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_DPOAll-zephyr-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_DPOAll-zephyr-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": 0.6278583559922558,
|
5 |
+
"train_runtime": 14837.7437,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.12,
|
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 sha256:39fb0990ef2112e59df8f0c25f1d9e31d3a47ea863e575d7e443c35eb52e1e6b
|
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:da743bdbc6d5d4239a5b5e5be6ceac1ed1dd3290891f1cc3561f16e684592607
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:241b9ee89ae493302865f3571d68e7cb6bc23e14242a48fe5814958afe6bb3e1
|
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": 0.6278583559922558,
|
5 |
+
"train_runtime": 14837.7437,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.12,
|
8 |
+
"train_steps_per_second": 0.086
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1962 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1274,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0007849293563579278,
|
13 |
+
"grad_norm": 6.093040937403707,
|
14 |
+
"learning_rate": 3.90625e-09,
|
15 |
+
"logits/chosen": 5914.52099609375,
|
16 |
+
"logits/rejected": 2785.021484375,
|
17 |
+
"logps/chosen": -212.45889282226562,
|
18 |
+
"logps/rejected": -98.59669494628906,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.007849293563579277,
|
28 |
+
"grad_norm": 6.05072585015556,
|
29 |
+
"learning_rate": 3.9062499999999997e-08,
|
30 |
+
"logits/chosen": 4973.81005859375,
|
31 |
+
"logits/rejected": 4328.2421875,
|
32 |
+
"logps/chosen": -204.26458740234375,
|
33 |
+
"logps/rejected": -179.73109436035156,
|
34 |
+
"loss": 0.6931,
|
35 |
+
"rewards/accuracies": 0.5092592835426331,
|
36 |
+
"rewards/chosen": 0.019286984577775,
|
37 |
+
"rewards/margins": 0.04475558549165726,
|
38 |
+
"rewards/rejected": -0.025468600913882256,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015698587127158554,
|
43 |
+
"grad_norm": 6.19573847618762,
|
44 |
+
"learning_rate": 7.812499999999999e-08,
|
45 |
+
"logits/chosen": 6084.08447265625,
|
46 |
+
"logits/rejected": 4834.19189453125,
|
47 |
+
"logps/chosen": -217.2179412841797,
|
48 |
+
"logps/rejected": -196.71627807617188,
|
49 |
+
"loss": 0.6932,
|
50 |
+
"rewards/accuracies": 0.491666704416275,
|
51 |
+
"rewards/chosen": -0.006735034286975861,
|
52 |
+
"rewards/margins": -0.00402786722406745,
|
53 |
+
"rewards/rejected": -0.002707168459892273,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.023547880690737835,
|
58 |
+
"grad_norm": 5.478939628494671,
|
59 |
+
"learning_rate": 1.1718749999999999e-07,
|
60 |
+
"logits/chosen": 6084.3291015625,
|
61 |
+
"logits/rejected": 5104.9287109375,
|
62 |
+
"logps/chosen": -250.56930541992188,
|
63 |
+
"logps/rejected": -209.365966796875,
|
64 |
+
"loss": 0.693,
|
65 |
+
"rewards/accuracies": 0.5916666388511658,
|
66 |
+
"rewards/chosen": 0.0030434236396104097,
|
67 |
+
"rewards/margins": 0.07141536474227905,
|
68 |
+
"rewards/rejected": -0.06837192922830582,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03139717425431711,
|
73 |
+
"grad_norm": 5.683384309053487,
|
74 |
+
"learning_rate": 1.5624999999999999e-07,
|
75 |
+
"logits/chosen": 5311.80126953125,
|
76 |
+
"logits/rejected": 4346.90771484375,
|
77 |
+
"logps/chosen": -212.0178985595703,
|
78 |
+
"logps/rejected": -181.733642578125,
|
79 |
+
"loss": 0.6928,
|
80 |
+
"rewards/accuracies": 0.5916666984558105,
|
81 |
+
"rewards/chosen": 0.06136460229754448,
|
82 |
+
"rewards/margins": 0.10798362642526627,
|
83 |
+
"rewards/rejected": -0.04661902040243149,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.03924646781789639,
|
88 |
+
"grad_norm": 5.773772011816319,
|
89 |
+
"learning_rate": 1.9531249999999998e-07,
|
90 |
+
"logits/chosen": 6425.0439453125,
|
91 |
+
"logits/rejected": 5042.47119140625,
|
92 |
+
"logps/chosen": -265.3039855957031,
|
93 |
+
"logps/rejected": -206.7879180908203,
|
94 |
+
"loss": 0.6924,
|
95 |
+
"rewards/accuracies": 0.6666666865348816,
|
96 |
+
"rewards/chosen": 0.32259494066238403,
|
97 |
+
"rewards/margins": 0.4108748435974121,
|
98 |
+
"rewards/rejected": -0.08827991783618927,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04709576138147567,
|
103 |
+
"grad_norm": 5.549546838003912,
|
104 |
+
"learning_rate": 2.3437499999999998e-07,
|
105 |
+
"logits/chosen": 5484.3701171875,
|
106 |
+
"logits/rejected": 4559.94970703125,
|
107 |
+
"logps/chosen": -213.7654266357422,
|
108 |
+
"logps/rejected": -209.1769256591797,
|
109 |
+
"loss": 0.6918,
|
110 |
+
"rewards/accuracies": 0.6666666865348816,
|
111 |
+
"rewards/chosen": 0.23852241039276123,
|
112 |
+
"rewards/margins": 0.6153593063354492,
|
113 |
+
"rewards/rejected": -0.3768369257450104,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.054945054945054944,
|
118 |
+
"grad_norm": 5.3363089121065395,
|
119 |
+
"learning_rate": 2.734375e-07,
|
120 |
+
"logits/chosen": 5194.4814453125,
|
121 |
+
"logits/rejected": 4918.6982421875,
|
122 |
+
"logps/chosen": -178.33897399902344,
|
123 |
+
"logps/rejected": -177.4080047607422,
|
124 |
+
"loss": 0.6911,
|
125 |
+
"rewards/accuracies": 0.6750000715255737,
|
126 |
+
"rewards/chosen": 0.14194367825984955,
|
127 |
+
"rewards/margins": 0.8182166218757629,
|
128 |
+
"rewards/rejected": -0.6762728691101074,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.06279434850863422,
|
133 |
+
"grad_norm": 5.589990285987142,
|
134 |
+
"learning_rate": 3.1249999999999997e-07,
|
135 |
+
"logits/chosen": 5774.57080078125,
|
136 |
+
"logits/rejected": 5269.759765625,
|
137 |
+
"logps/chosen": -196.86941528320312,
|
138 |
+
"logps/rejected": -183.05673217773438,
|
139 |
+
"loss": 0.6889,
|
140 |
+
"rewards/accuracies": 0.6333333253860474,
|
141 |
+
"rewards/chosen": -0.3008244037628174,
|
142 |
+
"rewards/margins": 1.1653871536254883,
|
143 |
+
"rewards/rejected": -1.4662115573883057,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0706436420722135,
|
148 |
+
"grad_norm": 6.3326385736616,
|
149 |
+
"learning_rate": 3.5156249999999997e-07,
|
150 |
+
"logits/chosen": 6037.1435546875,
|
151 |
+
"logits/rejected": 5178.23046875,
|
152 |
+
"logps/chosen": -220.5373077392578,
|
153 |
+
"logps/rejected": -191.18222045898438,
|
154 |
+
"loss": 0.6847,
|
155 |
+
"rewards/accuracies": 0.7583332657814026,
|
156 |
+
"rewards/chosen": -1.6551120281219482,
|
157 |
+
"rewards/margins": 5.083296298980713,
|
158 |
+
"rewards/rejected": -6.738408088684082,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07849293563579278,
|
163 |
+
"grad_norm": 7.037637671287219,
|
164 |
+
"learning_rate": 3.9062499999999997e-07,
|
165 |
+
"logits/chosen": 5949.7509765625,
|
166 |
+
"logits/rejected": 5727.8193359375,
|
167 |
+
"logps/chosen": -216.74551391601562,
|
168 |
+
"logps/rejected": -212.49813842773438,
|
169 |
+
"loss": 0.684,
|
170 |
+
"rewards/accuracies": 0.6583333611488342,
|
171 |
+
"rewards/chosen": -6.514804840087891,
|
172 |
+
"rewards/margins": 6.541618347167969,
|
173 |
+
"rewards/rejected": -13.056424140930176,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08634222919937205,
|
178 |
+
"grad_norm": 6.748245033085064,
|
179 |
+
"learning_rate": 4.2968749999999996e-07,
|
180 |
+
"logits/chosen": 6423.7314453125,
|
181 |
+
"logits/rejected": 5241.818359375,
|
182 |
+
"logps/chosen": -198.58094787597656,
|
183 |
+
"logps/rejected": -202.92428588867188,
|
184 |
+
"loss": 0.6778,
|
185 |
+
"rewards/accuracies": 0.6750000715255737,
|
186 |
+
"rewards/chosen": -15.466090202331543,
|
187 |
+
"rewards/margins": 8.465994834899902,
|
188 |
+
"rewards/rejected": -23.932086944580078,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.09419152276295134,
|
193 |
+
"grad_norm": 10.445551519317151,
|
194 |
+
"learning_rate": 4.6874999999999996e-07,
|
195 |
+
"logits/chosen": 6351.18212890625,
|
196 |
+
"logits/rejected": 5273.6953125,
|
197 |
+
"logps/chosen": -226.8378143310547,
|
198 |
+
"logps/rejected": -234.71200561523438,
|
199 |
+
"loss": 0.672,
|
200 |
+
"rewards/accuracies": 0.625,
|
201 |
+
"rewards/chosen": -24.001096725463867,
|
202 |
+
"rewards/margins": 12.545796394348145,
|
203 |
+
"rewards/rejected": -36.54689025878906,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.10204081632653061,
|
208 |
+
"grad_norm": 7.973080880427375,
|
209 |
+
"learning_rate": 4.999962424962166e-07,
|
210 |
+
"logits/chosen": 6361.275390625,
|
211 |
+
"logits/rejected": 5860.3828125,
|
212 |
+
"logps/chosen": -239.5140838623047,
|
213 |
+
"logps/rejected": -246.1350555419922,
|
214 |
+
"loss": 0.6659,
|
215 |
+
"rewards/accuracies": 0.6833333373069763,
|
216 |
+
"rewards/chosen": -29.705577850341797,
|
217 |
+
"rewards/margins": 18.78491973876953,
|
218 |
+
"rewards/rejected": -48.490501403808594,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.10989010989010989,
|
223 |
+
"grad_norm": 9.656148828714871,
|
224 |
+
"learning_rate": 4.998647417232375e-07,
|
225 |
+
"logits/chosen": 6324.2783203125,
|
226 |
+
"logits/rejected": 5568.7294921875,
|
227 |
+
"logps/chosen": -233.6736602783203,
|
228 |
+
"logps/rejected": -243.1141815185547,
|
229 |
+
"loss": 0.6643,
|
230 |
+
"rewards/accuracies": 0.6500000357627869,
|
231 |
+
"rewards/chosen": -48.00621795654297,
|
232 |
+
"rewards/margins": 17.51606559753418,
|
233 |
+
"rewards/rejected": -65.52229309082031,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.11773940345368916,
|
238 |
+
"grad_norm": 12.68709283782261,
|
239 |
+
"learning_rate": 4.995454786965036e-07,
|
240 |
+
"logits/chosen": 6543.3310546875,
|
241 |
+
"logits/rejected": 5417.107421875,
|
242 |
+
"logps/chosen": -245.687744140625,
|
243 |
+
"logps/rejected": -238.84017944335938,
|
244 |
+
"loss": 0.6608,
|
245 |
+
"rewards/accuracies": 0.6833333373069763,
|
246 |
+
"rewards/chosen": -44.00338363647461,
|
247 |
+
"rewards/margins": 22.5390682220459,
|
248 |
+
"rewards/rejected": -66.5424575805664,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.12558869701726844,
|
253 |
+
"grad_norm": 8.336675270819248,
|
254 |
+
"learning_rate": 4.990386933279972e-07,
|
255 |
+
"logits/chosen": 6377.17236328125,
|
256 |
+
"logits/rejected": 5662.22607421875,
|
257 |
+
"logps/chosen": -243.30667114257812,
|
258 |
+
"logps/rejected": -268.36431884765625,
|
259 |
+
"loss": 0.6573,
|
260 |
+
"rewards/accuracies": 0.6750000715255737,
|
261 |
+
"rewards/chosen": -45.77846145629883,
|
262 |
+
"rewards/margins": 25.528247833251953,
|
263 |
+
"rewards/rejected": -71.30671691894531,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.13343799058084774,
|
268 |
+
"grad_norm": 9.518393732214355,
|
269 |
+
"learning_rate": 4.983447664444096e-07,
|
270 |
+
"logits/chosen": 6593.54541015625,
|
271 |
+
"logits/rejected": 5842.90625,
|
272 |
+
"logps/chosen": -261.85162353515625,
|
273 |
+
"logps/rejected": -269.01934814453125,
|
274 |
+
"loss": 0.6572,
|
275 |
+
"rewards/accuracies": 0.6416667103767395,
|
276 |
+
"rewards/chosen": -52.23096466064453,
|
277 |
+
"rewards/margins": 20.466854095458984,
|
278 |
+
"rewards/rejected": -72.69782257080078,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.141287284144427,
|
283 |
+
"grad_norm": 9.551095723742446,
|
284 |
+
"learning_rate": 4.97464219500968e-07,
|
285 |
+
"logits/chosen": 5738.0458984375,
|
286 |
+
"logits/rejected": 4965.66162109375,
|
287 |
+
"logps/chosen": -243.9608917236328,
|
288 |
+
"logps/rejected": -260.8826599121094,
|
289 |
+
"loss": 0.6523,
|
290 |
+
"rewards/accuracies": 0.6916667222976685,
|
291 |
+
"rewards/chosen": -55.4331169128418,
|
292 |
+
"rewards/margins": 27.288272857666016,
|
293 |
+
"rewards/rejected": -82.72139739990234,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.14913657770800628,
|
298 |
+
"grad_norm": 9.729373391308025,
|
299 |
+
"learning_rate": 4.963977141895843e-07,
|
300 |
+
"logits/chosen": 5827.6171875,
|
301 |
+
"logits/rejected": 4940.27880859375,
|
302 |
+
"logps/chosen": -265.14093017578125,
|
303 |
+
"logps/rejected": -304.3471374511719,
|
304 |
+
"loss": 0.6414,
|
305 |
+
"rewards/accuracies": 0.7416666746139526,
|
306 |
+
"rewards/chosen": -61.3819694519043,
|
307 |
+
"rewards/margins": 51.72563934326172,
|
308 |
+
"rewards/rejected": -113.10758972167969,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.15698587127158556,
|
313 |
+
"grad_norm": 12.708150524514142,
|
314 |
+
"learning_rate": 4.951460519416227e-07,
|
315 |
+
"logits/chosen": 5715.02197265625,
|
316 |
+
"logits/rejected": 5263.1376953125,
|
317 |
+
"logps/chosen": -255.45626831054688,
|
318 |
+
"logps/rejected": -308.5564880371094,
|
319 |
+
"loss": 0.6432,
|
320 |
+
"rewards/accuracies": 0.7333333492279053,
|
321 |
+
"rewards/chosen": -72.91200256347656,
|
322 |
+
"rewards/margins": 38.973487854003906,
|
323 |
+
"rewards/rejected": -111.8854751586914,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16483516483516483,
|
328 |
+
"grad_norm": 13.38335440738734,
|
329 |
+
"learning_rate": 4.937101733256606e-07,
|
330 |
+
"logits/chosen": 5213.759765625,
|
331 |
+
"logits/rejected": 4587.78564453125,
|
332 |
+
"logps/chosen": -221.2035675048828,
|
333 |
+
"logps/rejected": -255.7327423095703,
|
334 |
+
"loss": 0.645,
|
335 |
+
"rewards/accuracies": 0.6666666269302368,
|
336 |
+
"rewards/chosen": -67.2903060913086,
|
337 |
+
"rewards/margins": 31.2614688873291,
|
338 |
+
"rewards/rejected": -98.5517807006836,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1726844583987441,
|
343 |
+
"grad_norm": 13.23088850436655,
|
344 |
+
"learning_rate": 4.920911573406924e-07,
|
345 |
+
"logits/chosen": 6382.59326171875,
|
346 |
+
"logits/rejected": 5369.0458984375,
|
347 |
+
"logps/chosen": -254.50845336914062,
|
348 |
+
"logps/rejected": -261.02984619140625,
|
349 |
+
"loss": 0.6396,
|
350 |
+
"rewards/accuracies": 0.7083333730697632,
|
351 |
+
"rewards/chosen": -58.17182159423828,
|
352 |
+
"rewards/margins": 38.86132049560547,
|
353 |
+
"rewards/rejected": -97.03313446044922,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.18053375196232338,
|
358 |
+
"grad_norm": 13.7002975170986,
|
359 |
+
"learning_rate": 4.902902206053098e-07,
|
360 |
+
"logits/chosen": 5725.72998046875,
|
361 |
+
"logits/rejected": 5134.1142578125,
|
362 |
+
"logps/chosen": -295.9504089355469,
|
363 |
+
"logps/rejected": -334.36383056640625,
|
364 |
+
"loss": 0.641,
|
365 |
+
"rewards/accuracies": 0.6750000715255737,
|
366 |
+
"rewards/chosen": -108.6116714477539,
|
367 |
+
"rewards/margins": 45.984703063964844,
|
368 |
+
"rewards/rejected": -154.59637451171875,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.18838304552590268,
|
373 |
+
"grad_norm": 11.470848035692125,
|
374 |
+
"learning_rate": 4.883087164434672e-07,
|
375 |
+
"logits/chosen": 5131.9599609375,
|
376 |
+
"logits/rejected": 4044.186279296875,
|
377 |
+
"logps/chosen": -262.76409912109375,
|
378 |
+
"logps/rejected": -300.7772521972656,
|
379 |
+
"loss": 0.63,
|
380 |
+
"rewards/accuracies": 0.675000011920929,
|
381 |
+
"rewards/chosen": -95.13509368896484,
|
382 |
+
"rewards/margins": 50.95269012451172,
|
383 |
+
"rewards/rejected": -146.08779907226562,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.19623233908948196,
|
388 |
+
"grad_norm": 16.695171401268386,
|
389 |
+
"learning_rate": 4.861481338675183e-07,
|
390 |
+
"logits/chosen": 6127.5693359375,
|
391 |
+
"logits/rejected": 5402.2724609375,
|
392 |
+
"logps/chosen": -271.9035949707031,
|
393 |
+
"logps/rejected": -345.59136962890625,
|
394 |
+
"loss": 0.6424,
|
395 |
+
"rewards/accuracies": 0.7083333134651184,
|
396 |
+
"rewards/chosen": -104.75971984863281,
|
397 |
+
"rewards/margins": 56.324981689453125,
|
398 |
+
"rewards/rejected": -161.08468627929688,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.20408163265306123,
|
403 |
+
"grad_norm": 15.604975772107185,
|
404 |
+
"learning_rate": 4.838100964592904e-07,
|
405 |
+
"logits/chosen": 6368.3525390625,
|
406 |
+
"logits/rejected": 5054.92529296875,
|
407 |
+
"logps/chosen": -287.34759521484375,
|
408 |
+
"logps/rejected": -301.80914306640625,
|
409 |
+
"loss": 0.6438,
|
410 |
+
"rewards/accuracies": 0.7416666746139526,
|
411 |
+
"rewards/chosen": -87.629150390625,
|
412 |
+
"rewards/margins": 47.95604705810547,
|
413 |
+
"rewards/rejected": -135.585205078125,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2119309262166405,
|
418 |
+
"grad_norm": 12.014162614621322,
|
419 |
+
"learning_rate": 4.812963611500339e-07,
|
420 |
+
"logits/chosen": 6167.998046875,
|
421 |
+
"logits/rejected": 5935.1181640625,
|
422 |
+
"logps/chosen": -288.6238708496094,
|
423 |
+
"logps/rejected": -318.166015625,
|
424 |
+
"loss": 0.6315,
|
425 |
+
"rewards/accuracies": 0.7166667580604553,
|
426 |
+
"rewards/chosen": -91.86804962158203,
|
427 |
+
"rewards/margins": 37.66888427734375,
|
428 |
+
"rewards/rejected": -129.5369415283203,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21978021978021978,
|
433 |
+
"grad_norm": 25.285219401191153,
|
434 |
+
"learning_rate": 4.786088169001671e-07,
|
435 |
+
"logits/chosen": 5262.55029296875,
|
436 |
+
"logits/rejected": 4536.3759765625,
|
437 |
+
"logps/chosen": -249.36483764648438,
|
438 |
+
"logps/rejected": -323.6359558105469,
|
439 |
+
"loss": 0.6274,
|
440 |
+
"rewards/accuracies": 0.7749999761581421,
|
441 |
+
"rewards/chosen": -86.21394348144531,
|
442 |
+
"rewards/margins": 68.12052917480469,
|
443 |
+
"rewards/rejected": -154.33448791503906,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.22762951334379905,
|
448 |
+
"grad_norm": 21.48499040413718,
|
449 |
+
"learning_rate": 4.7574948327980567e-07,
|
450 |
+
"logits/chosen": 7437.4541015625,
|
451 |
+
"logits/rejected": 5381.4013671875,
|
452 |
+
"logps/chosen": -332.65570068359375,
|
453 |
+
"logps/rejected": -372.79583740234375,
|
454 |
+
"loss": 0.6225,
|
455 |
+
"rewards/accuracies": 0.7916666865348816,
|
456 |
+
"rewards/chosen": -95.62727355957031,
|
457 |
+
"rewards/margins": 94.65281677246094,
|
458 |
+
"rewards/rejected": -190.28009033203125,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.23547880690737832,
|
463 |
+
"grad_norm": 14.64094770923456,
|
464 |
+
"learning_rate": 4.727205089511466e-07,
|
465 |
+
"logits/chosen": 5407.33056640625,
|
466 |
+
"logits/rejected": 5314.2958984375,
|
467 |
+
"logps/chosen": -247.26754760742188,
|
468 |
+
"logps/rejected": -310.8182678222656,
|
469 |
+
"loss": 0.6323,
|
470 |
+
"rewards/accuracies": 0.7250000238418579,
|
471 |
+
"rewards/chosen": -79.79512023925781,
|
472 |
+
"rewards/margins": 60.83668899536133,
|
473 |
+
"rewards/rejected": -140.63180541992188,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.24332810047095763,
|
478 |
+
"grad_norm": 15.88030348707004,
|
479 |
+
"learning_rate": 4.6952417005384247e-07,
|
480 |
+
"logits/chosen": 6043.89404296875,
|
481 |
+
"logits/rejected": 5373.5927734375,
|
482 |
+
"logps/chosen": -264.2408752441406,
|
483 |
+
"logps/rejected": -301.0606994628906,
|
484 |
+
"loss": 0.6422,
|
485 |
+
"rewards/accuracies": 0.7250000238418579,
|
486 |
+
"rewards/chosen": -86.66017150878906,
|
487 |
+
"rewards/margins": 38.932220458984375,
|
488 |
+
"rewards/rejected": -125.5923843383789,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.25117739403453687,
|
493 |
+
"grad_norm": 12.942810394852572,
|
494 |
+
"learning_rate": 4.661628684945851e-07,
|
495 |
+
"logits/chosen": 5981.30615234375,
|
496 |
+
"logits/rejected": 5134.4638671875,
|
497 |
+
"logps/chosen": -321.04461669921875,
|
498 |
+
"logps/rejected": -394.8025817871094,
|
499 |
+
"loss": 0.6322,
|
500 |
+
"rewards/accuracies": 0.7416666746139526,
|
501 |
+
"rewards/chosen": -119.98759460449219,
|
502 |
+
"rewards/margins": 72.79707336425781,
|
503 |
+
"rewards/rejected": -192.78469848632812,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.25902668759811615,
|
508 |
+
"grad_norm": 17.65657239960532,
|
509 |
+
"learning_rate": 4.626391301421782e-07,
|
510 |
+
"logits/chosen": 5767.1728515625,
|
511 |
+
"logits/rejected": 5235.9375,
|
512 |
+
"logps/chosen": -319.49798583984375,
|
513 |
+
"logps/rejected": -344.1056213378906,
|
514 |
+
"loss": 0.6455,
|
515 |
+
"rewards/accuracies": 0.7416667342185974,
|
516 |
+
"rewards/chosen": -125.0447769165039,
|
517 |
+
"rewards/margins": 41.73804473876953,
|
518 |
+
"rewards/rejected": -166.78280639648438,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.2668759811616955,
|
523 |
+
"grad_norm": 10.256221501911574,
|
524 |
+
"learning_rate": 4.5895560292945996e-07,
|
525 |
+
"logits/chosen": 6147.9560546875,
|
526 |
+
"logits/rejected": 6276.4072265625,
|
527 |
+
"logps/chosen": -274.11529541015625,
|
528 |
+
"logps/rejected": -340.8870849609375,
|
529 |
+
"loss": 0.651,
|
530 |
+
"rewards/accuracies": 0.699999988079071,
|
531 |
+
"rewards/chosen": -80.25703430175781,
|
532 |
+
"rewards/margins": 40.26253128051758,
|
533 |
+
"rewards/rejected": -120.51956939697266,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.27472527472527475,
|
538 |
+
"grad_norm": 23.69669876872275,
|
539 |
+
"learning_rate": 4.5511505486349865e-07,
|
540 |
+
"logits/chosen": 6537.46337890625,
|
541 |
+
"logits/rejected": 5889.2177734375,
|
542 |
+
"logps/chosen": -257.62890625,
|
543 |
+
"logps/rejected": -332.9743957519531,
|
544 |
+
"loss": 0.6256,
|
545 |
+
"rewards/accuracies": 0.7749999761581421,
|
546 |
+
"rewards/chosen": -62.803199768066406,
|
547 |
+
"rewards/margins": 63.349143981933594,
|
548 |
+
"rewards/rejected": -126.15234375,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.282574568288854,
|
553 |
+
"grad_norm": 16.915648438332628,
|
554 |
+
"learning_rate": 4.5112037194555876e-07,
|
555 |
+
"logits/chosen": 6069.42578125,
|
556 |
+
"logits/rejected": 5893.24951171875,
|
557 |
+
"logps/chosen": -293.303955078125,
|
558 |
+
"logps/rejected": -398.67724609375,
|
559 |
+
"loss": 0.6222,
|
560 |
+
"rewards/accuracies": 0.7833333611488342,
|
561 |
+
"rewards/chosen": -115.38047790527344,
|
562 |
+
"rewards/margins": 84.01496887207031,
|
563 |
+
"rewards/rejected": -199.39544677734375,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2904238618524333,
|
568 |
+
"grad_norm": 12.555265198666554,
|
569 |
+
"learning_rate": 4.4697455600239863e-07,
|
570 |
+
"logits/chosen": 5456.2978515625,
|
571 |
+
"logits/rejected": 5073.7060546875,
|
572 |
+
"logps/chosen": -296.23944091796875,
|
573 |
+
"logps/rejected": -330.85284423828125,
|
574 |
+
"loss": 0.6434,
|
575 |
+
"rewards/accuracies": 0.7083333134651184,
|
576 |
+
"rewards/chosen": -111.81736755371094,
|
577 |
+
"rewards/margins": 50.96443176269531,
|
578 |
+
"rewards/rejected": -162.78179931640625,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.29827315541601257,
|
583 |
+
"grad_norm": 14.362943259943494,
|
584 |
+
"learning_rate": 4.426807224305315e-07,
|
585 |
+
"logits/chosen": 6574.45458984375,
|
586 |
+
"logits/rejected": 5350.2958984375,
|
587 |
+
"logps/chosen": -315.9097595214844,
|
588 |
+
"logps/rejected": -338.9637451171875,
|
589 |
+
"loss": 0.6267,
|
590 |
+
"rewards/accuracies": 0.7666667103767395,
|
591 |
+
"rewards/chosen": -87.56874084472656,
|
592 |
+
"rewards/margins": 68.38545227050781,
|
593 |
+
"rewards/rejected": -155.95419311523438,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.30612244897959184,
|
598 |
+
"grad_norm": 17.276156747689946,
|
599 |
+
"learning_rate": 4.3824209785514326e-07,
|
600 |
+
"logits/chosen": 6646.9892578125,
|
601 |
+
"logits/rejected": 5010.45947265625,
|
602 |
+
"logps/chosen": -303.3409118652344,
|
603 |
+
"logps/rejected": -347.64373779296875,
|
604 |
+
"loss": 0.6345,
|
605 |
+
"rewards/accuracies": 0.7750000357627869,
|
606 |
+
"rewards/chosen": -87.84745788574219,
|
607 |
+
"rewards/margins": 79.94316101074219,
|
608 |
+
"rewards/rejected": -167.79061889648438,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3139717425431711,
|
613 |
+
"grad_norm": 16.15627046135233,
|
614 |
+
"learning_rate": 4.3366201770542687e-07,
|
615 |
+
"logits/chosen": 5679.2353515625,
|
616 |
+
"logits/rejected": 5516.23583984375,
|
617 |
+
"logps/chosen": -289.3190612792969,
|
618 |
+
"logps/rejected": -350.9610900878906,
|
619 |
+
"loss": 0.637,
|
620 |
+
"rewards/accuracies": 0.75,
|
621 |
+
"rewards/chosen": -98.53050994873047,
|
622 |
+
"rewards/margins": 63.691078186035156,
|
623 |
+
"rewards/rejected": -162.22158813476562,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.3218210361067504,
|
628 |
+
"grad_norm": 25.935620681417305,
|
629 |
+
"learning_rate": 4.2894392370815567e-07,
|
630 |
+
"logits/chosen": 6088.6064453125,
|
631 |
+
"logits/rejected": 5395.84912109375,
|
632 |
+
"logps/chosen": -339.7603759765625,
|
633 |
+
"logps/rejected": -411.3926696777344,
|
634 |
+
"loss": 0.6019,
|
635 |
+
"rewards/accuracies": 0.800000011920929,
|
636 |
+
"rewards/chosen": -127.27352142333984,
|
637 |
+
"rewards/margins": 75.66678619384766,
|
638 |
+
"rewards/rejected": -202.9403076171875,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.32967032967032966,
|
643 |
+
"grad_norm": 21.279196743760856,
|
644 |
+
"learning_rate": 4.2409136130137845e-07,
|
645 |
+
"logits/chosen": 5789.5654296875,
|
646 |
+
"logits/rejected": 5153.6044921875,
|
647 |
+
"logps/chosen": -319.99505615234375,
|
648 |
+
"logps/rejected": -372.98162841796875,
|
649 |
+
"loss": 0.6269,
|
650 |
+
"rewards/accuracies": 0.7333333492279053,
|
651 |
+
"rewards/chosen": -115.96516418457031,
|
652 |
+
"rewards/margins": 75.77505493164062,
|
653 |
+
"rewards/rejected": -191.74020385742188,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.33751962323390894,
|
658 |
+
"grad_norm": 14.662428194905122,
|
659 |
+
"learning_rate": 4.1910797697018017e-07,
|
660 |
+
"logits/chosen": 5631.46337890625,
|
661 |
+
"logits/rejected": 4653.8154296875,
|
662 |
+
"logps/chosen": -277.2632141113281,
|
663 |
+
"logps/rejected": -342.4476623535156,
|
664 |
+
"loss": 0.624,
|
665 |
+
"rewards/accuracies": 0.8583332896232605,
|
666 |
+
"rewards/chosen": -97.5182113647461,
|
667 |
+
"rewards/margins": 83.69635772705078,
|
668 |
+
"rewards/rejected": -181.21456909179688,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3453689167974882,
|
673 |
+
"grad_norm": 20.509381423565515,
|
674 |
+
"learning_rate": 4.1399751550651084e-07,
|
675 |
+
"logits/chosen": 5983.00341796875,
|
676 |
+
"logits/rejected": 5909.9189453125,
|
677 |
+
"logps/chosen": -294.4239807128906,
|
678 |
+
"logps/rejected": -366.37548828125,
|
679 |
+
"loss": 0.6294,
|
680 |
+
"rewards/accuracies": 0.7333333492279053,
|
681 |
+
"rewards/chosen": -112.0306396484375,
|
682 |
+
"rewards/margins": 62.66124725341797,
|
683 |
+
"rewards/rejected": -174.69189453125,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3532182103610675,
|
688 |
+
"grad_norm": 11.57774703743698,
|
689 |
+
"learning_rate": 4.087638171951401e-07,
|
690 |
+
"logits/chosen": 6951.85302734375,
|
691 |
+
"logits/rejected": 4954.27978515625,
|
692 |
+
"logps/chosen": -307.88006591796875,
|
693 |
+
"logps/rejected": -344.5763244628906,
|
694 |
+
"loss": 0.6245,
|
695 |
+
"rewards/accuracies": 0.7749999761581421,
|
696 |
+
"rewards/chosen": -99.11131286621094,
|
697 |
+
"rewards/margins": 82.47236633300781,
|
698 |
+
"rewards/rejected": -181.5836639404297,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.36106750392464676,
|
703 |
+
"grad_norm": 10.747587473405163,
|
704 |
+
"learning_rate": 4.034108149278543e-07,
|
705 |
+
"logits/chosen": 7119.5966796875,
|
706 |
+
"logits/rejected": 5446.58544921875,
|
707 |
+
"logps/chosen": -365.51141357421875,
|
708 |
+
"logps/rejected": -376.9080810546875,
|
709 |
+
"loss": 0.6136,
|
710 |
+
"rewards/accuracies": 0.7583333253860474,
|
711 |
+
"rewards/chosen": -115.07914733886719,
|
712 |
+
"rewards/margins": 71.62091064453125,
|
713 |
+
"rewards/rejected": -186.7000732421875,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.36891679748822603,
|
718 |
+
"grad_norm": 18.39563106747747,
|
719 |
+
"learning_rate": 3.979425312480629e-07,
|
720 |
+
"logits/chosen": 6053.51171875,
|
721 |
+
"logits/rejected": 5261.99365234375,
|
722 |
+
"logps/chosen": -349.2318420410156,
|
723 |
+
"logps/rejected": -409.2492370605469,
|
724 |
+
"loss": 0.634,
|
725 |
+
"rewards/accuracies": 0.7833333611488342,
|
726 |
+
"rewards/chosen": -136.96707153320312,
|
727 |
+
"rewards/margins": 69.71588134765625,
|
728 |
+
"rewards/rejected": -206.68295288085938,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.37676609105180536,
|
733 |
+
"grad_norm": 9.88717064834881,
|
734 |
+
"learning_rate": 3.923630753280357e-07,
|
735 |
+
"logits/chosen": 6531.0361328125,
|
736 |
+
"logits/rejected": 5563.5673828125,
|
737 |
+
"logps/chosen": -304.6759338378906,
|
738 |
+
"logps/rejected": -353.3858642578125,
|
739 |
+
"loss": 0.6225,
|
740 |
+
"rewards/accuracies": 0.7750000357627869,
|
741 |
+
"rewards/chosen": -97.28072357177734,
|
742 |
+
"rewards/margins": 81.7093734741211,
|
743 |
+
"rewards/rejected": -178.9901123046875,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.38461538461538464,
|
748 |
+
"grad_norm": 18.872015793003488,
|
749 |
+
"learning_rate": 3.866766398810424e-07,
|
750 |
+
"logits/chosen": 6090.294921875,
|
751 |
+
"logits/rejected": 5757.2998046875,
|
752 |
+
"logps/chosen": -270.914794921875,
|
753 |
+
"logps/rejected": -388.12066650390625,
|
754 |
+
"loss": 0.6047,
|
755 |
+
"rewards/accuracies": 0.824999988079071,
|
756 |
+
"rewards/chosen": -94.30628967285156,
|
757 |
+
"rewards/margins": 91.7900619506836,
|
758 |
+
"rewards/rejected": -186.0963592529297,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3924646781789639,
|
763 |
+
"grad_norm": 19.921576157729877,
|
764 |
+
"learning_rate": 3.8088749801071496e-07,
|
765 |
+
"logits/chosen": 6461.3857421875,
|
766 |
+
"logits/rejected": 4896.03759765625,
|
767 |
+
"logps/chosen": -404.9927673339844,
|
768 |
+
"logps/rejected": -488.85992431640625,
|
769 |
+
"loss": 0.6363,
|
770 |
+
"rewards/accuracies": 0.7583333849906921,
|
771 |
+
"rewards/chosen": -183.0391082763672,
|
772 |
+
"rewards/margins": 103.30455017089844,
|
773 |
+
"rewards/rejected": -286.3436584472656,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4003139717425432,
|
778 |
+
"grad_norm": 14.976740215989906,
|
779 |
+
"learning_rate": 3.75e-07,
|
780 |
+
"logits/chosen": 5273.30029296875,
|
781 |
+
"logits/rejected": 4571.634765625,
|
782 |
+
"logps/chosen": -316.82159423828125,
|
783 |
+
"logps/rejected": -388.461669921875,
|
784 |
+
"loss": 0.6164,
|
785 |
+
"rewards/accuracies": 0.800000011920929,
|
786 |
+
"rewards/chosen": -127.3386001586914,
|
787 |
+
"rewards/margins": 94.75777435302734,
|
788 |
+
"rewards/rejected": -222.0963897705078,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.40816326530612246,
|
793 |
+
"grad_norm": 15.310486602213532,
|
794 |
+
"learning_rate": 3.6901857004211443e-07,
|
795 |
+
"logits/chosen": 5530.29443359375,
|
796 |
+
"logits/rejected": 5099.7265625,
|
797 |
+
"logps/chosen": -315.60919189453125,
|
798 |
+
"logps/rejected": -381.65789794921875,
|
799 |
+
"loss": 0.6418,
|
800 |
+
"rewards/accuracies": 0.699999988079071,
|
801 |
+
"rewards/chosen": -117.1432113647461,
|
802 |
+
"rewards/margins": 68.7266845703125,
|
803 |
+
"rewards/rejected": -185.86990356445312,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.41601255886970173,
|
808 |
+
"grad_norm": 14.08983541941681,
|
809 |
+
"learning_rate": 3.6294770291596076e-07,
|
810 |
+
"logits/chosen": 6285.1962890625,
|
811 |
+
"logits/rejected": 5097.83935546875,
|
812 |
+
"logps/chosen": -322.7880554199219,
|
813 |
+
"logps/rejected": -361.3253479003906,
|
814 |
+
"loss": 0.6168,
|
815 |
+
"rewards/accuracies": 0.6916666030883789,
|
816 |
+
"rewards/chosen": -109.86531829833984,
|
817 |
+
"rewards/margins": 52.69968795776367,
|
818 |
+
"rewards/rejected": -162.5650177001953,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.423861852433281,
|
823 |
+
"grad_norm": 20.022842230444766,
|
824 |
+
"learning_rate": 3.5679196060850034e-07,
|
825 |
+
"logits/chosen": 5982.83935546875,
|
826 |
+
"logits/rejected": 5300.0537109375,
|
827 |
+
"logps/chosen": -333.60455322265625,
|
828 |
+
"logps/rejected": -389.5378723144531,
|
829 |
+
"loss": 0.6173,
|
830 |
+
"rewards/accuracies": 0.7416666746139526,
|
831 |
+
"rewards/chosen": -122.7867431640625,
|
832 |
+
"rewards/margins": 78.51233673095703,
|
833 |
+
"rewards/rejected": -201.29908752441406,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.4317111459968603,
|
838 |
+
"grad_norm": 24.653995851898625,
|
839 |
+
"learning_rate": 3.505559688866229e-07,
|
840 |
+
"logits/chosen": 5769.158203125,
|
841 |
+
"logits/rejected": 5321.18359375,
|
842 |
+
"logps/chosen": -375.0007019042969,
|
843 |
+
"logps/rejected": -469.31951904296875,
|
844 |
+
"loss": 0.6294,
|
845 |
+
"rewards/accuracies": 0.7500000596046448,
|
846 |
+
"rewards/chosen": -160.26025390625,
|
847 |
+
"rewards/margins": 83.9951171875,
|
848 |
+
"rewards/rejected": -244.25537109375,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.43956043956043955,
|
853 |
+
"grad_norm": 17.972565211019212,
|
854 |
+
"learning_rate": 3.4424441382108826e-07,
|
855 |
+
"logits/chosen": 5792.72998046875,
|
856 |
+
"logits/rejected": 5407.20068359375,
|
857 |
+
"logps/chosen": -351.23291015625,
|
858 |
+
"logps/rejected": -403.1977233886719,
|
859 |
+
"loss": 0.6269,
|
860 |
+
"rewards/accuracies": 0.7083333730697632,
|
861 |
+
"rewards/chosen": -147.9576416015625,
|
862 |
+
"rewards/margins": 62.0308952331543,
|
863 |
+
"rewards/rejected": -209.98855590820312,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.4474097331240188,
|
868 |
+
"grad_norm": 18.423331599938237,
|
869 |
+
"learning_rate": 3.378620382651523e-07,
|
870 |
+
"logits/chosen": 6100.2392578125,
|
871 |
+
"logits/rejected": 5616.0419921875,
|
872 |
+
"logps/chosen": -368.9530334472656,
|
873 |
+
"logps/rejected": -418.500732421875,
|
874 |
+
"loss": 0.6102,
|
875 |
+
"rewards/accuracies": 0.7749999761581421,
|
876 |
+
"rewards/chosen": -125.99314880371094,
|
877 |
+
"rewards/margins": 68.73707580566406,
|
878 |
+
"rewards/rejected": -194.730224609375,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4552590266875981,
|
883 |
+
"grad_norm": 40.58588385026,
|
884 |
+
"learning_rate": 3.314136382905234e-07,
|
885 |
+
"logits/chosen": 6104.7314453125,
|
886 |
+
"logits/rejected": 5396.8330078125,
|
887 |
+
"logps/chosen": -345.4382629394531,
|
888 |
+
"logps/rejected": -464.142578125,
|
889 |
+
"loss": 0.6198,
|
890 |
+
"rewards/accuracies": 0.783333420753479,
|
891 |
+
"rewards/chosen": -133.0227813720703,
|
892 |
+
"rewards/margins": 117.80845642089844,
|
893 |
+
"rewards/rejected": -250.8312530517578,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.4631083202511774,
|
898 |
+
"grad_norm": 21.906951775528675,
|
899 |
+
"learning_rate": 3.249040595833274e-07,
|
900 |
+
"logits/chosen": 6578.75537109375,
|
901 |
+
"logits/rejected": 5453.22900390625,
|
902 |
+
"logps/chosen": -414.60174560546875,
|
903 |
+
"logps/rejected": -468.26995849609375,
|
904 |
+
"loss": 0.6167,
|
905 |
+
"rewards/accuracies": 0.7666667103767395,
|
906 |
+
"rewards/chosen": -182.8759307861328,
|
907 |
+
"rewards/margins": 106.53523254394531,
|
908 |
+
"rewards/rejected": -289.41119384765625,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.47095761381475665,
|
913 |
+
"grad_norm": 22.906733288517135,
|
914 |
+
"learning_rate": 3.1833819380279023e-07,
|
915 |
+
"logits/chosen": 6241.1650390625,
|
916 |
+
"logits/rejected": 5260.3125,
|
917 |
+
"logps/chosen": -361.357666015625,
|
918 |
+
"logps/rejected": -456.5220642089844,
|
919 |
+
"loss": 0.6132,
|
920 |
+
"rewards/accuracies": 0.783333420753479,
|
921 |
+
"rewards/chosen": -183.8093719482422,
|
922 |
+
"rewards/margins": 83.0264663696289,
|
923 |
+
"rewards/rejected": -266.8358154296875,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.478806907378336,
|
928 |
+
"grad_norm": 12.469826515590201,
|
929 |
+
"learning_rate": 3.11720974905373e-07,
|
930 |
+
"logits/chosen": 6012.91552734375,
|
931 |
+
"logits/rejected": 5177.1376953125,
|
932 |
+
"logps/chosen": -345.945068359375,
|
933 |
+
"logps/rejected": -407.5060729980469,
|
934 |
+
"loss": 0.6138,
|
935 |
+
"rewards/accuracies": 0.7833333611488342,
|
936 |
+
"rewards/chosen": -139.82691955566406,
|
937 |
+
"rewards/margins": 82.2566146850586,
|
938 |
+
"rewards/rejected": -222.0835418701172,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.48665620094191525,
|
943 |
+
"grad_norm": 13.764094508128613,
|
944 |
+
"learning_rate": 3.0505737543712275e-07,
|
945 |
+
"logits/chosen": 5078.953125,
|
946 |
+
"logits/rejected": 4125.95361328125,
|
947 |
+
"logps/chosen": -322.87664794921875,
|
948 |
+
"logps/rejected": -369.62127685546875,
|
949 |
+
"loss": 0.6162,
|
950 |
+
"rewards/accuracies": 0.75,
|
951 |
+
"rewards/chosen": -139.11798095703125,
|
952 |
+
"rewards/margins": 69.40438079833984,
|
953 |
+
"rewards/rejected": -208.52236938476562,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4945054945054945,
|
958 |
+
"grad_norm": 27.054436253186108,
|
959 |
+
"learning_rate": 2.9835240279702513e-07,
|
960 |
+
"logits/chosen": 6608.65478515625,
|
961 |
+
"logits/rejected": 5554.52587890625,
|
962 |
+
"logps/chosen": -362.4518127441406,
|
963 |
+
"logps/rejected": -418.16998291015625,
|
964 |
+
"loss": 0.6106,
|
965 |
+
"rewards/accuracies": 0.7916666865348816,
|
966 |
+
"rewards/chosen": -119.63581848144531,
|
967 |
+
"rewards/margins": 104.2861328125,
|
968 |
+
"rewards/rejected": -223.9219512939453,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.5023547880690737,
|
973 |
+
"grad_norm": 17.671754927072275,
|
974 |
+
"learning_rate": 2.9161109547416667e-07,
|
975 |
+
"logits/chosen": 6268.4951171875,
|
976 |
+
"logits/rejected": 5317.8037109375,
|
977 |
+
"logps/chosen": -364.1328125,
|
978 |
+
"logps/rejected": -429.2177734375,
|
979 |
+
"loss": 0.6135,
|
980 |
+
"rewards/accuracies": 0.699999988079071,
|
981 |
+
"rewards/chosen": -153.37124633789062,
|
982 |
+
"rewards/margins": 61.33759689331055,
|
983 |
+
"rewards/rejected": -214.70883178710938,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.5102040816326531,
|
988 |
+
"grad_norm": 14.137157591920442,
|
989 |
+
"learning_rate": 2.848385192615339e-07,
|
990 |
+
"logits/chosen": 5331.8037109375,
|
991 |
+
"logits/rejected": 4288.7294921875,
|
992 |
+
"logps/chosen": -347.09747314453125,
|
993 |
+
"logps/rejected": -396.7239074707031,
|
994 |
+
"loss": 0.6211,
|
995 |
+
"rewards/accuracies": 0.8000000715255737,
|
996 |
+
"rewards/chosen": -150.75814819335938,
|
997 |
+
"rewards/margins": 77.23800659179688,
|
998 |
+
"rewards/rejected": -227.9961395263672,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5180533751962323,
|
1003 |
+
"grad_norm": 16.88587503102184,
|
1004 |
+
"learning_rate": 2.780397634492949e-07,
|
1005 |
+
"logits/chosen": 5999.3125,
|
1006 |
+
"logits/rejected": 4691.3330078125,
|
1007 |
+
"logps/chosen": -358.98828125,
|
1008 |
+
"logps/rejected": -429.1502380371094,
|
1009 |
+
"loss": 0.6216,
|
1010 |
+
"rewards/accuracies": 0.8166666030883789,
|
1011 |
+
"rewards/chosen": -141.60177612304688,
|
1012 |
+
"rewards/margins": 99.60104370117188,
|
1013 |
+
"rewards/rejected": -241.2028045654297,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5259026687598116,
|
1018 |
+
"grad_norm": 22.96076824322748,
|
1019 |
+
"learning_rate": 2.71219937000424e-07,
|
1020 |
+
"logits/chosen": 6003.61962890625,
|
1021 |
+
"logits/rejected": 4884.7255859375,
|
1022 |
+
"logps/chosen": -345.4893493652344,
|
1023 |
+
"logps/rejected": -394.2846374511719,
|
1024 |
+
"loss": 0.6262,
|
1025 |
+
"rewards/accuracies": 0.7666667103767395,
|
1026 |
+
"rewards/chosen": -138.72991943359375,
|
1027 |
+
"rewards/margins": 66.7003402709961,
|
1028 |
+
"rewards/rejected": -205.4302520751953,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.533751962323391,
|
1033 |
+
"grad_norm": 22.813069309884035,
|
1034 |
+
"learning_rate": 2.6438416471154273e-07,
|
1035 |
+
"logits/chosen": 5843.70458984375,
|
1036 |
+
"logits/rejected": 4834.39599609375,
|
1037 |
+
"logps/chosen": -359.9562683105469,
|
1038 |
+
"logps/rejected": -401.135498046875,
|
1039 |
+
"loss": 0.6166,
|
1040 |
+
"rewards/accuracies": 0.7833333611488342,
|
1041 |
+
"rewards/chosen": -146.29505920410156,
|
1042 |
+
"rewards/margins": 75.61378479003906,
|
1043 |
+
"rewards/rejected": -221.9088592529297,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.5416012558869702,
|
1048 |
+
"grad_norm": 18.765764198829793,
|
1049 |
+
"learning_rate": 2.5753758336186326e-07,
|
1050 |
+
"logits/chosen": 5820.8349609375,
|
1051 |
+
"logits/rejected": 5283.55078125,
|
1052 |
+
"logps/chosen": -351.8568420410156,
|
1053 |
+
"logps/rejected": -444.1844787597656,
|
1054 |
+
"loss": 0.6021,
|
1055 |
+
"rewards/accuracies": 0.7916666269302368,
|
1056 |
+
"rewards/chosen": -142.75038146972656,
|
1057 |
+
"rewards/margins": 85.23744201660156,
|
1058 |
+
"rewards/rejected": -227.9878387451172,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5494505494505495,
|
1063 |
+
"grad_norm": 14.748661687164306,
|
1064 |
+
"learning_rate": 2.5068533785312666e-07,
|
1065 |
+
"logits/chosen": 5523.3955078125,
|
1066 |
+
"logits/rejected": 5268.107421875,
|
1067 |
+
"logps/chosen": -343.63934326171875,
|
1068 |
+
"logps/rejected": -420.27886962890625,
|
1069 |
+
"loss": 0.6369,
|
1070 |
+
"rewards/accuracies": 0.7333333492279053,
|
1071 |
+
"rewards/chosen": -154.3790283203125,
|
1072 |
+
"rewards/margins": 78.92584991455078,
|
1073 |
+
"rewards/rejected": -233.3048553466797,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.5572998430141287,
|
1078 |
+
"grad_norm": 15.464054804569159,
|
1079 |
+
"learning_rate": 2.4383257734343794e-07,
|
1080 |
+
"logits/chosen": 5437.234375,
|
1081 |
+
"logits/rejected": 5426.69677734375,
|
1082 |
+
"logps/chosen": -344.1163330078125,
|
1083 |
+
"logps/rejected": -430.07904052734375,
|
1084 |
+
"loss": 0.608,
|
1085 |
+
"rewards/accuracies": 0.7500000596046448,
|
1086 |
+
"rewards/chosen": -150.20494079589844,
|
1087 |
+
"rewards/margins": 77.2534408569336,
|
1088 |
+
"rewards/rejected": -227.4583740234375,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.565149136577708,
|
1093 |
+
"grad_norm": 18.732066069845217,
|
1094 |
+
"learning_rate": 2.3698445137790258e-07,
|
1095 |
+
"logits/chosen": 5845.06640625,
|
1096 |
+
"logits/rejected": 4940.61865234375,
|
1097 |
+
"logps/chosen": -361.6242370605469,
|
1098 |
+
"logps/rejected": -430.0552673339844,
|
1099 |
+
"loss": 0.6127,
|
1100 |
+
"rewards/accuracies": 0.75,
|
1101 |
+
"rewards/chosen": -142.62103271484375,
|
1102 |
+
"rewards/margins": 87.6690902709961,
|
1103 |
+
"rewards/rejected": -230.2901153564453,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5729984301412873,
|
1108 |
+
"grad_norm": 17.14795101097142,
|
1109 |
+
"learning_rate": 2.3014610601897157e-07,
|
1110 |
+
"logits/chosen": 6328.41552734375,
|
1111 |
+
"logits/rejected": 4775.5185546875,
|
1112 |
+
"logps/chosen": -369.47235107421875,
|
1113 |
+
"logps/rejected": -404.1590881347656,
|
1114 |
+
"loss": 0.6148,
|
1115 |
+
"rewards/accuracies": 0.7750000357627869,
|
1116 |
+
"rewards/chosen": -144.32643127441406,
|
1117 |
+
"rewards/margins": 84.75894165039062,
|
1118 |
+
"rewards/rejected": -229.08535766601562,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5808477237048666,
|
1123 |
+
"grad_norm": 13.832807015732437,
|
1124 |
+
"learning_rate": 2.2332267997940513e-07,
|
1125 |
+
"logits/chosen": 5258.61572265625,
|
1126 |
+
"logits/rejected": 4415.40576171875,
|
1127 |
+
"logps/chosen": -324.30242919921875,
|
1128 |
+
"logps/rejected": -375.59405517578125,
|
1129 |
+
"loss": 0.6053,
|
1130 |
+
"rewards/accuracies": 0.7666666507720947,
|
1131 |
+
"rewards/chosen": -131.87802124023438,
|
1132 |
+
"rewards/margins": 81.06999206542969,
|
1133 |
+
"rewards/rejected": -212.947998046875,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5886970172684458,
|
1138 |
+
"grad_norm": 15.482096718237434,
|
1139 |
+
"learning_rate": 2.1651930076075723e-07,
|
1140 |
+
"logits/chosen": 5748.50830078125,
|
1141 |
+
"logits/rejected": 5138.494140625,
|
1142 |
+
"logps/chosen": -329.36572265625,
|
1143 |
+
"logps/rejected": -381.31109619140625,
|
1144 |
+
"loss": 0.6253,
|
1145 |
+
"rewards/accuracies": 0.7416666746139526,
|
1146 |
+
"rewards/chosen": -148.93975830078125,
|
1147 |
+
"rewards/margins": 65.27706909179688,
|
1148 |
+
"rewards/rejected": -214.21682739257812,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.5965463108320251,
|
1153 |
+
"grad_norm": 16.50457423188824,
|
1154 |
+
"learning_rate": 2.0974108080028692e-07,
|
1155 |
+
"logits/chosen": 6050.1806640625,
|
1156 |
+
"logits/rejected": 4695.55126953125,
|
1157 |
+
"logps/chosen": -332.60772705078125,
|
1158 |
+
"logps/rejected": -383.9396057128906,
|
1159 |
+
"loss": 0.615,
|
1160 |
+
"rewards/accuracies": 0.7666667103767395,
|
1161 |
+
"rewards/chosen": -129.35684204101562,
|
1162 |
+
"rewards/margins": 80.0522232055664,
|
1163 |
+
"rewards/rejected": -209.4090576171875,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6043956043956044,
|
1168 |
+
"grad_norm": 16.19292968682205,
|
1169 |
+
"learning_rate": 2.0299311362918773e-07,
|
1170 |
+
"logits/chosen": 6270.7763671875,
|
1171 |
+
"logits/rejected": 5331.49755859375,
|
1172 |
+
"logps/chosen": -374.3070373535156,
|
1173 |
+
"logps/rejected": -449.4652404785156,
|
1174 |
+
"loss": 0.6274,
|
1175 |
+
"rewards/accuracies": 0.7250000238418579,
|
1176 |
+
"rewards/chosen": -144.57337951660156,
|
1177 |
+
"rewards/margins": 81.0317153930664,
|
1178 |
+
"rewards/rejected": -225.60513305664062,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6122448979591837,
|
1183 |
+
"grad_norm": 13.854569491977498,
|
1184 |
+
"learning_rate": 1.962804700450265e-07,
|
1185 |
+
"logits/chosen": 6101.94970703125,
|
1186 |
+
"logits/rejected": 5776.4658203125,
|
1187 |
+
"logps/chosen": -351.2977294921875,
|
1188 |
+
"logps/rejected": -441.8768005371094,
|
1189 |
+
"loss": 0.6162,
|
1190 |
+
"rewards/accuracies": 0.73333340883255,
|
1191 |
+
"rewards/chosen": -135.1923828125,
|
1192 |
+
"rewards/margins": 69.29673767089844,
|
1193 |
+
"rewards/rejected": -204.4891357421875,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.6200941915227629,
|
1198 |
+
"grad_norm": 26.357276507505432,
|
1199 |
+
"learning_rate": 1.8960819430126334e-07,
|
1200 |
+
"logits/chosen": 5692.7373046875,
|
1201 |
+
"logits/rejected": 4988.34423828125,
|
1202 |
+
"logps/chosen": -352.75152587890625,
|
1203 |
+
"logps/rejected": -436.21380615234375,
|
1204 |
+
"loss": 0.606,
|
1205 |
+
"rewards/accuracies": 0.800000011920929,
|
1206 |
+
"rewards/chosen": -154.62054443359375,
|
1207 |
+
"rewards/margins": 92.99554443359375,
|
1208 |
+
"rewards/rejected": -247.61605834960938,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.6279434850863422,
|
1213 |
+
"grad_norm": 26.128991277323944,
|
1214 |
+
"learning_rate": 1.8298130031671972e-07,
|
1215 |
+
"logits/chosen": 5666.7470703125,
|
1216 |
+
"logits/rejected": 4928.1630859375,
|
1217 |
+
"logps/chosen": -374.0252380371094,
|
1218 |
+
"logps/rejected": -446.89398193359375,
|
1219 |
+
"loss": 0.6227,
|
1220 |
+
"rewards/accuracies": 0.7333333492279053,
|
1221 |
+
"rewards/chosen": -157.30239868164062,
|
1222 |
+
"rewards/margins": 76.89336395263672,
|
1223 |
+
"rewards/rejected": -234.1957550048828,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6357927786499215,
|
1228 |
+
"grad_norm": 21.20668683192694,
|
1229 |
+
"learning_rate": 1.7640476790784075e-07,
|
1230 |
+
"logits/chosen": 5246.98876953125,
|
1231 |
+
"logits/rejected": 4623.890625,
|
1232 |
+
"logps/chosen": -351.83685302734375,
|
1233 |
+
"logps/rejected": -468.95904541015625,
|
1234 |
+
"loss": 0.6118,
|
1235 |
+
"rewards/accuracies": 0.7583333253860474,
|
1236 |
+
"rewards/chosen": -149.3814239501953,
|
1237 |
+
"rewards/margins": 98.28030395507812,
|
1238 |
+
"rewards/rejected": -247.6617431640625,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.6436420722135008,
|
1243 |
+
"grad_norm": 20.646225897051636,
|
1244 |
+
"learning_rate": 1.6988353904658492e-07,
|
1245 |
+
"logits/chosen": 5737.23974609375,
|
1246 |
+
"logits/rejected": 4359.0126953125,
|
1247 |
+
"logps/chosen": -371.08319091796875,
|
1248 |
+
"logps/rejected": -399.9681396484375,
|
1249 |
+
"loss": 0.6117,
|
1250 |
+
"rewards/accuracies": 0.7666666507720947,
|
1251 |
+
"rewards/chosen": -149.86865234375,
|
1252 |
+
"rewards/margins": 81.41114807128906,
|
1253 |
+
"rewards/rejected": -231.27981567382812,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.6514913657770801,
|
1258 |
+
"grad_norm": 39.77030169382563,
|
1259 |
+
"learning_rate": 1.634225141467513e-07,
|
1260 |
+
"logits/chosen": 5644.4755859375,
|
1261 |
+
"logits/rejected": 4988.80859375,
|
1262 |
+
"logps/chosen": -366.618408203125,
|
1263 |
+
"logps/rejected": -447.57489013671875,
|
1264 |
+
"loss": 0.6127,
|
1265 |
+
"rewards/accuracies": 0.7749999761581421,
|
1266 |
+
"rewards/chosen": -162.43235778808594,
|
1267 |
+
"rewards/margins": 92.68769836425781,
|
1268 |
+
"rewards/rejected": -255.1200408935547,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6593406593406593,
|
1273 |
+
"grad_norm": 13.895052837155353,
|
1274 |
+
"learning_rate": 1.570265483815364e-07,
|
1275 |
+
"logits/chosen": 6220.3994140625,
|
1276 |
+
"logits/rejected": 5031.82080078125,
|
1277 |
+
"logps/chosen": -372.7491760253906,
|
1278 |
+
"logps/rejected": -434.67779541015625,
|
1279 |
+
"loss": 0.6189,
|
1280 |
+
"rewards/accuracies": 0.7083333730697632,
|
1281 |
+
"rewards/chosen": -145.41937255859375,
|
1282 |
+
"rewards/margins": 76.46521759033203,
|
1283 |
+
"rewards/rejected": -221.8845977783203,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.6671899529042387,
|
1288 |
+
"grad_norm": 12.774810316086143,
|
1289 |
+
"learning_rate": 1.5070044803508691e-07,
|
1290 |
+
"logits/chosen": 5741.9931640625,
|
1291 |
+
"logits/rejected": 5091.0048828125,
|
1292 |
+
"logps/chosen": -347.2725524902344,
|
1293 |
+
"logps/rejected": -424.1080017089844,
|
1294 |
+
"loss": 0.5974,
|
1295 |
+
"rewards/accuracies": 0.7750000357627869,
|
1296 |
+
"rewards/chosen": -131.7950897216797,
|
1297 |
+
"rewards/margins": 91.85758209228516,
|
1298 |
+
"rewards/rejected": -223.6526641845703,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.6750392464678179,
|
1303 |
+
"grad_norm": 17.871490937493935,
|
1304 |
+
"learning_rate": 1.444489668907914e-07,
|
1305 |
+
"logits/chosen": 6167.5400390625,
|
1306 |
+
"logits/rejected": 5200.32568359375,
|
1307 |
+
"logps/chosen": -374.5239562988281,
|
1308 |
+
"logps/rejected": -405.5271301269531,
|
1309 |
+
"loss": 0.6325,
|
1310 |
+
"rewards/accuracies": 0.7250000238418579,
|
1311 |
+
"rewards/chosen": -126.7532958984375,
|
1312 |
+
"rewards/margins": 76.09200286865234,
|
1313 |
+
"rewards/rejected": -202.84530639648438,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6828885400313972,
|
1318 |
+
"grad_norm": 17.06846349127134,
|
1319 |
+
"learning_rate": 1.3827680265902232e-07,
|
1320 |
+
"logits/chosen": 6157.00634765625,
|
1321 |
+
"logits/rejected": 5048.666015625,
|
1322 |
+
"logps/chosen": -344.4704895019531,
|
1323 |
+
"logps/rejected": -391.15289306640625,
|
1324 |
+
"loss": 0.6177,
|
1325 |
+
"rewards/accuracies": 0.7583333849906921,
|
1326 |
+
"rewards/chosen": -114.37376403808594,
|
1327 |
+
"rewards/margins": 76.09016418457031,
|
1328 |
+
"rewards/rejected": -190.4639434814453,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6907378335949764,
|
1333 |
+
"grad_norm": 15.528467832759812,
|
1334 |
+
"learning_rate": 1.3218859344701632e-07,
|
1335 |
+
"logits/chosen": 5415.63671875,
|
1336 |
+
"logits/rejected": 5133.5498046875,
|
1337 |
+
"logps/chosen": -312.1150817871094,
|
1338 |
+
"logps/rejected": -407.8897705078125,
|
1339 |
+
"loss": 0.6164,
|
1340 |
+
"rewards/accuracies": 0.7833333611488342,
|
1341 |
+
"rewards/chosen": -101.6041259765625,
|
1342 |
+
"rewards/margins": 74.69647216796875,
|
1343 |
+
"rewards/rejected": -176.3006134033203,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6985871271585558,
|
1348 |
+
"grad_norm": 17.183055961017374,
|
1349 |
+
"learning_rate": 1.2618891427354172e-07,
|
1350 |
+
"logits/chosen": 6400.65478515625,
|
1351 |
+
"logits/rejected": 5158.58837890625,
|
1352 |
+
"logps/chosen": -360.47662353515625,
|
1353 |
+
"logps/rejected": -399.84051513671875,
|
1354 |
+
"loss": 0.6248,
|
1355 |
+
"rewards/accuracies": 0.800000011920929,
|
1356 |
+
"rewards/chosen": -102.88056945800781,
|
1357 |
+
"rewards/margins": 85.1794204711914,
|
1358 |
+
"rewards/rejected": -188.0599822998047,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.706436420722135,
|
1363 |
+
"grad_norm": 14.954999382868223,
|
1364 |
+
"learning_rate": 1.202822736309758e-07,
|
1365 |
+
"logits/chosen": 5437.9140625,
|
1366 |
+
"logits/rejected": 4952.78515625,
|
1367 |
+
"logps/chosen": -315.7103576660156,
|
1368 |
+
"logps/rejected": -405.45086669921875,
|
1369 |
+
"loss": 0.6149,
|
1370 |
+
"rewards/accuracies": 0.75,
|
1371 |
+
"rewards/chosen": -111.3611831665039,
|
1372 |
+
"rewards/margins": 83.65962982177734,
|
1373 |
+
"rewards/rejected": -195.02081298828125,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7142857142857143,
|
1378 |
+
"grad_norm": 17.482836351512447,
|
1379 |
+
"learning_rate": 1.1447311009737299e-07,
|
1380 |
+
"logits/chosen": 5352.5107421875,
|
1381 |
+
"logits/rejected": 5015.8212890625,
|
1382 |
+
"logps/chosen": -335.0443420410156,
|
1383 |
+
"logps/rejected": -422.0838317871094,
|
1384 |
+
"loss": 0.6238,
|
1385 |
+
"rewards/accuracies": 0.7916666269302368,
|
1386 |
+
"rewards/chosen": -126.8180160522461,
|
1387 |
+
"rewards/margins": 87.3373031616211,
|
1388 |
+
"rewards/rejected": -214.1553497314453,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.7221350078492935,
|
1393 |
+
"grad_norm": 14.726061760391564,
|
1394 |
+
"learning_rate": 1.0876578900107053e-07,
|
1395 |
+
"logits/chosen": 5908.712890625,
|
1396 |
+
"logits/rejected": 4864.37109375,
|
1397 |
+
"logps/chosen": -364.682861328125,
|
1398 |
+
"logps/rejected": -407.4881591796875,
|
1399 |
+
"loss": 0.6111,
|
1400 |
+
"rewards/accuracies": 0.8333333134651184,
|
1401 |
+
"rewards/chosen": -132.26129150390625,
|
1402 |
+
"rewards/margins": 77.08457946777344,
|
1403 |
+
"rewards/rejected": -209.34585571289062,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.7299843014128728,
|
1408 |
+
"grad_norm": 12.17491356029005,
|
1409 |
+
"learning_rate": 1.0316459914033793e-07,
|
1410 |
+
"logits/chosen": 5847.6396484375,
|
1411 |
+
"logits/rejected": 4304.47998046875,
|
1412 |
+
"logps/chosen": -374.629638671875,
|
1413 |
+
"logps/rejected": -411.969482421875,
|
1414 |
+
"loss": 0.6084,
|
1415 |
+
"rewards/accuracies": 0.783333420753479,
|
1416 |
+
"rewards/chosen": -138.6407012939453,
|
1417 |
+
"rewards/margins": 87.40455627441406,
|
1418 |
+
"rewards/rejected": -226.04525756835938,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.7378335949764521,
|
1423 |
+
"grad_norm": 14.942393863065405,
|
1424 |
+
"learning_rate": 9.767374956053584e-08,
|
1425 |
+
"logits/chosen": 5655.4033203125,
|
1426 |
+
"logits/rejected": 4892.77978515625,
|
1427 |
+
"logps/chosen": -362.05084228515625,
|
1428 |
+
"logps/rejected": -447.89691162109375,
|
1429 |
+
"loss": 0.616,
|
1430 |
+
"rewards/accuracies": 0.7500000596046448,
|
1431 |
+
"rewards/chosen": -143.75718688964844,
|
1432 |
+
"rewards/margins": 99.15988159179688,
|
1433 |
+
"rewards/rejected": -242.91708374023438,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7456828885400314,
|
1438 |
+
"grad_norm": 15.68275244303951,
|
1439 |
+
"learning_rate": 9.229736639120561e-08,
|
1440 |
+
"logits/chosen": 5820.70068359375,
|
1441 |
+
"logits/rejected": 5320.892578125,
|
1442 |
+
"logps/chosen": -365.70635986328125,
|
1443 |
+
"logps/rejected": -428.5652770996094,
|
1444 |
+
"loss": 0.631,
|
1445 |
+
"rewards/accuracies": 0.7250000238418579,
|
1446 |
+
"rewards/chosen": -147.90518188476562,
|
1447 |
+
"rewards/margins": 66.50559997558594,
|
1448 |
+
"rewards/rejected": -214.4107666015625,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.7535321821036107,
|
1453 |
+
"grad_norm": 19.23996720411505,
|
1454 |
+
"learning_rate": 8.70394897454659e-08,
|
1455 |
+
"logits/chosen": 5713.681640625,
|
1456 |
+
"logits/rejected": 5020.9267578125,
|
1457 |
+
"logps/chosen": -342.4471130371094,
|
1458 |
+
"logps/rejected": -417.79901123046875,
|
1459 |
+
"loss": 0.6123,
|
1460 |
+
"rewards/accuracies": 0.8333333730697632,
|
1461 |
+
"rewards/chosen": -124.01869201660156,
|
1462 |
+
"rewards/margins": 91.303955078125,
|
1463 |
+
"rewards/rejected": -215.32266235351562,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7613814756671899,
|
1468 |
+
"grad_norm": 22.33397911127439,
|
1469 |
+
"learning_rate": 8.19040706840472e-08,
|
1470 |
+
"logits/chosen": 5806.43359375,
|
1471 |
+
"logits/rejected": 4807.3515625,
|
1472 |
+
"logps/chosen": -376.2249755859375,
|
1473 |
+
"logps/rejected": -434.6560974121094,
|
1474 |
+
"loss": 0.6119,
|
1475 |
+
"rewards/accuracies": 0.7583333253860474,
|
1476 |
+
"rewards/chosen": -136.00497436523438,
|
1477 |
+
"rewards/margins": 91.96058654785156,
|
1478 |
+
"rewards/rejected": -227.965576171875,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7692307692307693,
|
1483 |
+
"grad_norm": 13.761008157112903,
|
1484 |
+
"learning_rate": 7.689496824624525e-08,
|
1485 |
+
"logits/chosen": 5534.2548828125,
|
1486 |
+
"logits/rejected": 4398.90087890625,
|
1487 |
+
"logps/chosen": -362.1374816894531,
|
1488 |
+
"logps/rejected": -422.9102478027344,
|
1489 |
+
"loss": 0.6029,
|
1490 |
+
"rewards/accuracies": 0.8083332777023315,
|
1491 |
+
"rewards/chosen": -133.32089233398438,
|
1492 |
+
"rewards/margins": 99.09576416015625,
|
1493 |
+
"rewards/rejected": -232.4166717529297,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.7770800627943485,
|
1498 |
+
"grad_norm": 18.096681200370565,
|
1499 |
+
"learning_rate": 7.201594655002458e-08,
|
1500 |
+
"logits/chosen": 5845.0439453125,
|
1501 |
+
"logits/rejected": 4824.6376953125,
|
1502 |
+
"logps/chosen": -375.0849914550781,
|
1503 |
+
"logps/rejected": -435.990478515625,
|
1504 |
+
"loss": 0.599,
|
1505 |
+
"rewards/accuracies": 0.783333420753479,
|
1506 |
+
"rewards/chosen": -149.19004821777344,
|
1507 |
+
"rewards/margins": 92.73072814941406,
|
1508 |
+
"rewards/rejected": -241.92074584960938,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.7849293563579278,
|
1513 |
+
"grad_norm": 19.80400883141873,
|
1514 |
+
"learning_rate": 6.727067196345099e-08,
|
1515 |
+
"logits/chosen": 5522.568359375,
|
1516 |
+
"logits/rejected": 4610.0341796875,
|
1517 |
+
"logps/chosen": -366.5689392089844,
|
1518 |
+
"logps/rejected": -410.90081787109375,
|
1519 |
+
"loss": 0.6154,
|
1520 |
+
"rewards/accuracies": 0.7333333492279053,
|
1521 |
+
"rewards/chosen": -152.8131103515625,
|
1522 |
+
"rewards/margins": 77.74247741699219,
|
1523 |
+
"rewards/rejected": -230.55557250976562,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.792778649921507,
|
1528 |
+
"grad_norm": 19.909366846280882,
|
1529 |
+
"learning_rate": 6.26627103495786e-08,
|
1530 |
+
"logits/chosen": 5702.2314453125,
|
1531 |
+
"logits/rejected": 4692.59130859375,
|
1532 |
+
"logps/chosen": -357.6479187011719,
|
1533 |
+
"logps/rejected": -417.7315368652344,
|
1534 |
+
"loss": 0.6253,
|
1535 |
+
"rewards/accuracies": 0.7083333730697632,
|
1536 |
+
"rewards/chosen": -142.938720703125,
|
1537 |
+
"rewards/margins": 83.35922241210938,
|
1538 |
+
"rewards/rejected": -226.2979736328125,
|
1539 |
+
"step": 1010
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.8006279434850864,
|
1543 |
+
"grad_norm": 13.222506396766855,
|
1544 |
+
"learning_rate": 5.8195524386862374e-08,
|
1545 |
+
"logits/chosen": 5807.0205078125,
|
1546 |
+
"logits/rejected": 5114.4541015625,
|
1547 |
+
"logps/chosen": -379.9997863769531,
|
1548 |
+
"logps/rejected": -456.28125,
|
1549 |
+
"loss": 0.6175,
|
1550 |
+
"rewards/accuracies": 0.8166667222976685,
|
1551 |
+
"rewards/chosen": -131.8211669921875,
|
1552 |
+
"rewards/margins": 98.37938690185547,
|
1553 |
+
"rewards/rejected": -230.20053100585938,
|
1554 |
+
"step": 1020
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.8084772370486656,
|
1558 |
+
"grad_norm": 14.840716751556135,
|
1559 |
+
"learning_rate": 5.38724709671092e-08,
|
1560 |
+
"logits/chosen": 6213.39697265625,
|
1561 |
+
"logits/rejected": 5793.4111328125,
|
1562 |
+
"logps/chosen": -374.4881286621094,
|
1563 |
+
"logps/rejected": -466.87982177734375,
|
1564 |
+
"loss": 0.6064,
|
1565 |
+
"rewards/accuracies": 0.7916666865348816,
|
1566 |
+
"rewards/chosen": -143.019775390625,
|
1567 |
+
"rewards/margins": 90.74076843261719,
|
1568 |
+
"rewards/rejected": -233.7605438232422,
|
1569 |
+
"step": 1030
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8163265306122449,
|
1573 |
+
"grad_norm": 15.902716058683295,
|
1574 |
+
"learning_rate": 4.969679867292276e-08,
|
1575 |
+
"logits/chosen": 5481.22265625,
|
1576 |
+
"logits/rejected": 4915.169921875,
|
1577 |
+
"logps/chosen": -365.6921691894531,
|
1578 |
+
"logps/rejected": -450.8426818847656,
|
1579 |
+
"loss": 0.6114,
|
1580 |
+
"rewards/accuracies": 0.7583333849906921,
|
1581 |
+
"rewards/chosen": -145.59046936035156,
|
1582 |
+
"rewards/margins": 96.06826782226562,
|
1583 |
+
"rewards/rejected": -241.6587371826172,
|
1584 |
+
"step": 1040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8241758241758241,
|
1588 |
+
"grad_norm": 15.329902609184328,
|
1589 |
+
"learning_rate": 4.5671645336537416e-08,
|
1590 |
+
"logits/chosen": 5554.18017578125,
|
1591 |
+
"logits/rejected": 4997.1005859375,
|
1592 |
+
"logps/chosen": -381.65789794921875,
|
1593 |
+
"logps/rejected": -449.450927734375,
|
1594 |
+
"loss": 0.6103,
|
1595 |
+
"rewards/accuracies": 0.7916666865348816,
|
1596 |
+
"rewards/chosen": -144.17726135253906,
|
1597 |
+
"rewards/margins": 89.47932434082031,
|
1598 |
+
"rewards/rejected": -233.6565399169922,
|
1599 |
+
"step": 1050
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.8320251177394035,
|
1603 |
+
"grad_norm": 55.197735270402006,
|
1604 |
+
"learning_rate": 4.180003568187776e-08,
|
1605 |
+
"logits/chosen": 6873.0361328125,
|
1606 |
+
"logits/rejected": 5345.8271484375,
|
1607 |
+
"logps/chosen": -410.3626403808594,
|
1608 |
+
"logps/rejected": -439.2491149902344,
|
1609 |
+
"loss": 0.6283,
|
1610 |
+
"rewards/accuracies": 0.7083333730697632,
|
1611 |
+
"rewards/chosen": -149.37527465820312,
|
1612 |
+
"rewards/margins": 69.83467102050781,
|
1613 |
+
"rewards/rejected": -219.20993041992188,
|
1614 |
+
"step": 1060
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.8398744113029827,
|
1618 |
+
"grad_norm": 19.762608641409,
|
1619 |
+
"learning_rate": 3.8084879051612144e-08,
|
1620 |
+
"logits/chosen": 5707.0205078125,
|
1621 |
+
"logits/rejected": 5145.00927734375,
|
1622 |
+
"logps/chosen": -366.8685302734375,
|
1623 |
+
"logps/rejected": -423.092529296875,
|
1624 |
+
"loss": 0.6147,
|
1625 |
+
"rewards/accuracies": 0.7583333849906921,
|
1626 |
+
"rewards/chosen": -141.62551879882812,
|
1627 |
+
"rewards/margins": 88.30266571044922,
|
1628 |
+
"rewards/rejected": -229.9281768798828,
|
1629 |
+
"step": 1070
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.847723704866562,
|
1633 |
+
"grad_norm": 16.196550037488134,
|
1634 |
+
"learning_rate": 3.452896722091128e-08,
|
1635 |
+
"logits/chosen": 6264.1298828125,
|
1636 |
+
"logits/rejected": 4766.61083984375,
|
1637 |
+
"logps/chosen": -405.56341552734375,
|
1638 |
+
"logps/rejected": -432.5325622558594,
|
1639 |
+
"loss": 0.6033,
|
1640 |
+
"rewards/accuracies": 0.800000011920929,
|
1641 |
+
"rewards/chosen": -138.9940948486328,
|
1642 |
+
"rewards/margins": 92.55856323242188,
|
1643 |
+
"rewards/rejected": -231.55264282226562,
|
1644 |
+
"step": 1080
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.8555729984301413,
|
1648 |
+
"grad_norm": 20.291014842445787,
|
1649 |
+
"learning_rate": 3.11349722995527e-08,
|
1650 |
+
"logits/chosen": 6290.5830078125,
|
1651 |
+
"logits/rejected": 4671.265625,
|
1652 |
+
"logps/chosen": -373.1634826660156,
|
1653 |
+
"logps/rejected": -431.679931640625,
|
1654 |
+
"loss": 0.6037,
|
1655 |
+
"rewards/accuracies": 0.7083333730697632,
|
1656 |
+
"rewards/chosen": -145.68887329101562,
|
1657 |
+
"rewards/margins": 73.10652160644531,
|
1658 |
+
"rewards/rejected": -218.79537963867188,
|
1659 |
+
"step": 1090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.8634222919937206,
|
1663 |
+
"grad_norm": 17.99288812895582,
|
1664 |
+
"learning_rate": 2.7905444723949762e-08,
|
1665 |
+
"logits/chosen": 6118.28271484375,
|
1666 |
+
"logits/rejected": 5002.5498046875,
|
1667 |
+
"logps/chosen": -382.5477294921875,
|
1668 |
+
"logps/rejected": -433.43798828125,
|
1669 |
+
"loss": 0.6151,
|
1670 |
+
"rewards/accuracies": 0.7750000953674316,
|
1671 |
+
"rewards/chosen": -144.01138305664062,
|
1672 |
+
"rewards/margins": 99.92918395996094,
|
1673 |
+
"rewards/rejected": -243.9405517578125,
|
1674 |
+
"step": 1100
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8712715855572999,
|
1678 |
+
"grad_norm": 18.552548907991827,
|
1679 |
+
"learning_rate": 2.484281134061142e-08,
|
1680 |
+
"logits/chosen": 6458.51123046875,
|
1681 |
+
"logits/rejected": 5143.70263671875,
|
1682 |
+
"logps/chosen": -413.1473693847656,
|
1683 |
+
"logps/rejected": -460.0634765625,
|
1684 |
+
"loss": 0.6059,
|
1685 |
+
"rewards/accuracies": 0.7916666865348816,
|
1686 |
+
"rewards/chosen": -148.53378295898438,
|
1687 |
+
"rewards/margins": 89.26164245605469,
|
1688 |
+
"rewards/rejected": -237.79541015625,
|
1689 |
+
"step": 1110
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8791208791208791,
|
1693 |
+
"grad_norm": 39.56227188436796,
|
1694 |
+
"learning_rate": 2.194937358247506e-08,
|
1695 |
+
"logits/chosen": 6335.6669921875,
|
1696 |
+
"logits/rejected": 5074.86474609375,
|
1697 |
+
"logps/chosen": -396.36737060546875,
|
1698 |
+
"logps/rejected": -461.27423095703125,
|
1699 |
+
"loss": 0.608,
|
1700 |
+
"rewards/accuracies": 0.7749999761581421,
|
1701 |
+
"rewards/chosen": -151.22695922851562,
|
1702 |
+
"rewards/margins": 93.27647399902344,
|
1703 |
+
"rewards/rejected": -244.50341796875,
|
1704 |
+
"step": 1120
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.8869701726844584,
|
1708 |
+
"grad_norm": 18.148758631996266,
|
1709 |
+
"learning_rate": 1.9227305739481612e-08,
|
1710 |
+
"logits/chosen": 5765.23486328125,
|
1711 |
+
"logits/rejected": 4463.29541015625,
|
1712 |
+
"logps/chosen": -364.4913330078125,
|
1713 |
+
"logps/rejected": -408.61187744140625,
|
1714 |
+
"loss": 0.6017,
|
1715 |
+
"rewards/accuracies": 0.7666666507720947,
|
1716 |
+
"rewards/chosen": -129.7092742919922,
|
1717 |
+
"rewards/margins": 98.6770248413086,
|
1718 |
+
"rewards/rejected": -228.3863067626953,
|
1719 |
+
"step": 1130
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.8948194662480377,
|
1723 |
+
"grad_norm": 16.994877433404973,
|
1724 |
+
"learning_rate": 1.6678653324693787e-08,
|
1725 |
+
"logits/chosen": 6387.3359375,
|
1726 |
+
"logits/rejected": 5097.41015625,
|
1727 |
+
"logps/chosen": -400.7387390136719,
|
1728 |
+
"logps/rejected": -451.8038024902344,
|
1729 |
+
"loss": 0.5946,
|
1730 |
+
"rewards/accuracies": 0.7416666746139526,
|
1731 |
+
"rewards/chosen": -143.11801147460938,
|
1732 |
+
"rewards/margins": 87.87274932861328,
|
1733 |
+
"rewards/rejected": -230.99075317382812,
|
1734 |
+
"step": 1140
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.902668759811617,
|
1738 |
+
"grad_norm": 11.193775448088072,
|
1739 |
+
"learning_rate": 1.4305331537183384e-08,
|
1740 |
+
"logits/chosen": 5634.30419921875,
|
1741 |
+
"logits/rejected": 5102.05615234375,
|
1742 |
+
"logps/chosen": -367.156005859375,
|
1743 |
+
"logps/rejected": -442.4237365722656,
|
1744 |
+
"loss": 0.6015,
|
1745 |
+
"rewards/accuracies": 0.7166666984558105,
|
1746 |
+
"rewards/chosen": -140.172607421875,
|
1747 |
+
"rewards/margins": 82.76316833496094,
|
1748 |
+
"rewards/rejected": -222.935791015625,
|
1749 |
+
"step": 1150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.9105180533751962,
|
1753 |
+
"grad_norm": 18.50142880229726,
|
1754 |
+
"learning_rate": 1.2109123822844653e-08,
|
1755 |
+
"logits/chosen": 5791.82861328125,
|
1756 |
+
"logits/rejected": 4512.34228515625,
|
1757 |
+
"logps/chosen": -374.96600341796875,
|
1758 |
+
"logps/rejected": -425.4412536621094,
|
1759 |
+
"loss": 0.6118,
|
1760 |
+
"rewards/accuracies": 0.7833333611488342,
|
1761 |
+
"rewards/chosen": -146.40921020507812,
|
1762 |
+
"rewards/margins": 83.09394836425781,
|
1763 |
+
"rewards/rejected": -229.50314331054688,
|
1764 |
+
"step": 1160
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.9183673469387755,
|
1768 |
+
"grad_norm": 16.45322143829113,
|
1769 |
+
"learning_rate": 1.0091680534213387e-08,
|
1770 |
+
"logits/chosen": 6355.1123046875,
|
1771 |
+
"logits/rejected": 6031.12744140625,
|
1772 |
+
"logps/chosen": -378.3938903808594,
|
1773 |
+
"logps/rejected": -480.53863525390625,
|
1774 |
+
"loss": 0.6105,
|
1775 |
+
"rewards/accuracies": 0.7250000238418579,
|
1776 |
+
"rewards/chosen": -135.44552612304688,
|
1777 |
+
"rewards/margins": 98.34616088867188,
|
1778 |
+
"rewards/rejected": -233.7917022705078,
|
1779 |
+
"step": 1170
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.9262166405023547,
|
1783 |
+
"grad_norm": 23.32993982299152,
|
1784 |
+
"learning_rate": 8.254517690300944e-09,
|
1785 |
+
"logits/chosen": 5549.52392578125,
|
1786 |
+
"logits/rejected": 4957.7138671875,
|
1787 |
+
"logps/chosen": -378.49566650390625,
|
1788 |
+
"logps/rejected": -448.3548889160156,
|
1789 |
+
"loss": 0.6038,
|
1790 |
+
"rewards/accuracies": 0.7416666746139526,
|
1791 |
+
"rewards/chosen": -138.54971313476562,
|
1792 |
+
"rewards/margins": 92.9834213256836,
|
1793 |
+
"rewards/rejected": -231.5331268310547,
|
1794 |
+
"step": 1180
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.9340659340659341,
|
1798 |
+
"grad_norm": 11.697466694155857,
|
1799 |
+
"learning_rate": 6.599015837372907e-09,
|
1800 |
+
"logits/chosen": 6053.71044921875,
|
1801 |
+
"logits/rejected": 5201.91845703125,
|
1802 |
+
"logps/chosen": -410.1524963378906,
|
1803 |
+
"logps/rejected": -463.343994140625,
|
1804 |
+
"loss": 0.6132,
|
1805 |
+
"rewards/accuracies": 0.7166666388511658,
|
1806 |
+
"rewards/chosen": -161.26699829101562,
|
1807 |
+
"rewards/margins": 84.92450714111328,
|
1808 |
+
"rewards/rejected": -246.1914825439453,
|
1809 |
+
"step": 1190
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.9419152276295133,
|
1813 |
+
"grad_norm": 29.00561816867174,
|
1814 |
+
"learning_rate": 5.126419011529992e-09,
|
1815 |
+
"logits/chosen": 6306.44140625,
|
1816 |
+
"logits/rejected": 5252.5625,
|
1817 |
+
"logps/chosen": -392.0524597167969,
|
1818 |
+
"logps/rejected": -466.8185119628906,
|
1819 |
+
"loss": 0.6043,
|
1820 |
+
"rewards/accuracies": 0.8333333134651184,
|
1821 |
+
"rewards/chosen": -136.3907470703125,
|
1822 |
+
"rewards/margins": 111.76222229003906,
|
1823 |
+
"rewards/rejected": -248.15292358398438,
|
1824 |
+
"step": 1200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.9497645211930926,
|
1828 |
+
"grad_norm": 24.03652143626847,
|
1829 |
+
"learning_rate": 3.837833803870177e-09,
|
1830 |
+
"logits/chosen": 5867.791015625,
|
1831 |
+
"logits/rejected": 5074.435546875,
|
1832 |
+
"logps/chosen": -392.6157531738281,
|
1833 |
+
"logps/rejected": -466.23956298828125,
|
1834 |
+
"loss": 0.6164,
|
1835 |
+
"rewards/accuracies": 0.783333420753479,
|
1836 |
+
"rewards/chosen": -152.4302520751953,
|
1837 |
+
"rewards/margins": 95.60807037353516,
|
1838 |
+
"rewards/rejected": -248.03829956054688,
|
1839 |
+
"step": 1210
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.957613814756672,
|
1843 |
+
"grad_norm": 23.781485972909927,
|
1844 |
+
"learning_rate": 2.734228528934679e-09,
|
1845 |
+
"logits/chosen": 7340.81494140625,
|
1846 |
+
"logits/rejected": 5272.85400390625,
|
1847 |
+
"logps/chosen": -449.55072021484375,
|
1848 |
+
"logps/rejected": -496.0115661621094,
|
1849 |
+
"loss": 0.6098,
|
1850 |
+
"rewards/accuracies": 0.7083333730697632,
|
1851 |
+
"rewards/chosen": -152.78236389160156,
|
1852 |
+
"rewards/margins": 98.0320053100586,
|
1853 |
+
"rewards/rejected": -250.8143768310547,
|
1854 |
+
"step": 1220
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.9654631083202512,
|
1858 |
+
"grad_norm": 25.628197989466248,
|
1859 |
+
"learning_rate": 1.8164324970625645e-09,
|
1860 |
+
"logits/chosen": 6506.375,
|
1861 |
+
"logits/rejected": 5016.78759765625,
|
1862 |
+
"logps/chosen": -400.7377624511719,
|
1863 |
+
"logps/rejected": -448.590576171875,
|
1864 |
+
"loss": 0.624,
|
1865 |
+
"rewards/accuracies": 0.75,
|
1866 |
+
"rewards/chosen": -140.1560821533203,
|
1867 |
+
"rewards/margins": 95.43777465820312,
|
1868 |
+
"rewards/rejected": -235.59384155273438,
|
1869 |
+
"step": 1230
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.9733124018838305,
|
1873 |
+
"grad_norm": 19.957302011366814,
|
1874 |
+
"learning_rate": 1.0851353912008642e-09,
|
1875 |
+
"logits/chosen": 5557.27685546875,
|
1876 |
+
"logits/rejected": 5068.2919921875,
|
1877 |
+
"logps/chosen": -379.62493896484375,
|
1878 |
+
"logps/rejected": -472.33477783203125,
|
1879 |
+
"loss": 0.6141,
|
1880 |
+
"rewards/accuracies": 0.7333332896232605,
|
1881 |
+
"rewards/chosen": -148.0125732421875,
|
1882 |
+
"rewards/margins": 89.1643295288086,
|
1883 |
+
"rewards/rejected": -237.17691040039062,
|
1884 |
+
"step": 1240
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.9811616954474097,
|
1888 |
+
"grad_norm": 15.727811449834665,
|
1889 |
+
"learning_rate": 5.408867486384471e-10,
|
1890 |
+
"logits/chosen": 5699.9697265625,
|
1891 |
+
"logits/rejected": 4726.44580078125,
|
1892 |
+
"logps/chosen": -367.1297912597656,
|
1893 |
+
"logps/rejected": -415.16668701171875,
|
1894 |
+
"loss": 0.6068,
|
1895 |
+
"rewards/accuracies": 0.7833332419395447,
|
1896 |
+
"rewards/chosen": -136.82162475585938,
|
1897 |
+
"rewards/margins": 88.91475677490234,
|
1898 |
+
"rewards/rejected": -225.7363739013672,
|
1899 |
+
"step": 1250
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.989010989010989,
|
1903 |
+
"grad_norm": 18.48673738798219,
|
1904 |
+
"learning_rate": 1.840955480532924e-10,
|
1905 |
+
"logits/chosen": 5415.2001953125,
|
1906 |
+
"logits/rejected": 5022.5712890625,
|
1907 |
+
"logps/chosen": -370.6057434082031,
|
1908 |
+
"logps/rejected": -442.42633056640625,
|
1909 |
+
"loss": 0.6035,
|
1910 |
+
"rewards/accuracies": 0.7666666507720947,
|
1911 |
+
"rewards/chosen": -138.44517517089844,
|
1912 |
+
"rewards/margins": 87.65608215332031,
|
1913 |
+
"rewards/rejected": -226.10122680664062,
|
1914 |
+
"step": 1260
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.9968602825745683,
|
1918 |
+
"grad_norm": 20.059405514745603,
|
1919 |
+
"learning_rate": 1.502990218302247e-11,
|
1920 |
+
"logits/chosen": 5661.7509765625,
|
1921 |
+
"logits/rejected": 4540.9052734375,
|
1922 |
+
"logps/chosen": -372.86297607421875,
|
1923 |
+
"logps/rejected": -427.48162841796875,
|
1924 |
+
"loss": 0.6166,
|
1925 |
+
"rewards/accuracies": 0.7749999761581421,
|
1926 |
+
"rewards/chosen": -148.38900756835938,
|
1927 |
+
"rewards/margins": 92.78841400146484,
|
1928 |
+
"rewards/rejected": -241.1774139404297,
|
1929 |
+
"step": 1270
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.0,
|
1933 |
+
"step": 1274,
|
1934 |
+
"total_flos": 0.0,
|
1935 |
+
"train_loss": 0.6278583559922558,
|
1936 |
+
"train_runtime": 14837.7437,
|
1937 |
+
"train_samples_per_second": 4.12,
|
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 |
+
}
|