits/chosen": 519.01025390625,
|
1621 |
+
"logits/rejected": 546.77587890625,
|
1622 |
+
"logps/chosen": -11113.267578125,
|
1623 |
+
"logps/rejected": -10381.822265625,
|
1624 |
+
"loss": 0.6944,
|
1625 |
+
"rewards/accuracies": 0.4749999940395355,
|
1626 |
+
"rewards/chosen": -10888.025390625,
|
1627 |
+
"rewards/margins": -699.3690185546875,
|
1628 |
+
"rewards/rejected": -10188.65625,
|
1629 |
+
"step": 1070
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.847723704866562,
|
1633 |
+
"grad_norm": 0.0007197800185943902,
|
1634 |
+
"learning_rate": 3.452896722091128e-08,
|
1635 |
+
"logits/chosen": 619.9454956054688,
|
1636 |
+
"logits/rejected": 521.5427856445312,
|
1637 |
+
"logps/chosen": -12005.8955078125,
|
1638 |
+
"logps/rejected": -9818.310546875,
|
1639 |
+
"loss": 0.6944,
|
1640 |
+
"rewards/accuracies": 0.34166669845581055,
|
1641 |
+
"rewards/chosen": -11739.326171875,
|
1642 |
+
"rewards/margins": -2121.99365234375,
|
1643 |
+
"rewards/rejected": -9617.3330078125,
|
1644 |
+
"step": 1080
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.8555729984301413,
|
1648 |
+
"grad_norm": 0.0002482736757925687,
|
1649 |
+
"learning_rate": 3.11349722995527e-08,
|
1650 |
+
"logits/chosen": 710.8172607421875,
|
1651 |
+
"logits/rejected": 605.4769287109375,
|
1652 |
+
"logps/chosen": -11714.08984375,
|
1653 |
+
"logps/rejected": -9476.154296875,
|
1654 |
+
"loss": 0.6944,
|
1655 |
+
"rewards/accuracies": 0.3750000298023224,
|
1656 |
+
"rewards/chosen": -11486.615234375,
|
1657 |
+
"rewards/margins": -2223.34521484375,
|
1658 |
+
"rewards/rejected": -9263.2705078125,
|
1659 |
+
"step": 1090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.8634222919937206,
|
1663 |
+
"grad_norm": 0.0010064561005363537,
|
1664 |
+
"learning_rate": 2.7905444723949762e-08,
|
1665 |
+
"logits/chosen": 569.6670532226562,
|
1666 |
+
"logits/rejected": 575.785888671875,
|
1667 |
+
"logps/chosen": -11909.3740234375,
|
1668 |
+
"logps/rejected": -9983.9169921875,
|
1669 |
+
"loss": 0.6944,
|
1670 |
+
"rewards/accuracies": 0.3750000298023224,
|
1671 |
+
"rewards/chosen": -11670.837890625,
|
1672 |
+
"rewards/margins": -1876.4185791015625,
|
1673 |
+
"rewards/rejected": -9794.419921875,
|
1674 |
+
"step": 1100
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8712715855572999,
|
1678 |
+
"grad_norm": 0.0003760939578581169,
|
1679 |
+
"learning_rate": 2.484281134061142e-08,
|
1680 |
+
"logits/chosen": 736.3983764648438,
|
1681 |
+
"logits/rejected": 638.23974609375,
|
1682 |
+
"logps/chosen": -12203.880859375,
|
1683 |
+
"logps/rejected": -10321.19921875,
|
1684 |
+
"loss": 0.6944,
|
1685 |
+
"rewards/accuracies": 0.38333335518836975,
|
1686 |
+
"rewards/chosen": -11939.2685546875,
|
1687 |
+
"rewards/margins": -1840.337158203125,
|
1688 |
+
"rewards/rejected": -10098.9306640625,
|
1689 |
+
"step": 1110
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8791208791208791,
|
1693 |
+
"grad_norm": 0.00021809248372642968,
|
1694 |
+
"learning_rate": 2.194937358247506e-08,
|
1695 |
+
"logits/chosen": 548.2640380859375,
|
1696 |
+
"logits/rejected": 535.1536865234375,
|
1697 |
+
"logps/chosen": -12217.0576171875,
|
1698 |
+
"logps/rejected": -10378.3642578125,
|
1699 |
+
"loss": 0.6945,
|
1700 |
+
"rewards/accuracies": 0.44999998807907104,
|
1701 |
+
"rewards/chosen": -11971.9169921875,
|
1702 |
+
"rewards/margins": -1810.3236083984375,
|
1703 |
+
"rewards/rejected": -10161.5927734375,
|
1704 |
+
"step": 1120
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.8869701726844584,
|
1708 |
+
"grad_norm": 0.0002678202477740615,
|
1709 |
+
"learning_rate": 1.9227305739481612e-08,
|
1710 |
+
"logits/chosen": 546.5886840820312,
|
1711 |
+
"logits/rejected": 471.8921813964844,
|
1712 |
+
"logps/chosen": -11283.3466796875,
|
1713 |
+
"logps/rejected": -9136.5048828125,
|
1714 |
+
"loss": 0.6944,
|
1715 |
+
"rewards/accuracies": 0.35833337903022766,
|
1716 |
+
"rewards/chosen": -11048.564453125,
|
1717 |
+
"rewards/margins": -2092.28466796875,
|
1718 |
+
"rewards/rejected": -8956.279296875,
|
1719 |
+
"step": 1130
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.8948194662480377,
|
1723 |
+
"grad_norm": 0.0005387042417401348,
|
1724 |
+
"learning_rate": 1.6678653324693787e-08,
|
1725 |
+
"logits/chosen": 464.132568359375,
|
1726 |
+
"logits/rejected": 543.2286376953125,
|
1727 |
+
"logps/chosen": -12346.04296875,
|
1728 |
+
"logps/rejected": -10363.9443359375,
|
1729 |
+
"loss": 0.6944,
|
1730 |
+
"rewards/accuracies": 0.4000000059604645,
|
1731 |
+
"rewards/chosen": -12088.423828125,
|
1732 |
+
"rewards/margins": -1945.2904052734375,
|
1733 |
+
"rewards/rejected": -10143.1318359375,
|
1734 |
+
"step": 1140
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.902668759811617,
|
1738 |
+
"grad_norm": 0.00028081548767204913,
|
1739 |
+
"learning_rate": 1.4305331537183384e-08,
|
1740 |
+
"logits/chosen": 474.62298583984375,
|
1741 |
+
"logits/rejected": 503.7117614746094,
|
1742 |
+
"logps/chosen": -10857.63671875,
|
1743 |
+
"logps/rejected": -10257.396484375,
|
1744 |
+
"loss": 0.6944,
|
1745 |
+
"rewards/accuracies": 0.44999998807907104,
|
1746 |
+
"rewards/chosen": -10630.65234375,
|
1747 |
+
"rewards/margins": -592.7437744140625,
|
1748 |
+
"rewards/rejected": -10037.9091796875,
|
1749 |
+
"step": 1150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.9105180533751962,
|
1753 |
+
"grad_norm": 0.0004423495668441553,
|
1754 |
+
"learning_rate": 1.2109123822844653e-08,
|
1755 |
+
"logits/chosen": 524.8532104492188,
|
1756 |
+
"logits/rejected": 533.907958984375,
|
1757 |
+
"logps/chosen": -11179.892578125,
|
1758 |
+
"logps/rejected": -9216.802734375,
|
1759 |
+
"loss": 0.6944,
|
1760 |
+
"rewards/accuracies": 0.366666704416275,
|
1761 |
+
"rewards/chosen": -10951.333984375,
|
1762 |
+
"rewards/margins": -1930.469970703125,
|
1763 |
+
"rewards/rejected": -9020.865234375,
|
1764 |
+
"step": 1160
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.9183673469387755,
|
1768 |
+
"grad_norm": 0.00019514550735900794,
|
1769 |
+
"learning_rate": 1.0091680534213387e-08,
|
1770 |
+
"logits/chosen": 615.3060302734375,
|
1771 |
+
"logits/rejected": 558.8253784179688,
|
1772 |
+
"logps/chosen": -12210.0439453125,
|
1773 |
+
"logps/rejected": -12054.3017578125,
|
1774 |
+
"loss": 0.6945,
|
1775 |
+
"rewards/accuracies": 0.5083333253860474,
|
1776 |
+
"rewards/chosen": -11967.0947265625,
|
1777 |
+
"rewards/margins": -159.54014587402344,
|
1778 |
+
"rewards/rejected": -11807.5546875,
|
1779 |
+
"step": 1170
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.9262166405023547,
|
1783 |
+
"grad_norm": 0.0004545153062548297,
|
1784 |
+
"learning_rate": 8.254517690300944e-09,
|
1785 |
+
"logits/chosen": 616.0506591796875,
|
1786 |
+
"logits/rejected": 626.9619750976562,
|
1787 |
+
"logps/chosen": -10846.5625,
|
1788 |
+
"logps/rejected": -10076.8857421875,
|
1789 |
+
"loss": 0.6944,
|
1790 |
+
"rewards/accuracies": 0.42500001192092896,
|
1791 |
+
"rewards/chosen": -10606.6162109375,
|
1792 |
+
"rewards/margins": -746.5523681640625,
|
1793 |
+
"rewards/rejected": -9860.064453125,
|
1794 |
+
"step": 1180
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.9340659340659341,
|
1798 |
+
"grad_norm": 0.003226387409113769,
|
1799 |
+
"learning_rate": 6.599015837372907e-09,
|
1800 |
+
"logits/chosen": 554.5615844726562,
|
1801 |
+
"logits/rejected": 558.3009033203125,
|
1802 |
+
"logps/chosen": -11654.806640625,
|
1803 |
+
"logps/rejected": -10600.859375,
|
1804 |
+
"loss": 0.6944,
|
1805 |
+
"rewards/accuracies": 0.4333333373069763,
|
1806 |
+
"rewards/chosen": -11405.919921875,
|
1807 |
+
"rewards/margins": -1022.2127685546875,
|
1808 |
+
"rewards/rejected": -10383.70703125,
|
1809 |
+
"step": 1190
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.9419152276295133,
|
1813 |
+
"grad_norm": 0.00016417329889322683,
|
1814 |
+
"learning_rate": 5.126419011529992e-09,
|
1815 |
+
"logits/chosen": 487.95513916015625,
|
1816 |
+
"logits/rejected": 477.30352783203125,
|
1817 |
+
"logps/chosen": -11990.833984375,
|
1818 |
+
"logps/rejected": -10696.8125,
|
1819 |
+
"loss": 0.6944,
|
1820 |
+
"rewards/accuracies": 0.46666663885116577,
|
1821 |
+
"rewards/chosen": -11735.171875,
|
1822 |
+
"rewards/margins": -1257.026123046875,
|
1823 |
+
"rewards/rejected": -10478.146484375,
|
1824 |
+
"step": 1200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.9497645211930926,
|
1828 |
+
"grad_norm": 0.0005186075718613249,
|
1829 |
+
"learning_rate": 3.837833803870177e-09,
|
1830 |
+
"logits/chosen": 388.5582580566406,
|
1831 |
+
"logits/rejected": 399.3382568359375,
|
1832 |
+
"logps/chosen": -11644.5869140625,
|
1833 |
+
"logps/rejected": -10613.4970703125,
|
1834 |
+
"loss": 0.6944,
|
1835 |
+
"rewards/accuracies": 0.5083333253860474,
|
1836 |
+
"rewards/chosen": -11404.4013671875,
|
1837 |
+
"rewards/margins": -1009.1047973632812,
|
1838 |
+
"rewards/rejected": -10395.2958984375,
|
1839 |
+
"step": 1210
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.957613814756672,
|
1843 |
+
"grad_norm": 0.0006889943530268683,
|
1844 |
+
"learning_rate": 2.734228528934679e-09,
|
1845 |
+
"logits/chosen": 607.74072265625,
|
1846 |
+
"logits/rejected": 482.1900939941406,
|
1847 |
+
"logps/chosen": -13991.2314453125,
|
1848 |
+
"logps/rejected": -11046.5498046875,
|
1849 |
+
"loss": 0.6945,
|
1850 |
+
"rewards/accuracies": 0.34166666865348816,
|
1851 |
+
"rewards/chosen": -13694.462890625,
|
1852 |
+
"rewards/margins": -2893.10888671875,
|
1853 |
+
"rewards/rejected": -10801.353515625,
|
1854 |
+
"step": 1220
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.9654631083202512,
|
1858 |
+
"grad_norm": 0.0003228878623085867,
|
1859 |
+
"learning_rate": 1.8164324970625645e-09,
|
1860 |
+
"logits/chosen": 612.4022827148438,
|
1861 |
+
"logits/rejected": 605.3236083984375,
|
1862 |
+
"logps/chosen": -12401.9326171875,
|
1863 |
+
"logps/rejected": -10077.7578125,
|
1864 |
+
"loss": 0.6944,
|
1865 |
+
"rewards/accuracies": 0.3499999940395355,
|
1866 |
+
"rewards/chosen": -12141.349609375,
|
1867 |
+
"rewards/margins": -2276.58935546875,
|
1868 |
+
"rewards/rejected": -9864.7607421875,
|
1869 |
+
"step": 1230
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.9733124018838305,
|
1873 |
+
"grad_norm": 0.0004635193620610196,
|
1874 |
+
"learning_rate": 1.0851353912008642e-09,
|
1875 |
+
"logits/chosen": 548.4609375,
|
1876 |
+
"logits/rejected": 406.30108642578125,
|
1877 |
+
"logps/chosen": -10926.345703125,
|
1878 |
+
"logps/rejected": -10544.0869140625,
|
1879 |
+
"loss": 0.6944,
|
1880 |
+
"rewards/accuracies": 0.4333333373069763,
|
1881 |
+
"rewards/chosen": -10694.732421875,
|
1882 |
+
"rewards/margins": -385.8048095703125,
|
1883 |
+
"rewards/rejected": -10308.9296875,
|
1884 |
+
"step": 1240
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.9811616954474097,
|
1888 |
+
"grad_norm": 0.0005082408297896108,
|
1889 |
+
"learning_rate": 5.408867486384471e-10,
|
1890 |
+
"logits/chosen": 561.4332275390625,
|
1891 |
+
"logits/rejected": 464.0692443847656,
|
1892 |
+
"logps/chosen": -11016.3642578125,
|
1893 |
+
"logps/rejected": -9608.521484375,
|
1894 |
+
"loss": 0.6944,
|
1895 |
+
"rewards/accuracies": 0.40833336114883423,
|
1896 |
+
"rewards/chosen": -10786.0556640625,
|
1897 |
+
"rewards/margins": -1366.96337890625,
|
1898 |
+
"rewards/rejected": -9419.091796875,
|
1899 |
+
"step": 1250
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.989010989010989,
|
1903 |
+
"grad_norm": 0.0001467066278307736,
|
1904 |
+
"learning_rate": 1.840955480532924e-10,
|
1905 |
+
"logits/chosen": 427.8658142089844,
|
1906 |
+
"logits/rejected": 491.8282775878906,
|
1907 |
+
"logps/chosen": -10776.49609375,
|
1908 |
+
"logps/rejected": -10325.6982421875,
|
1909 |
+
"loss": 0.6945,
|
1910 |
+
"rewards/accuracies": 0.491666704416275,
|
1911 |
+
"rewards/chosen": -10544.3359375,
|
1912 |
+
"rewards/margins": -434.962158203125,
|
1913 |
+
"rewards/rejected": -10109.3740234375,
|
1914 |
+
"step": 1260
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.9968602825745683,
|
1918 |
+
"grad_norm": 0.0001355855815871487,
|
1919 |
+
"learning_rate": 1.502990218302247e-11,
|
1920 |
+
"logits/chosen": 581.5196533203125,
|
1921 |
+
"logits/rejected": 462.2622985839844,
|
1922 |
+
"logps/chosen": -10980.98828125,
|
1923 |
+
"logps/rejected": -9310.0419921875,
|
1924 |
+
"loss": 0.6945,
|
1925 |
+
"rewards/accuracies": 0.42500001192092896,
|
1926 |
+
"rewards/chosen": -10756.513671875,
|
1927 |
+
"rewards/margins": -1632.776123046875,
|
1928 |
+
"rewards/rejected": -9123.736328125,
|
1929 |
+
"step": 1270
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.0,
|
1933 |
+
"step": 1274,
|
1934 |
+
"total_flos": 0.0,
|
1935 |
+
"train_loss": 0.7359606589028375,
|
1936 |
+
"train_runtime": 14766.5572,
|
1937 |
+
"train_samples_per_second": 4.14,
|
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 |
+
}
|