TTTXXX01 commited on
Commit
11ebeee
1 Parent(s): ca72765

Model save

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: alignment-handbook/zephyr-7b-sft-full
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: DPO_shift2-Negative-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
+ # DPO_shift2-Negative-zephyr-7b-sft-full
17
+
18
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/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": 0.6310614222072919,
5
+ "train_runtime": 13007.3728,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 4.7,
8
+ "train_steps_per_second": 0.098
9
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.41.2",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
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:ac97530f9d1d6a8c84c27e185fca6106da7f546dfa8085f777991f987c5cde2a
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd75b671dde65602949ab6f1a8a56c952c23e56775e668b2661634d88342c39
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f39bffd82f2bbbdf26b1c4fac21fb6cff31e9bcf9a89c8c28f2c2d500fbfa4b
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
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.6310614222072919,
5
+ "train_runtime": 13007.3728,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 4.7,
8
+ "train_steps_per_second": 0.098
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1962 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1274,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0007849293563579278,
13
+ "grad_norm": 7.6070190011438665,
14
+ "learning_rate": 3.90625e-09,
15
+ "logits/chosen": 5881.4375,
16
+ "logits/rejected": 2834.66162109375,
17
+ "logps/chosen": -257.5969543457031,
18
+ "logps/rejected": -120.09489440917969,
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": 8.292103607244062,
29
+ "learning_rate": 3.9062499999999997e-08,
30
+ "logits/chosen": 4946.02587890625,
31
+ "logits/rejected": 4332.443359375,
32
+ "logps/chosen": -248.808837890625,
33
+ "logps/rejected": -214.24110412597656,
34
+ "loss": 0.6932,
35
+ "rewards/accuracies": 0.3888889253139496,
36
+ "rewards/chosen": 0.007352272514253855,
37
+ "rewards/margins": -0.04363558441400528,
38
+ "rewards/rejected": 0.0509878545999527,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.015698587127158554,
43
+ "grad_norm": 7.004971570853845,
44
+ "learning_rate": 7.812499999999999e-08,
45
+ "logits/chosen": 6023.1796875,
46
+ "logits/rejected": 4842.9091796875,
47
+ "logps/chosen": -266.2599792480469,
48
+ "logps/rejected": -232.38601684570312,
49
+ "loss": 0.6933,
50
+ "rewards/accuracies": 0.5,
51
+ "rewards/chosen": 0.05332508683204651,
52
+ "rewards/margins": -0.012739470228552818,
53
+ "rewards/rejected": 0.06606455147266388,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.023547880690737835,
58
+ "grad_norm": 6.884207614473328,
59
+ "learning_rate": 1.1718749999999999e-07,
60
+ "logits/chosen": 6032.62890625,
61
+ "logits/rejected": 5038.45556640625,
62
+ "logps/chosen": -310.3996887207031,
63
+ "logps/rejected": -262.9111328125,
64
+ "loss": 0.693,
65
+ "rewards/accuracies": 0.5750000476837158,
66
+ "rewards/chosen": 0.20968368649482727,
67
+ "rewards/margins": 0.08424334973096848,
68
+ "rewards/rejected": 0.1254403293132782,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.03139717425431711,
73
+ "grad_norm": 7.259392888061773,
74
+ "learning_rate": 1.5624999999999999e-07,
75
+ "logits/chosen": 5241.93896484375,
76
+ "logits/rejected": 4344.1708984375,
77
+ "logps/chosen": -263.4868469238281,
78
+ "logps/rejected": -224.7186737060547,
79
+ "loss": 0.6923,
80
+ "rewards/accuracies": 0.6000000238418579,
81
+ "rewards/chosen": 0.5333760976791382,
82
+ "rewards/margins": 0.18804652988910675,
83
+ "rewards/rejected": 0.3453296422958374,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.03924646781789639,
88
+ "grad_norm": 7.738968697847914,
89
+ "learning_rate": 1.9531249999999998e-07,
90
+ "logits/chosen": 6364.2314453125,
91
+ "logits/rejected": 4975.1728515625,
92
+ "logps/chosen": -324.3128967285156,
93
+ "logps/rejected": -257.80108642578125,
94
+ "loss": 0.6913,
95
+ "rewards/accuracies": 0.6916666626930237,
96
+ "rewards/chosen": 1.7967116832733154,
97
+ "rewards/margins": 1.0479546785354614,
98
+ "rewards/rejected": 0.748757004737854,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.04709576138147567,
103
+ "grad_norm": 7.908366760507787,
104
+ "learning_rate": 2.3437499999999998e-07,
105
+ "logits/chosen": 5382.3125,
106
+ "logits/rejected": 4503.8955078125,
107
+ "logps/chosen": -268.0205383300781,
108
+ "logps/rejected": -261.6384582519531,
109
+ "loss": 0.6894,
110
+ "rewards/accuracies": 0.6416667103767395,
111
+ "rewards/chosen": 1.9065296649932861,
112
+ "rewards/margins": 1.3541371822357178,
113
+ "rewards/rejected": 0.5523924827575684,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.054945054945054944,
118
+ "grad_norm": 6.1363185745056095,
119
+ "learning_rate": 2.734375e-07,
120
+ "logits/chosen": 5104.6328125,
121
+ "logits/rejected": 4838.6162109375,
122
+ "logps/chosen": -231.5017547607422,
123
+ "logps/rejected": -233.1387481689453,
124
+ "loss": 0.6876,
125
+ "rewards/accuracies": 0.6583333611488342,
126
+ "rewards/chosen": 1.7562404870986938,
127
+ "rewards/margins": 2.241947650909424,
128
+ "rewards/rejected": -0.48570698499679565,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.06279434850863422,
133
+ "grad_norm": 6.313648303908843,
134
+ "learning_rate": 3.1249999999999997e-07,
135
+ "logits/chosen": 5691.92822265625,
136
+ "logits/rejected": 5161.9208984375,
137
+ "logps/chosen": -256.8810119628906,
138
+ "logps/rejected": -246.78268432617188,
139
+ "loss": 0.6837,
140
+ "rewards/accuracies": 0.6333333253860474,
141
+ "rewards/chosen": -0.9025794863700867,
142
+ "rewards/margins": 3.5677428245544434,
143
+ "rewards/rejected": -4.470322608947754,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.0706436420722135,
148
+ "grad_norm": 7.17648924651081,
149
+ "learning_rate": 3.5156249999999997e-07,
150
+ "logits/chosen": 5875.908203125,
151
+ "logits/rejected": 5055.4775390625,
152
+ "logps/chosen": -287.22882080078125,
153
+ "logps/rejected": -253.146728515625,
154
+ "loss": 0.6781,
155
+ "rewards/accuracies": 0.7416667342185974,
156
+ "rewards/chosen": -2.037750720977783,
157
+ "rewards/margins": 7.642518043518066,
158
+ "rewards/rejected": -9.680269241333008,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.07849293563579278,
163
+ "grad_norm": 7.7941596557126624,
164
+ "learning_rate": 3.9062499999999997e-07,
165
+ "logits/chosen": 5771.35400390625,
166
+ "logits/rejected": 5554.82470703125,
167
+ "logps/chosen": -283.1836853027344,
168
+ "logps/rejected": -282.7068176269531,
169
+ "loss": 0.6766,
170
+ "rewards/accuracies": 0.6916667222976685,
171
+ "rewards/chosen": -4.9085798263549805,
172
+ "rewards/margins": 9.60995864868164,
173
+ "rewards/rejected": -14.518537521362305,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.08634222919937205,
178
+ "grad_norm": 9.345408351017173,
179
+ "learning_rate": 4.2968749999999996e-07,
180
+ "logits/chosen": 6213.28173828125,
181
+ "logits/rejected": 5103.55517578125,
182
+ "logps/chosen": -261.7968444824219,
183
+ "logps/rejected": -261.9189453125,
184
+ "loss": 0.6654,
185
+ "rewards/accuracies": 0.7083333730697632,
186
+ "rewards/chosen": -4.658997535705566,
187
+ "rewards/margins": 13.647018432617188,
188
+ "rewards/rejected": -18.306015014648438,
189
+ "step": 110
190
+ },
191
+ {
192
+ "epoch": 0.09419152276295134,
193
+ "grad_norm": 10.145203775900786,
194
+ "learning_rate": 4.6874999999999996e-07,
195
+ "logits/chosen": 6057.29052734375,
196
+ "logits/rejected": 5066.5625,
197
+ "logps/chosen": -305.77459716796875,
198
+ "logps/rejected": -314.111572265625,
199
+ "loss": 0.6665,
200
+ "rewards/accuracies": 0.7166666984558105,
201
+ "rewards/chosen": -26.187755584716797,
202
+ "rewards/margins": 18.321544647216797,
203
+ "rewards/rejected": -44.50930404663086,
204
+ "step": 120
205
+ },
206
+ {
207
+ "epoch": 0.10204081632653061,
208
+ "grad_norm": 7.094150089546659,
209
+ "learning_rate": 4.999962424962166e-07,
210
+ "logits/chosen": 6036.177734375,
211
+ "logits/rejected": 5572.85009765625,
212
+ "logps/chosen": -299.9012145996094,
213
+ "logps/rejected": -295.4285583496094,
214
+ "loss": 0.6674,
215
+ "rewards/accuracies": 0.658333420753479,
216
+ "rewards/chosen": -9.793970108032227,
217
+ "rewards/margins": 12.203898429870605,
218
+ "rewards/rejected": -21.997867584228516,
219
+ "step": 130
220
+ },
221
+ {
222
+ "epoch": 0.10989010989010989,
223
+ "grad_norm": 8.740739358429577,
224
+ "learning_rate": 4.998647417232375e-07,
225
+ "logits/chosen": 5906.3203125,
226
+ "logits/rejected": 5174.52783203125,
227
+ "logps/chosen": -266.81195068359375,
228
+ "logps/rejected": -270.7115173339844,
229
+ "loss": 0.6712,
230
+ "rewards/accuracies": 0.6416667103767395,
231
+ "rewards/chosen": -6.569715976715088,
232
+ "rewards/margins": 13.785995483398438,
233
+ "rewards/rejected": -20.355710983276367,
234
+ "step": 140
235
+ },
236
+ {
237
+ "epoch": 0.11773940345368916,
238
+ "grad_norm": 15.789592358858716,
239
+ "learning_rate": 4.995454786965036e-07,
240
+ "logits/chosen": 6020.12939453125,
241
+ "logits/rejected": 5010.9521484375,
242
+ "logps/chosen": -284.8111267089844,
243
+ "logps/rejected": -268.1068420410156,
244
+ "loss": 0.6656,
245
+ "rewards/accuracies": 0.6750000715255737,
246
+ "rewards/chosen": -6.939129829406738,
247
+ "rewards/margins": 19.278301239013672,
248
+ "rewards/rejected": -26.21742820739746,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 0.12558869701726844,
253
+ "grad_norm": 9.090539317617692,
254
+ "learning_rate": 4.990386933279972e-07,
255
+ "logits/chosen": 5993.25341796875,
256
+ "logits/rejected": 5322.8603515625,
257
+ "logps/chosen": -292.59307861328125,
258
+ "logps/rejected": -305.57769775390625,
259
+ "loss": 0.6599,
260
+ "rewards/accuracies": 0.7416666746139526,
261
+ "rewards/chosen": -19.02887535095215,
262
+ "rewards/margins": 20.415613174438477,
263
+ "rewards/rejected": -39.444488525390625,
264
+ "step": 160
265
+ },
266
+ {
267
+ "epoch": 0.13343799058084774,
268
+ "grad_norm": 13.372920007721838,
269
+ "learning_rate": 4.983447664444096e-07,
270
+ "logits/chosen": 6258.017578125,
271
+ "logits/rejected": 5565.6845703125,
272
+ "logps/chosen": -315.3527526855469,
273
+ "logps/rejected": -318.45050048828125,
274
+ "loss": 0.6544,
275
+ "rewards/accuracies": 0.6500000357627869,
276
+ "rewards/chosen": -25.55523681640625,
277
+ "rewards/margins": 23.88918113708496,
278
+ "rewards/rejected": -49.444419860839844,
279
+ "step": 170
280
+ },
281
+ {
282
+ "epoch": 0.141287284144427,
283
+ "grad_norm": 14.27741481958782,
284
+ "learning_rate": 4.97464219500968e-07,
285
+ "logits/chosen": 5531.6142578125,
286
+ "logits/rejected": 4802.4638671875,
287
+ "logps/chosen": -295.49737548828125,
288
+ "logps/rejected": -306.994384765625,
289
+ "loss": 0.6564,
290
+ "rewards/accuracies": 0.6499999761581421,
291
+ "rewards/chosen": -32.053043365478516,
292
+ "rewards/margins": 27.674352645874023,
293
+ "rewards/rejected": -59.72739791870117,
294
+ "step": 180
295
+ },
296
+ {
297
+ "epoch": 0.14913657770800628,
298
+ "grad_norm": 14.09329925384393,
299
+ "learning_rate": 4.963977141895843e-07,
300
+ "logits/chosen": 5590.63818359375,
301
+ "logits/rejected": 4784.70068359375,
302
+ "logps/chosen": -334.12109375,
303
+ "logps/rejected": -354.5445556640625,
304
+ "loss": 0.6353,
305
+ "rewards/accuracies": 0.7416667342185974,
306
+ "rewards/chosen": -46.83644485473633,
307
+ "rewards/margins": 46.24668502807617,
308
+ "rewards/rejected": -93.0831298828125,
309
+ "step": 190
310
+ },
311
+ {
312
+ "epoch": 0.15698587127158556,
313
+ "grad_norm": 11.55780859392514,
314
+ "learning_rate": 4.951460519416227e-07,
315
+ "logits/chosen": 5547.5302734375,
316
+ "logits/rejected": 5110.81005859375,
317
+ "logps/chosen": -287.798095703125,
318
+ "logps/rejected": -339.49029541015625,
319
+ "loss": 0.6461,
320
+ "rewards/accuracies": 0.7083333730697632,
321
+ "rewards/chosen": -36.548126220703125,
322
+ "rewards/margins": 39.468544006347656,
323
+ "rewards/rejected": -76.01667785644531,
324
+ "step": 200
325
+ },
326
+ {
327
+ "epoch": 0.16483516483516483,
328
+ "grad_norm": 21.82214651560815,
329
+ "learning_rate": 4.937101733256606e-07,
330
+ "logits/chosen": 5047.630859375,
331
+ "logits/rejected": 4442.10498046875,
332
+ "logps/chosen": -271.02423095703125,
333
+ "logps/rejected": -302.889404296875,
334
+ "loss": 0.6477,
335
+ "rewards/accuracies": 0.625,
336
+ "rewards/chosen": -46.31133270263672,
337
+ "rewards/margins": 34.11729431152344,
338
+ "rewards/rejected": -80.42862701416016,
339
+ "step": 210
340
+ },
341
+ {
342
+ "epoch": 0.1726844583987441,
343
+ "grad_norm": 29.099460861389012,
344
+ "learning_rate": 4.920911573406924e-07,
345
+ "logits/chosen": 6142.0341796875,
346
+ "logits/rejected": 5178.005859375,
347
+ "logps/chosen": -333.2041320800781,
348
+ "logps/rejected": -327.04351806640625,
349
+ "loss": 0.6432,
350
+ "rewards/accuracies": 0.7000000476837158,
351
+ "rewards/chosen": -50.571189880371094,
352
+ "rewards/margins": 42.93184280395508,
353
+ "rewards/rejected": -93.50303649902344,
354
+ "step": 220
355
+ },
356
+ {
357
+ "epoch": 0.18053375196232338,
358
+ "grad_norm": 11.33998439372873,
359
+ "learning_rate": 4.902902206053098e-07,
360
+ "logits/chosen": 5614.0341796875,
361
+ "logits/rejected": 5065.51123046875,
362
+ "logps/chosen": -323.0210266113281,
363
+ "logps/rejected": -348.66387939453125,
364
+ "loss": 0.645,
365
+ "rewards/accuracies": 0.6583333611488342,
366
+ "rewards/chosen": -52.74376678466797,
367
+ "rewards/margins": 37.89786148071289,
368
+ "rewards/rejected": -90.6416244506836,
369
+ "step": 230
370
+ },
371
+ {
372
+ "epoch": 0.18838304552590268,
373
+ "grad_norm": 19.303454918030365,
374
+ "learning_rate": 4.883087164434672e-07,
375
+ "logits/chosen": 5058.9169921875,
376
+ "logits/rejected": 4021.076904296875,
377
+ "logps/chosen": -298.27947998046875,
378
+ "logps/rejected": -326.84698486328125,
379
+ "loss": 0.6375,
380
+ "rewards/accuracies": 0.73333340883255,
381
+ "rewards/chosen": -58.58591842651367,
382
+ "rewards/margins": 55.33477020263672,
383
+ "rewards/rejected": -113.9206771850586,
384
+ "step": 240
385
+ },
386
+ {
387
+ "epoch": 0.19623233908948196,
388
+ "grad_norm": 22.796191821196953,
389
+ "learning_rate": 4.861481338675183e-07,
390
+ "logits/chosen": 5985.2314453125,
391
+ "logits/rejected": 5300.16259765625,
392
+ "logps/chosen": -288.8643798828125,
393
+ "logps/rejected": -353.60687255859375,
394
+ "loss": 0.6467,
395
+ "rewards/accuracies": 0.7083333730697632,
396
+ "rewards/chosen": -53.216957092285156,
397
+ "rewards/margins": 45.99776077270508,
398
+ "rewards/rejected": -99.21472930908203,
399
+ "step": 250
400
+ },
401
+ {
402
+ "epoch": 0.20408163265306123,
403
+ "grad_norm": 22.085356937400984,
404
+ "learning_rate": 4.838100964592904e-07,
405
+ "logits/chosen": 6164.17724609375,
406
+ "logits/rejected": 4921.74072265625,
407
+ "logps/chosen": -344.24920654296875,
408
+ "logps/rejected": -333.50433349609375,
409
+ "loss": 0.6499,
410
+ "rewards/accuracies": 0.7000000476837158,
411
+ "rewards/chosen": -59.49656295776367,
412
+ "rewards/margins": 35.483604431152344,
413
+ "rewards/rejected": -94.98017883300781,
414
+ "step": 260
415
+ },
416
+ {
417
+ "epoch": 0.2119309262166405,
418
+ "grad_norm": 12.489294995446524,
419
+ "learning_rate": 4.812963611500339e-07,
420
+ "logits/chosen": 5998.5322265625,
421
+ "logits/rejected": 5768.5107421875,
422
+ "logps/chosen": -372.312255859375,
423
+ "logps/rejected": -408.15008544921875,
424
+ "loss": 0.6342,
425
+ "rewards/accuracies": 0.6916667222976685,
426
+ "rewards/chosen": -97.80362701416016,
427
+ "rewards/margins": 43.51809310913086,
428
+ "rewards/rejected": -141.3217315673828,
429
+ "step": 270
430
+ },
431
+ {
432
+ "epoch": 0.21978021978021978,
433
+ "grad_norm": 16.417376858466337,
434
+ "learning_rate": 4.786088169001671e-07,
435
+ "logits/chosen": 5130.7666015625,
436
+ "logits/rejected": 4434.3466796875,
437
+ "logps/chosen": -319.5972595214844,
438
+ "logps/rejected": -379.0505676269531,
439
+ "loss": 0.6394,
440
+ "rewards/accuracies": 0.7916666269302368,
441
+ "rewards/chosen": -90.88194274902344,
442
+ "rewards/margins": 53.75859451293945,
443
+ "rewards/rejected": -144.64053344726562,
444
+ "step": 280
445
+ },
446
+ {
447
+ "epoch": 0.22762951334379905,
448
+ "grad_norm": 11.775433051492161,
449
+ "learning_rate": 4.7574948327980567e-07,
450
+ "logits/chosen": 7151.7099609375,
451
+ "logits/rejected": 5225.49169921875,
452
+ "logps/chosen": -390.4671325683594,
453
+ "logps/rejected": -385.64324951171875,
454
+ "loss": 0.6242,
455
+ "rewards/accuracies": 0.800000011920929,
456
+ "rewards/chosen": -65.6766128540039,
457
+ "rewards/margins": 62.20024490356445,
458
+ "rewards/rejected": -127.8768539428711,
459
+ "step": 290
460
+ },
461
+ {
462
+ "epoch": 0.23547880690737832,
463
+ "grad_norm": 20.393847208182954,
464
+ "learning_rate": 4.727205089511466e-07,
465
+ "logits/chosen": 5204.720703125,
466
+ "logits/rejected": 5109.517578125,
467
+ "logps/chosen": -291.4892272949219,
468
+ "logps/rejected": -349.64764404296875,
469
+ "loss": 0.636,
470
+ "rewards/accuracies": 0.6583333611488342,
471
+ "rewards/chosen": -54.74866485595703,
472
+ "rewards/margins": 50.97196960449219,
473
+ "rewards/rejected": -105.72062683105469,
474
+ "step": 300
475
+ },
476
+ {
477
+ "epoch": 0.24332810047095763,
478
+ "grad_norm": 12.64896234084034,
479
+ "learning_rate": 4.6952417005384247e-07,
480
+ "logits/chosen": 5871.3505859375,
481
+ "logits/rejected": 5241.853515625,
482
+ "logps/chosen": -292.93157958984375,
483
+ "logps/rejected": -314.87689208984375,
484
+ "loss": 0.6464,
485
+ "rewards/accuracies": 0.7166666388511658,
486
+ "rewards/chosen": -37.26299285888672,
487
+ "rewards/margins": 35.94820022583008,
488
+ "rewards/rejected": -73.21118927001953,
489
+ "step": 310
490
+ },
491
+ {
492
+ "epoch": 0.25117739403453687,
493
+ "grad_norm": 11.711611435010754,
494
+ "learning_rate": 4.661628684945851e-07,
495
+ "logits/chosen": 5884.6513671875,
496
+ "logits/rejected": 5080.0869140625,
497
+ "logps/chosen": -317.3797302246094,
498
+ "logps/rejected": -366.9216613769531,
499
+ "loss": 0.6397,
500
+ "rewards/accuracies": 0.6999999284744263,
501
+ "rewards/chosen": -40.09249496459961,
502
+ "rewards/margins": 54.90401077270508,
503
+ "rewards/rejected": -94.99651336669922,
504
+ "step": 320
505
+ },
506
+ {
507
+ "epoch": 0.25902668759811615,
508
+ "grad_norm": 16.606143175279893,
509
+ "learning_rate": 4.626391301421782e-07,
510
+ "logits/chosen": 5659.63232421875,
511
+ "logits/rejected": 5144.689453125,
512
+ "logps/chosen": -322.4103088378906,
513
+ "logps/rejected": -339.0274353027344,
514
+ "loss": 0.6465,
515
+ "rewards/accuracies": 0.675000011920929,
516
+ "rewards/chosen": -52.312225341796875,
517
+ "rewards/margins": 37.32312774658203,
518
+ "rewards/rejected": -89.6353530883789,
519
+ "step": 330
520
+ },
521
+ {
522
+ "epoch": 0.2668759811616955,
523
+ "grad_norm": 11.957399046843578,
524
+ "learning_rate": 4.5895560292945996e-07,
525
+ "logits/chosen": 5975.3984375,
526
+ "logits/rejected": 6048.248046875,
527
+ "logps/chosen": -306.0935974121094,
528
+ "logps/rejected": -384.51226806640625,
529
+ "loss": 0.6382,
530
+ "rewards/accuracies": 0.6666667461395264,
531
+ "rewards/chosen": -38.0104866027832,
532
+ "rewards/margins": 44.62034225463867,
533
+ "rewards/rejected": -82.63082885742188,
534
+ "step": 340
535
+ },
536
+ {
537
+ "epoch": 0.27472527472527475,
538
+ "grad_norm": 19.05929325375797,
539
+ "learning_rate": 4.5511505486349865e-07,
540
+ "logits/chosen": 6281.623046875,
541
+ "logits/rejected": 5641.45556640625,
542
+ "logps/chosen": -324.3663330078125,
543
+ "logps/rejected": -403.8905944824219,
544
+ "loss": 0.6352,
545
+ "rewards/accuracies": 0.7749999761581421,
546
+ "rewards/chosen": -51.458587646484375,
547
+ "rewards/margins": 68.93352508544922,
548
+ "rewards/rejected": -120.3921127319336,
549
+ "step": 350
550
+ },
551
+ {
552
+ "epoch": 0.282574568288854,
553
+ "grad_norm": 22.14740963615657,
554
+ "learning_rate": 4.5112037194555876e-07,
555
+ "logits/chosen": 5807.75927734375,
556
+ "logits/rejected": 5624.56396484375,
557
+ "logps/chosen": -337.0799255371094,
558
+ "logps/rejected": -433.28485107421875,
559
+ "loss": 0.6332,
560
+ "rewards/accuracies": 0.7666667103767395,
561
+ "rewards/chosen": -93.39493560791016,
562
+ "rewards/margins": 65.91687774658203,
563
+ "rewards/rejected": -159.31179809570312,
564
+ "step": 360
565
+ },
566
+ {
567
+ "epoch": 0.2904238618524333,
568
+ "grad_norm": 26.999582029041648,
569
+ "learning_rate": 4.4697455600239863e-07,
570
+ "logits/chosen": 5266.83642578125,
571
+ "logits/rejected": 4898.1513671875,
572
+ "logps/chosen": -338.98809814453125,
573
+ "logps/rejected": -360.06561279296875,
574
+ "loss": 0.6496,
575
+ "rewards/accuracies": 0.699999988079071,
576
+ "rewards/chosen": -80.08573913574219,
577
+ "rewards/margins": 41.56218719482422,
578
+ "rewards/rejected": -121.64791107177734,
579
+ "step": 370
580
+ },
581
+ {
582
+ "epoch": 0.29827315541601257,
583
+ "grad_norm": 10.145481304719103,
584
+ "learning_rate": 4.426807224305315e-07,
585
+ "logits/chosen": 6373.15576171875,
586
+ "logits/rejected": 5213.06591796875,
587
+ "logps/chosen": -349.0050964355469,
588
+ "logps/rejected": -351.0923156738281,
589
+ "loss": 0.6338,
590
+ "rewards/accuracies": 0.7916666865348816,
591
+ "rewards/chosen": -41.02812576293945,
592
+ "rewards/margins": 54.1557731628418,
593
+ "rewards/rejected": -95.18390655517578,
594
+ "step": 380
595
+ },
596
+ {
597
+ "epoch": 0.30612244897959184,
598
+ "grad_norm": 15.861363596358661,
599
+ "learning_rate": 4.3824209785514326e-07,
600
+ "logits/chosen": 6477.939453125,
601
+ "logits/rejected": 4905.5,
602
+ "logps/chosen": -341.7349548339844,
603
+ "logps/rejected": -361.1855163574219,
604
+ "loss": 0.6272,
605
+ "rewards/accuracies": 0.7916666865348816,
606
+ "rewards/chosen": -50.20849609375,
607
+ "rewards/margins": 65.48529052734375,
608
+ "rewards/rejected": -115.69378662109375,
609
+ "step": 390
610
+ },
611
+ {
612
+ "epoch": 0.3139717425431711,
613
+ "grad_norm": 20.26773681163985,
614
+ "learning_rate": 4.3366201770542687e-07,
615
+ "logits/chosen": 5476.63818359375,
616
+ "logits/rejected": 5291.42138671875,
617
+ "logps/chosen": -368.3787536621094,
618
+ "logps/rejected": -435.31072998046875,
619
+ "loss": 0.6384,
620
+ "rewards/accuracies": 0.75,
621
+ "rewards/chosen": -93.76130676269531,
622
+ "rewards/margins": 54.93895721435547,
623
+ "rewards/rejected": -148.7002716064453,
624
+ "step": 400
625
+ },
626
+ {
627
+ "epoch": 0.3218210361067504,
628
+ "grad_norm": 25.748156010376984,
629
+ "learning_rate": 4.2894392370815567e-07,
630
+ "logits/chosen": 5894.26708984375,
631
+ "logits/rejected": 5256.75634765625,
632
+ "logps/chosen": -404.880126953125,
633
+ "logps/rejected": -464.7074279785156,
634
+ "loss": 0.608,
635
+ "rewards/accuracies": 0.7583333849906921,
636
+ "rewards/chosen": -113.01127624511719,
637
+ "rewards/margins": 69.0715560913086,
638
+ "rewards/rejected": -182.08285522460938,
639
+ "step": 410
640
+ },
641
+ {
642
+ "epoch": 0.32967032967032966,
643
+ "grad_norm": 21.231993994206345,
644
+ "learning_rate": 4.2409136130137845e-07,
645
+ "logits/chosen": 5564.29833984375,
646
+ "logits/rejected": 4995.458984375,
647
+ "logps/chosen": -390.73931884765625,
648
+ "logps/rejected": -428.530517578125,
649
+ "loss": 0.6319,
650
+ "rewards/accuracies": 0.7250000238418579,
651
+ "rewards/chosen": -104.84605407714844,
652
+ "rewards/margins": 70.60201263427734,
653
+ "rewards/rejected": -175.44808959960938,
654
+ "step": 420
655
+ },
656
+ {
657
+ "epoch": 0.33751962323390894,
658
+ "grad_norm": 21.61004113876247,
659
+ "learning_rate": 4.1910797697018017e-07,
660
+ "logits/chosen": 5397.30712890625,
661
+ "logits/rejected": 4497.5673828125,
662
+ "logps/chosen": -340.72528076171875,
663
+ "logps/rejected": -390.37115478515625,
664
+ "loss": 0.6261,
665
+ "rewards/accuracies": 0.8166667222976685,
666
+ "rewards/chosen": -83.93035888671875,
667
+ "rewards/margins": 81.43653869628906,
668
+ "rewards/rejected": -165.36691284179688,
669
+ "step": 430
670
+ },
671
+ {
672
+ "epoch": 0.3453689167974882,
673
+ "grad_norm": 34.40148362381541,
674
+ "learning_rate": 4.1399751550651084e-07,
675
+ "logits/chosen": 5793.47119140625,
676
+ "logits/rejected": 5737.45263671875,
677
+ "logps/chosen": -303.27130126953125,
678
+ "logps/rejected": -359.61187744140625,
679
+ "loss": 0.6351,
680
+ "rewards/accuracies": 0.6999999284744263,
681
+ "rewards/chosen": -52.5032844543457,
682
+ "rewards/margins": 46.893043518066406,
683
+ "rewards/rejected": -99.39633178710938,
684
+ "step": 440
685
+ },
686
+ {
687
+ "epoch": 0.3532182103610675,
688
+ "grad_norm": 12.221057520913048,
689
+ "learning_rate": 4.087638171951401e-07,
690
+ "logits/chosen": 6695.4169921875,
691
+ "logits/rejected": 4779.6669921875,
692
+ "logps/chosen": -343.7985534667969,
693
+ "logps/rejected": -348.4494934082031,
694
+ "loss": 0.63,
695
+ "rewards/accuracies": 0.7416666746139526,
696
+ "rewards/chosen": -56.74163818359375,
697
+ "rewards/margins": 65.7086181640625,
698
+ "rewards/rejected": -122.45025634765625,
699
+ "step": 450
700
+ },
701
+ {
702
+ "epoch": 0.36106750392464676,
703
+ "grad_norm": 14.928154473572407,
704
+ "learning_rate": 4.034108149278543e-07,
705
+ "logits/chosen": 6924.58056640625,
706
+ "logits/rejected": 5269.8779296875,
707
+ "logps/chosen": -399.5293273925781,
708
+ "logps/rejected": -400.42681884765625,
709
+ "loss": 0.6167,
710
+ "rewards/accuracies": 0.7666666507720947,
711
+ "rewards/chosen": -66.81822204589844,
712
+ "rewards/margins": 68.95711517333984,
713
+ "rewards/rejected": -135.77532958984375,
714
+ "step": 460
715
+ },
716
+ {
717
+ "epoch": 0.36891679748822603,
718
+ "grad_norm": 33.075423246716404,
719
+ "learning_rate": 3.979425312480629e-07,
720
+ "logits/chosen": 5881.1962890625,
721
+ "logits/rejected": 5122.140625,
722
+ "logps/chosen": -389.74981689453125,
723
+ "logps/rejected": -441.1351623535156,
724
+ "loss": 0.6418,
725
+ "rewards/accuracies": 0.7250000238418579,
726
+ "rewards/chosen": -101.96400451660156,
727
+ "rewards/margins": 61.07242965698242,
728
+ "rewards/rejected": -163.03643798828125,
729
+ "step": 470
730
+ },
731
+ {
732
+ "epoch": 0.37676609105180536,
733
+ "grad_norm": 14.819747656679679,
734
+ "learning_rate": 3.923630753280357e-07,
735
+ "logits/chosen": 6393.35693359375,
736
+ "logits/rejected": 5423.63671875,
737
+ "logps/chosen": -363.44342041015625,
738
+ "logps/rejected": -406.1517028808594,
739
+ "loss": 0.6263,
740
+ "rewards/accuracies": 0.7916666865348816,
741
+ "rewards/chosen": -83.63682556152344,
742
+ "rewards/margins": 75.72159576416016,
743
+ "rewards/rejected": -159.3583984375,
744
+ "step": 480
745
+ },
746
+ {
747
+ "epoch": 0.38461538461538464,
748
+ "grad_norm": 15.214454392153003,
749
+ "learning_rate": 3.866766398810424e-07,
750
+ "logits/chosen": 6030.3671875,
751
+ "logits/rejected": 5667.58935546875,
752
+ "logps/chosen": -291.21600341796875,
753
+ "logps/rejected": -404.61065673828125,
754
+ "loss": 0.6114,
755
+ "rewards/accuracies": 0.824999988079071,
756
+ "rewards/chosen": -50.27495574951172,
757
+ "rewards/margins": 81.7363052368164,
758
+ "rewards/rejected": -132.01126098632812,
759
+ "step": 490
760
+ },
761
+ {
762
+ "epoch": 0.3924646781789639,
763
+ "grad_norm": 26.504081081962486,
764
+ "learning_rate": 3.8088749801071496e-07,
765
+ "logits/chosen": 6422.83056640625,
766
+ "logits/rejected": 4957.6240234375,
767
+ "logps/chosen": -383.7412109375,
768
+ "logps/rejected": -426.57318115234375,
769
+ "loss": 0.6265,
770
+ "rewards/accuracies": 0.7583333253860474,
771
+ "rewards/chosen": -85.2517318725586,
772
+ "rewards/margins": 76.8886947631836,
773
+ "rewards/rejected": -162.1404266357422,
774
+ "step": 500
775
+ },
776
+ {
777
+ "epoch": 0.4003139717425432,
778
+ "grad_norm": 19.92131685224601,
779
+ "learning_rate": 3.75e-07,
780
+ "logits/chosen": 5211.85888671875,
781
+ "logits/rejected": 4546.10302734375,
782
+ "logps/chosen": -338.0028076171875,
783
+ "logps/rejected": -391.8753356933594,
784
+ "loss": 0.6233,
785
+ "rewards/accuracies": 0.7750000953674316,
786
+ "rewards/chosen": -81.1429672241211,
787
+ "rewards/margins": 81.61470031738281,
788
+ "rewards/rejected": -162.75765991210938,
789
+ "step": 510
790
+ },
791
+ {
792
+ "epoch": 0.40816326530612246,
793
+ "grad_norm": 17.195866910495663,
794
+ "learning_rate": 3.6901857004211443e-07,
795
+ "logits/chosen": 5492.595703125,
796
+ "logits/rejected": 5055.5869140625,
797
+ "logps/chosen": -354.20428466796875,
798
+ "logps/rejected": -411.8438415527344,
799
+ "loss": 0.6448,
800
+ "rewards/accuracies": 0.7166666984558105,
801
+ "rewards/chosen": -88.03140258789062,
802
+ "rewards/margins": 54.68613815307617,
803
+ "rewards/rejected": -142.71755981445312,
804
+ "step": 520
805
+ },
806
+ {
807
+ "epoch": 0.41601255886970173,
808
+ "grad_norm": 11.497234011291072,
809
+ "learning_rate": 3.6294770291596076e-07,
810
+ "logits/chosen": 6242.5810546875,
811
+ "logits/rejected": 5086.48828125,
812
+ "logps/chosen": -348.9159240722656,
813
+ "logps/rejected": -372.79046630859375,
814
+ "loss": 0.619,
815
+ "rewards/accuracies": 0.7166666388511658,
816
+ "rewards/chosen": -64.62379455566406,
817
+ "rewards/margins": 44.09585189819336,
818
+ "rewards/rejected": -108.71965026855469,
819
+ "step": 530
820
+ },
821
+ {
822
+ "epoch": 0.423861852433281,
823
+ "grad_norm": 16.092408213575606,
824
+ "learning_rate": 3.5679196060850034e-07,
825
+ "logits/chosen": 5961.3251953125,
826
+ "logits/rejected": 5273.64794921875,
827
+ "logps/chosen": -344.6712646484375,
828
+ "logps/rejected": -383.50048828125,
829
+ "loss": 0.6307,
830
+ "rewards/accuracies": 0.75,
831
+ "rewards/chosen": -67.28762817382812,
832
+ "rewards/margins": 60.815452575683594,
833
+ "rewards/rejected": -128.1031036376953,
834
+ "step": 540
835
+ },
836
+ {
837
+ "epoch": 0.4317111459968603,
838
+ "grad_norm": 22.117577767433108,
839
+ "learning_rate": 3.505559688866229e-07,
840
+ "logits/chosen": 5753.71728515625,
841
+ "logits/rejected": 5307.4189453125,
842
+ "logps/chosen": -353.93414306640625,
843
+ "logps/rejected": -433.62823486328125,
844
+ "loss": 0.6245,
845
+ "rewards/accuracies": 0.7333333492279053,
846
+ "rewards/chosen": -72.5975112915039,
847
+ "rewards/margins": 69.84739685058594,
848
+ "rewards/rejected": -142.44491577148438,
849
+ "step": 550
850
+ },
851
+ {
852
+ "epoch": 0.43956043956043955,
853
+ "grad_norm": 16.177064459530992,
854
+ "learning_rate": 3.4424441382108826e-07,
855
+ "logits/chosen": 5751.61767578125,
856
+ "logits/rejected": 5381.62939453125,
857
+ "logps/chosen": -358.9526672363281,
858
+ "logps/rejected": -400.9219055175781,
859
+ "loss": 0.6408,
860
+ "rewards/accuracies": 0.7166666984558105,
861
+ "rewards/chosen": -82.8250732421875,
862
+ "rewards/margins": 51.318634033203125,
863
+ "rewards/rejected": -134.14370727539062,
864
+ "step": 560
865
+ },
866
+ {
867
+ "epoch": 0.4474097331240188,
868
+ "grad_norm": 22.155261104381104,
869
+ "learning_rate": 3.378620382651523e-07,
870
+ "logits/chosen": 6090.033203125,
871
+ "logits/rejected": 5616.0712890625,
872
+ "logps/chosen": -389.67449951171875,
873
+ "logps/rejected": -432.17083740234375,
874
+ "loss": 0.6186,
875
+ "rewards/accuracies": 0.7916667461395264,
876
+ "rewards/chosen": -75.10955810546875,
877
+ "rewards/margins": 65.12030792236328,
878
+ "rewards/rejected": -140.22988891601562,
879
+ "step": 570
880
+ },
881
+ {
882
+ "epoch": 0.4552590266875981,
883
+ "grad_norm": 21.25069883148197,
884
+ "learning_rate": 3.314136382905234e-07,
885
+ "logits/chosen": 6104.90234375,
886
+ "logits/rejected": 5452.4833984375,
887
+ "logps/chosen": -363.5154724121094,
888
+ "logps/rejected": -447.11553955078125,
889
+ "loss": 0.6198,
890
+ "rewards/accuracies": 0.800000011920929,
891
+ "rewards/chosen": -76.26863098144531,
892
+ "rewards/margins": 85.99644470214844,
893
+ "rewards/rejected": -162.2650909423828,
894
+ "step": 580
895
+ },
896
+ {
897
+ "epoch": 0.4631083202511774,
898
+ "grad_norm": 17.362372097837717,
899
+ "learning_rate": 3.249040595833274e-07,
900
+ "logits/chosen": 6601.0,
901
+ "logits/rejected": 5511.4287109375,
902
+ "logps/chosen": -402.6153259277344,
903
+ "logps/rejected": -423.739501953125,
904
+ "loss": 0.6132,
905
+ "rewards/accuracies": 0.7749999761581421,
906
+ "rewards/chosen": -96.46189880371094,
907
+ "rewards/margins": 81.43740844726562,
908
+ "rewards/rejected": -177.89932250976562,
909
+ "step": 590
910
+ },
911
+ {
912
+ "epoch": 0.47095761381475665,
913
+ "grad_norm": 23.17004436475313,
914
+ "learning_rate": 3.1833819380279023e-07,
915
+ "logits/chosen": 6238.583984375,
916
+ "logits/rejected": 5254.064453125,
917
+ "logps/chosen": -360.0862731933594,
918
+ "logps/rejected": -433.875,
919
+ "loss": 0.6181,
920
+ "rewards/accuracies": 0.7916666865348816,
921
+ "rewards/chosen": -107.59527587890625,
922
+ "rewards/margins": 71.31594848632812,
923
+ "rewards/rejected": -178.91122436523438,
924
+ "step": 600
925
+ },
926
+ {
927
+ "epoch": 0.478806907378336,
928
+ "grad_norm": 12.736341325859744,
929
+ "learning_rate": 3.11720974905373e-07,
930
+ "logits/chosen": 5983.64990234375,
931
+ "logits/rejected": 5169.474609375,
932
+ "logps/chosen": -365.88275146484375,
933
+ "logps/rejected": -418.73504638671875,
934
+ "loss": 0.6131,
935
+ "rewards/accuracies": 0.8333333730697632,
936
+ "rewards/chosen": -93.04127502441406,
937
+ "rewards/margins": 75.20207977294922,
938
+ "rewards/rejected": -168.2433624267578,
939
+ "step": 610
940
+ },
941
+ {
942
+ "epoch": 0.48665620094191525,
943
+ "grad_norm": 14.41955430489932,
944
+ "learning_rate": 3.0505737543712275e-07,
945
+ "logits/chosen": 5046.630859375,
946
+ "logits/rejected": 4108.693359375,
947
+ "logps/chosen": -358.97125244140625,
948
+ "logps/rejected": -385.05572509765625,
949
+ "loss": 0.6279,
950
+ "rewards/accuracies": 0.7083333730697632,
951
+ "rewards/chosen": -111.14530181884766,
952
+ "rewards/margins": 60.3331298828125,
953
+ "rewards/rejected": -171.4784393310547,
954
+ "step": 620
955
+ },
956
+ {
957
+ "epoch": 0.4945054945054945,
958
+ "grad_norm": 14.568591201789333,
959
+ "learning_rate": 2.9835240279702513e-07,
960
+ "logits/chosen": 6596.6220703125,
961
+ "logits/rejected": 5537.1279296875,
962
+ "logps/chosen": -393.75347900390625,
963
+ "logps/rejected": -425.38739013671875,
964
+ "loss": 0.621,
965
+ "rewards/accuracies": 0.7750000357627869,
966
+ "rewards/chosen": -77.04191589355469,
967
+ "rewards/margins": 82.31060028076172,
968
+ "rewards/rejected": -159.35252380371094,
969
+ "step": 630
970
+ },
971
+ {
972
+ "epoch": 0.5023547880690737,
973
+ "grad_norm": 13.739673447904634,
974
+ "learning_rate": 2.9161109547416667e-07,
975
+ "logits/chosen": 6305.04052734375,
976
+ "logits/rejected": 5372.958984375,
977
+ "logps/chosen": -365.43939208984375,
978
+ "logps/rejected": -413.84014892578125,
979
+ "loss": 0.6222,
980
+ "rewards/accuracies": 0.6916667222976685,
981
+ "rewards/chosen": -86.74894714355469,
982
+ "rewards/margins": 49.25041580200195,
983
+ "rewards/rejected": -135.99935913085938,
984
+ "step": 640
985
+ },
986
+ {
987
+ "epoch": 0.5102040816326531,
988
+ "grad_norm": 15.591649633238864,
989
+ "learning_rate": 2.848385192615339e-07,
990
+ "logits/chosen": 5376.2451171875,
991
+ "logits/rejected": 4345.314453125,
992
+ "logps/chosen": -336.9205322265625,
993
+ "logps/rejected": -367.5696105957031,
994
+ "loss": 0.6219,
995
+ "rewards/accuracies": 0.7416666746139526,
996
+ "rewards/chosen": -79.38199615478516,
997
+ "rewards/margins": 61.08577346801758,
998
+ "rewards/rejected": -140.46775817871094,
999
+ "step": 650
1000
+ },
1001
+ {
1002
+ "epoch": 0.5180533751962323,
1003
+ "grad_norm": 18.657960252226093,
1004
+ "learning_rate": 2.780397634492949e-07,
1005
+ "logits/chosen": 5987.65380859375,
1006
+ "logits/rejected": 4756.13671875,
1007
+ "logps/chosen": -371.12078857421875,
1008
+ "logps/rejected": -419.0254821777344,
1009
+ "loss": 0.625,
1010
+ "rewards/accuracies": 0.8000000715255737,
1011
+ "rewards/chosen": -80.80254364013672,
1012
+ "rewards/margins": 85.95211791992188,
1013
+ "rewards/rejected": -166.75466918945312,
1014
+ "step": 660
1015
+ },
1016
+ {
1017
+ "epoch": 0.5259026687598116,
1018
+ "grad_norm": 20.61975768497305,
1019
+ "learning_rate": 2.71219937000424e-07,
1020
+ "logits/chosen": 5989.3681640625,
1021
+ "logits/rejected": 4901.67138671875,
1022
+ "logps/chosen": -370.17462158203125,
1023
+ "logps/rejected": -413.4952697753906,
1024
+ "loss": 0.6243,
1025
+ "rewards/accuracies": 0.7416666746139526,
1026
+ "rewards/chosen": -93.9641342163086,
1027
+ "rewards/margins": 68.44216918945312,
1028
+ "rewards/rejected": -162.4062957763672,
1029
+ "step": 670
1030
+ },
1031
+ {
1032
+ "epoch": 0.533751962323391,
1033
+ "grad_norm": 18.87684601216833,
1034
+ "learning_rate": 2.6438416471154273e-07,
1035
+ "logits/chosen": 5865.7666015625,
1036
+ "logits/rejected": 4891.36669921875,
1037
+ "logps/chosen": -372.4833679199219,
1038
+ "logps/rejected": -396.7239685058594,
1039
+ "loss": 0.6267,
1040
+ "rewards/accuracies": 0.75,
1041
+ "rewards/chosen": -94.6555404663086,
1042
+ "rewards/margins": 67.06285095214844,
1043
+ "rewards/rejected": -161.7183837890625,
1044
+ "step": 680
1045
+ },
1046
+ {
1047
+ "epoch": 0.5416012558869702,
1048
+ "grad_norm": 14.822028291771003,
1049
+ "learning_rate": 2.5753758336186326e-07,
1050
+ "logits/chosen": 5776.60498046875,
1051
+ "logits/rejected": 5268.0185546875,
1052
+ "logps/chosen": -350.5502624511719,
1053
+ "logps/rejected": -428.06854248046875,
1054
+ "loss": 0.603,
1055
+ "rewards/accuracies": 0.7749999761581421,
1056
+ "rewards/chosen": -75.46115112304688,
1057
+ "rewards/margins": 75.14856719970703,
1058
+ "rewards/rejected": -150.60972595214844,
1059
+ "step": 690
1060
+ },
1061
+ {
1062
+ "epoch": 0.5494505494505495,
1063
+ "grad_norm": 13.55417698931459,
1064
+ "learning_rate": 2.5068533785312666e-07,
1065
+ "logits/chosen": 5536.5478515625,
1066
+ "logits/rejected": 5285.6142578125,
1067
+ "logps/chosen": -339.8960876464844,
1068
+ "logps/rejected": -404.1838684082031,
1069
+ "loss": 0.6348,
1070
+ "rewards/accuracies": 0.7749999761581421,
1071
+ "rewards/chosen": -89.77982330322266,
1072
+ "rewards/margins": 68.95240783691406,
1073
+ "rewards/rejected": -158.7322235107422,
1074
+ "step": 700
1075
+ },
1076
+ {
1077
+ "epoch": 0.5572998430141287,
1078
+ "grad_norm": 13.967254349794798,
1079
+ "learning_rate": 2.4383257734343794e-07,
1080
+ "logits/chosen": 5494.7998046875,
1081
+ "logits/rejected": 5455.1875,
1082
+ "logps/chosen": -332.26739501953125,
1083
+ "logps/rejected": -411.1310119628906,
1084
+ "loss": 0.6169,
1085
+ "rewards/accuracies": 0.7750000953674316,
1086
+ "rewards/chosen": -83.0215072631836,
1087
+ "rewards/margins": 64.02027893066406,
1088
+ "rewards/rejected": -147.04177856445312,
1089
+ "step": 710
1090
+ },
1091
+ {
1092
+ "epoch": 0.565149136577708,
1093
+ "grad_norm": 15.383264284785263,
1094
+ "learning_rate": 2.3698445137790258e-07,
1095
+ "logits/chosen": 5931.5546875,
1096
+ "logits/rejected": 5057.220703125,
1097
+ "logps/chosen": -349.0887756347656,
1098
+ "logps/rejected": -400.6289978027344,
1099
+ "loss": 0.6146,
1100
+ "rewards/accuracies": 0.7833333611488342,
1101
+ "rewards/chosen": -64.32401275634766,
1102
+ "rewards/margins": 78.18653869628906,
1103
+ "rewards/rejected": -142.51055908203125,
1104
+ "step": 720
1105
+ },
1106
+ {
1107
+ "epoch": 0.5729984301412873,
1108
+ "grad_norm": 13.338256084406837,
1109
+ "learning_rate": 2.3014610601897157e-07,
1110
+ "logits/chosen": 6402.5517578125,
1111
+ "logits/rejected": 4874.70361328125,
1112
+ "logps/chosen": -372.53619384765625,
1113
+ "logps/rejected": -397.6921081542969,
1114
+ "loss": 0.6161,
1115
+ "rewards/accuracies": 0.7916667461395264,
1116
+ "rewards/chosen": -77.47715759277344,
1117
+ "rewards/margins": 79.93022918701172,
1118
+ "rewards/rejected": -157.40737915039062,
1119
+ "step": 730
1120
+ },
1121
+ {
1122
+ "epoch": 0.5808477237048666,
1123
+ "grad_norm": 17.616655194208075,
1124
+ "learning_rate": 2.2332267997940513e-07,
1125
+ "logits/chosen": 5318.05322265625,
1126
+ "logits/rejected": 4492.63818359375,
1127
+ "logps/chosen": -317.3236999511719,
1128
+ "logps/rejected": -361.37701416015625,
1129
+ "loss": 0.6124,
1130
+ "rewards/accuracies": 0.783333420753479,
1131
+ "rewards/chosen": -69.31564331054688,
1132
+ "rewards/margins": 74.50846862792969,
1133
+ "rewards/rejected": -143.82412719726562,
1134
+ "step": 740
1135
+ },
1136
+ {
1137
+ "epoch": 0.5886970172684458,
1138
+ "grad_norm": 17.26484587041811,
1139
+ "learning_rate": 2.1651930076075723e-07,
1140
+ "logits/chosen": 5809.0048828125,
1141
+ "logits/rejected": 5208.9267578125,
1142
+ "logps/chosen": -324.5057373046875,
1143
+ "logps/rejected": -368.41693115234375,
1144
+ "loss": 0.6283,
1145
+ "rewards/accuracies": 0.7250000238418579,
1146
+ "rewards/chosen": -84.24357604980469,
1147
+ "rewards/margins": 61.6234130859375,
1148
+ "rewards/rejected": -145.8669891357422,
1149
+ "step": 750
1150
+ },
1151
+ {
1152
+ "epoch": 0.5965463108320251,
1153
+ "grad_norm": 18.908183485265077,
1154
+ "learning_rate": 2.0974108080028692e-07,
1155
+ "logits/chosen": 6082.65185546875,
1156
+ "logits/rejected": 4746.8046875,
1157
+ "logps/chosen": -353.37567138671875,
1158
+ "logps/rejected": -395.29595947265625,
1159
+ "loss": 0.6149,
1160
+ "rewards/accuracies": 0.7500000596046448,
1161
+ "rewards/chosen": -90.01509094238281,
1162
+ "rewards/margins": 67.36105346679688,
1163
+ "rewards/rejected": -157.3761444091797,
1164
+ "step": 760
1165
+ },
1166
+ {
1167
+ "epoch": 0.6043956043956044,
1168
+ "grad_norm": 17.1773340775,
1169
+ "learning_rate": 2.0299311362918773e-07,
1170
+ "logits/chosen": 6311.5419921875,
1171
+ "logits/rejected": 5381.1201171875,
1172
+ "logps/chosen": -386.3832092285156,
1173
+ "logps/rejected": -444.20550537109375,
1174
+ "loss": 0.6297,
1175
+ "rewards/accuracies": 0.7583333849906921,
1176
+ "rewards/chosen": -91.73824310302734,
1177
+ "rewards/margins": 67.6690902709961,
1178
+ "rewards/rejected": -159.40731811523438,
1179
+ "step": 770
1180
+ },
1181
+ {
1182
+ "epoch": 0.6122448979591837,
1183
+ "grad_norm": 12.140213576431595,
1184
+ "learning_rate": 1.962804700450265e-07,
1185
+ "logits/chosen": 6080.9736328125,
1186
+ "logits/rejected": 5723.802734375,
1187
+ "logps/chosen": -384.7323303222656,
1188
+ "logps/rejected": -490.9775390625,
1189
+ "loss": 0.6177,
1190
+ "rewards/accuracies": 0.7583333849906921,
1191
+ "rewards/chosen": -101.59971618652344,
1192
+ "rewards/margins": 74.81465148925781,
1193
+ "rewards/rejected": -176.4143829345703,
1194
+ "step": 780
1195
+ },
1196
+ {
1197
+ "epoch": 0.6200941915227629,
1198
+ "grad_norm": 23.19008194008529,
1199
+ "learning_rate": 1.8960819430126334e-07,
1200
+ "logits/chosen": 5738.3056640625,
1201
+ "logits/rejected": 5031.94189453125,
1202
+ "logps/chosen": -359.13568115234375,
1203
+ "logps/rejected": -446.73992919921875,
1204
+ "loss": 0.61,
1205
+ "rewards/accuracies": 0.800000011920929,
1206
+ "rewards/chosen": -104.6843032836914,
1207
+ "rewards/margins": 86.70986938476562,
1208
+ "rewards/rejected": -191.39418029785156,
1209
+ "step": 790
1210
+ },
1211
+ {
1212
+ "epoch": 0.6279434850863422,
1213
+ "grad_norm": 21.233318483525284,
1214
+ "learning_rate": 1.8298130031671972e-07,
1215
+ "logits/chosen": 5713.6044921875,
1216
+ "logits/rejected": 4974.9345703125,
1217
+ "logps/chosen": -377.11602783203125,
1218
+ "logps/rejected": -432.98297119140625,
1219
+ "loss": 0.6231,
1220
+ "rewards/accuracies": 0.7583333849906921,
1221
+ "rewards/chosen": -103.37955474853516,
1222
+ "rewards/margins": 63.08623504638672,
1223
+ "rewards/rejected": -166.46578979492188,
1224
+ "step": 800
1225
+ },
1226
+ {
1227
+ "epoch": 0.6357927786499215,
1228
+ "grad_norm": 18.08127392611742,
1229
+ "learning_rate": 1.7640476790784075e-07,
1230
+ "logits/chosen": 5225.978515625,
1231
+ "logits/rejected": 4710.2734375,
1232
+ "logps/chosen": -369.49896240234375,
1233
+ "logps/rejected": -446.40484619140625,
1234
+ "loss": 0.6149,
1235
+ "rewards/accuracies": 0.7250000238418579,
1236
+ "rewards/chosen": -95.6690673828125,
1237
+ "rewards/margins": 76.96039581298828,
1238
+ "rewards/rejected": -172.62945556640625,
1239
+ "step": 810
1240
+ },
1241
+ {
1242
+ "epoch": 0.6436420722135008,
1243
+ "grad_norm": 27.28580138938831,
1244
+ "learning_rate": 1.6988353904658492e-07,
1245
+ "logits/chosen": 5757.90625,
1246
+ "logits/rejected": 4414.92041015625,
1247
+ "logps/chosen": -383.70391845703125,
1248
+ "logps/rejected": -388.5174560546875,
1249
+ "loss": 0.6193,
1250
+ "rewards/accuracies": 0.7833333611488342,
1251
+ "rewards/chosen": -100.63114166259766,
1252
+ "rewards/margins": 72.06126403808594,
1253
+ "rewards/rejected": -172.69239807128906,
1254
+ "step": 820
1255
+ },
1256
+ {
1257
+ "epoch": 0.6514913657770801,
1258
+ "grad_norm": 26.165106071182983,
1259
+ "learning_rate": 1.634225141467513e-07,
1260
+ "logits/chosen": 5647.6025390625,
1261
+ "logits/rejected": 5025.44970703125,
1262
+ "logps/chosen": -368.6767883300781,
1263
+ "logps/rejected": -442.51751708984375,
1264
+ "loss": 0.6168,
1265
+ "rewards/accuracies": 0.7916666865348816,
1266
+ "rewards/chosen": -105.22233581542969,
1267
+ "rewards/margins": 89.50996398925781,
1268
+ "rewards/rejected": -194.73228454589844,
1269
+ "step": 830
1270
+ },
1271
+ {
1272
+ "epoch": 0.6593406593406593,
1273
+ "grad_norm": 12.05974686118023,
1274
+ "learning_rate": 1.570265483815364e-07,
1275
+ "logits/chosen": 6232.81005859375,
1276
+ "logits/rejected": 5058.81494140625,
1277
+ "logps/chosen": -383.663818359375,
1278
+ "logps/rejected": -444.72442626953125,
1279
+ "loss": 0.6187,
1280
+ "rewards/accuracies": 0.6916666030883789,
1281
+ "rewards/chosen": -98.13055419921875,
1282
+ "rewards/margins": 72.39865112304688,
1283
+ "rewards/rejected": -170.52920532226562,
1284
+ "step": 840
1285
+ },
1286
+ {
1287
+ "epoch": 0.6671899529042387,
1288
+ "grad_norm": 14.238384519302777,
1289
+ "learning_rate": 1.5070044803508691e-07,
1290
+ "logits/chosen": 5735.76953125,
1291
+ "logits/rejected": 5156.517578125,
1292
+ "logps/chosen": -371.0335693359375,
1293
+ "logps/rejected": -424.44903564453125,
1294
+ "loss": 0.6042,
1295
+ "rewards/accuracies": 0.7583333253860474,
1296
+ "rewards/chosen": -98.491455078125,
1297
+ "rewards/margins": 79.99961853027344,
1298
+ "rewards/rejected": -178.49105834960938,
1299
+ "step": 850
1300
+ },
1301
+ {
1302
+ "epoch": 0.6750392464678179,
1303
+ "grad_norm": 21.691254923241676,
1304
+ "learning_rate": 1.444489668907914e-07,
1305
+ "logits/chosen": 6212.0146484375,
1306
+ "logits/rejected": 5258.91845703125,
1307
+ "logps/chosen": -396.6695251464844,
1308
+ "logps/rejected": -415.2281799316406,
1309
+ "loss": 0.6366,
1310
+ "rewards/accuracies": 0.7666666507720947,
1311
+ "rewards/chosen": -93.80113220214844,
1312
+ "rewards/margins": 67.12193298339844,
1313
+ "rewards/rejected": -160.92306518554688,
1314
+ "step": 860
1315
+ },
1316
+ {
1317
+ "epoch": 0.6828885400313972,
1318
+ "grad_norm": 15.830471277855608,
1319
+ "learning_rate": 1.3827680265902232e-07,
1320
+ "logits/chosen": 6164.56201171875,
1321
+ "logits/rejected": 5070.73779296875,
1322
+ "logps/chosen": -370.5370788574219,
1323
+ "logps/rejected": -404.1648254394531,
1324
+ "loss": 0.6199,
1325
+ "rewards/accuracies": 0.7499999403953552,
1326
+ "rewards/chosen": -81.1246109008789,
1327
+ "rewards/margins": 68.8310775756836,
1328
+ "rewards/rejected": -149.9556884765625,
1329
+ "step": 870
1330
+ },
1331
+ {
1332
+ "epoch": 0.6907378335949764,
1333
+ "grad_norm": 19.644559397703166,
1334
+ "learning_rate": 1.3218859344701632e-07,
1335
+ "logits/chosen": 5451.4140625,
1336
+ "logits/rejected": 5144.291015625,
1337
+ "logps/chosen": -334.55950927734375,
1338
+ "logps/rejected": -431.77099609375,
1339
+ "loss": 0.6184,
1340
+ "rewards/accuracies": 0.7749999761581421,
1341
+ "rewards/chosen": -75.80677032470703,
1342
+ "rewards/margins": 67.65657806396484,
1343
+ "rewards/rejected": -143.46334838867188,
1344
+ "step": 880
1345
+ },
1346
+ {
1347
+ "epoch": 0.6985871271585558,
1348
+ "grad_norm": 15.901674866172888,
1349
+ "learning_rate": 1.2618891427354172e-07,
1350
+ "logits/chosen": 6396.1279296875,
1351
+ "logits/rejected": 5205.91162109375,
1352
+ "logps/chosen": -382.37579345703125,
1353
+ "logps/rejected": -417.2171936035156,
1354
+ "loss": 0.6239,
1355
+ "rewards/accuracies": 0.7916666865348816,
1356
+ "rewards/chosen": -69.84732818603516,
1357
+ "rewards/margins": 85.34009552001953,
1358
+ "rewards/rejected": -155.18740844726562,
1359
+ "step": 890
1360
+ },
1361
+ {
1362
+ "epoch": 0.706436420722135,
1363
+ "grad_norm": 16.09863720828146,
1364
+ "learning_rate": 1.202822736309758e-07,
1365
+ "logits/chosen": 5450.23681640625,
1366
+ "logits/rejected": 4962.1318359375,
1367
+ "logps/chosen": -340.2064514160156,
1368
+ "logps/rejected": -422.90478515625,
1369
+ "loss": 0.6223,
1370
+ "rewards/accuracies": 0.75,
1371
+ "rewards/chosen": -82.16495513916016,
1372
+ "rewards/margins": 76.31831359863281,
1373
+ "rewards/rejected": -158.4832763671875,
1374
+ "step": 900
1375
+ },
1376
+ {
1377
+ "epoch": 0.7142857142857143,
1378
+ "grad_norm": 25.11806872646705,
1379
+ "learning_rate": 1.1447311009737299e-07,
1380
+ "logits/chosen": 5361.8212890625,
1381
+ "logits/rejected": 5049.03173828125,
1382
+ "logps/chosen": -341.89459228515625,
1383
+ "logps/rejected": -418.7533264160156,
1384
+ "loss": 0.631,
1385
+ "rewards/accuracies": 0.7583333849906921,
1386
+ "rewards/chosen": -84.32719421386719,
1387
+ "rewards/margins": 76.45072937011719,
1388
+ "rewards/rejected": -160.77792358398438,
1389
+ "step": 910
1390
+ },
1391
+ {
1392
+ "epoch": 0.7221350078492935,
1393
+ "grad_norm": 15.417662364209441,
1394
+ "learning_rate": 1.0876578900107053e-07,
1395
+ "logits/chosen": 5907.921875,
1396
+ "logits/rejected": 4922.83349609375,
1397
+ "logps/chosen": -362.728759765625,
1398
+ "logps/rejected": -393.6321716308594,
1399
+ "loss": 0.6225,
1400
+ "rewards/accuracies": 0.8333333730697632,
1401
+ "rewards/chosen": -76.00703430175781,
1402
+ "rewards/margins": 72.67141723632812,
1403
+ "rewards/rejected": -148.67845153808594,
1404
+ "step": 920
1405
+ },
1406
+ {
1407
+ "epoch": 0.7299843014128728,
1408
+ "grad_norm": 13.068633060932935,
1409
+ "learning_rate": 1.0316459914033793e-07,
1410
+ "logits/chosen": 5875.71240234375,
1411
+ "logits/rejected": 4352.42041015625,
1412
+ "logps/chosen": -371.8520812988281,
1413
+ "logps/rejected": -387.53839111328125,
1414
+ "loss": 0.618,
1415
+ "rewards/accuracies": 0.7833333611488342,
1416
+ "rewards/chosen": -83.89849090576172,
1417
+ "rewards/margins": 70.6930160522461,
1418
+ "rewards/rejected": -154.59152221679688,
1419
+ "step": 930
1420
+ },
1421
+ {
1422
+ "epoch": 0.7378335949764521,
1423
+ "grad_norm": 19.777463963280816,
1424
+ "learning_rate": 9.767374956053584e-08,
1425
+ "logits/chosen": 5708.94482421875,
1426
+ "logits/rejected": 4980.36181640625,
1427
+ "logps/chosen": -343.82733154296875,
1428
+ "logps/rejected": -408.415771484375,
1429
+ "loss": 0.6222,
1430
+ "rewards/accuracies": 0.7666667103767395,
1431
+ "rewards/chosen": -78.96133422851562,
1432
+ "rewards/margins": 82.29380798339844,
1433
+ "rewards/rejected": -161.25514221191406,
1434
+ "step": 940
1435
+ },
1436
+ {
1437
+ "epoch": 0.7456828885400314,
1438
+ "grad_norm": 14.697590410758233,
1439
+ "learning_rate": 9.229736639120561e-08,
1440
+ "logits/chosen": 5883.52978515625,
1441
+ "logits/rejected": 5368.93359375,
1442
+ "logps/chosen": -346.15911865234375,
1443
+ "logps/rejected": -399.55218505859375,
1444
+ "loss": 0.6306,
1445
+ "rewards/accuracies": 0.7333333492279053,
1446
+ "rewards/chosen": -82.5989990234375,
1447
+ "rewards/margins": 54.160057067871094,
1448
+ "rewards/rejected": -136.75906372070312,
1449
+ "step": 950
1450
+ },
1451
+ {
1452
+ "epoch": 0.7535321821036107,
1453
+ "grad_norm": 23.114265338822328,
1454
+ "learning_rate": 8.70394897454659e-08,
1455
+ "logits/chosen": 5751.0556640625,
1456
+ "logits/rejected": 5106.9912109375,
1457
+ "logps/chosen": -331.0142517089844,
1458
+ "logps/rejected": -385.95538330078125,
1459
+ "loss": 0.6177,
1460
+ "rewards/accuracies": 0.7916666865348816,
1461
+ "rewards/chosen": -67.00068664550781,
1462
+ "rewards/margins": 72.63203430175781,
1463
+ "rewards/rejected": -139.63272094726562,
1464
+ "step": 960
1465
+ },
1466
+ {
1467
+ "epoch": 0.7613814756671899,
1468
+ "grad_norm": 18.27070448355251,
1469
+ "learning_rate": 8.19040706840472e-08,
1470
+ "logits/chosen": 5845.2509765625,
1471
+ "logits/rejected": 4865.30810546875,
1472
+ "logps/chosen": -361.5416564941406,
1473
+ "logps/rejected": -396.51556396484375,
1474
+ "loss": 0.6133,
1475
+ "rewards/accuracies": 0.7250000238418579,
1476
+ "rewards/chosen": -72.41023254394531,
1477
+ "rewards/margins": 77.77088928222656,
1478
+ "rewards/rejected": -150.18113708496094,
1479
+ "step": 970
1480
+ },
1481
+ {
1482
+ "epoch": 0.7692307692307693,
1483
+ "grad_norm": 12.08737263588805,
1484
+ "learning_rate": 7.689496824624525e-08,
1485
+ "logits/chosen": 5548.05224609375,
1486
+ "logits/rejected": 4407.2763671875,
1487
+ "logps/chosen": -346.5332336425781,
1488
+ "logps/rejected": -395.7588806152344,
1489
+ "loss": 0.6106,
1490
+ "rewards/accuracies": 0.7333333492279053,
1491
+ "rewards/chosen": -69.89125061035156,
1492
+ "rewards/margins": 87.18049621582031,
1493
+ "rewards/rejected": -157.07174682617188,
1494
+ "step": 980
1495
+ },
1496
+ {
1497
+ "epoch": 0.7770800627943485,
1498
+ "grad_norm": 18.79192365654695,
1499
+ "learning_rate": 7.201594655002458e-08,
1500
+ "logits/chosen": 5900.44482421875,
1501
+ "logits/rejected": 4868.0849609375,
1502
+ "logps/chosen": -349.3968811035156,
1503
+ "logps/rejected": -387.33416748046875,
1504
+ "loss": 0.6149,
1505
+ "rewards/accuracies": 0.73333340883255,
1506
+ "rewards/chosen": -81.28948974609375,
1507
+ "rewards/margins": 69.76005554199219,
1508
+ "rewards/rejected": -151.049560546875,
1509
+ "step": 990
1510
+ },
1511
+ {
1512
+ "epoch": 0.7849293563579278,
1513
+ "grad_norm": 18.79350845073137,
1514
+ "learning_rate": 6.727067196345099e-08,
1515
+ "logits/chosen": 5536.19873046875,
1516
+ "logits/rejected": 4639.8720703125,
1517
+ "logps/chosen": -336.35577392578125,
1518
+ "logps/rejected": -365.3442077636719,
1519
+ "loss": 0.6212,
1520
+ "rewards/accuracies": 0.7250000238418579,
1521
+ "rewards/chosen": -76.03428649902344,
1522
+ "rewards/margins": 63.63414764404297,
1523
+ "rewards/rejected": -139.66844177246094,
1524
+ "step": 1000
1525
+ },
1526
+ {
1527
+ "epoch": 0.792778649921507,
1528
+ "grad_norm": 15.409532424479464,
1529
+ "learning_rate": 6.26627103495786e-08,
1530
+ "logits/chosen": 5746.2666015625,
1531
+ "logits/rejected": 4735.36376953125,
1532
+ "logps/chosen": -329.68927001953125,
1533
+ "logps/rejected": -368.9176025390625,
1534
+ "loss": 0.624,
1535
+ "rewards/accuracies": 0.6583333015441895,
1536
+ "rewards/chosen": -70.27388763427734,
1537
+ "rewards/margins": 63.12858963012695,
1538
+ "rewards/rejected": -133.40248107910156,
1539
+ "step": 1010
1540
+ },
1541
+ {
1542
+ "epoch": 0.8006279434850864,
1543
+ "grad_norm": 13.475517503615837,
1544
+ "learning_rate": 5.8195524386862374e-08,
1545
+ "logits/chosen": 5811.63671875,
1546
+ "logits/rejected": 5106.11669921875,
1547
+ "logps/chosen": -357.29742431640625,
1548
+ "logps/rejected": -421.65594482421875,
1549
+ "loss": 0.614,
1550
+ "rewards/accuracies": 0.7916666865348816,
1551
+ "rewards/chosen": -59.400840759277344,
1552
+ "rewards/margins": 88.65455627441406,
1553
+ "rewards/rejected": -148.05538940429688,
1554
+ "step": 1020
1555
+ },
1556
+ {
1557
+ "epoch": 0.8084772370486656,
1558
+ "grad_norm": 18.09767323128694,
1559
+ "learning_rate": 5.38724709671092e-08,
1560
+ "logits/chosen": 6252.6279296875,
1561
+ "logits/rejected": 5865.5927734375,
1562
+ "logps/chosen": -347.6499328613281,
1563
+ "logps/rejected": -426.4112854003906,
1564
+ "loss": 0.6117,
1565
+ "rewards/accuracies": 0.800000011920929,
1566
+ "rewards/chosen": -69.84974670410156,
1567
+ "rewards/margins": 81.45121765136719,
1568
+ "rewards/rejected": -151.30096435546875,
1569
+ "step": 1030
1570
+ },
1571
+ {
1572
+ "epoch": 0.8163265306122449,
1573
+ "grad_norm": 15.841210395276628,
1574
+ "learning_rate": 4.969679867292276e-08,
1575
+ "logits/chosen": 5529.40673828125,
1576
+ "logits/rejected": 4980.63818359375,
1577
+ "logps/chosen": -338.6473388671875,
1578
+ "logps/rejected": -407.2497253417969,
1579
+ "loss": 0.6156,
1580
+ "rewards/accuracies": 0.7500000596046448,
1581
+ "rewards/chosen": -73.40410614013672,
1582
+ "rewards/margins": 80.27185821533203,
1583
+ "rewards/rejected": -153.6759490966797,
1584
+ "step": 1040
1585
+ },
1586
+ {
1587
+ "epoch": 0.8241758241758241,
1588
+ "grad_norm": 16.846051622731085,
1589
+ "learning_rate": 4.5671645336537416e-08,
1590
+ "logits/chosen": 5591.8466796875,
1591
+ "logits/rejected": 5026.0830078125,
1592
+ "logps/chosen": -353.8576965332031,
1593
+ "logps/rejected": -416.2503967285156,
1594
+ "loss": 0.612,
1595
+ "rewards/accuracies": 0.75,
1596
+ "rewards/chosen": -72.3245620727539,
1597
+ "rewards/margins": 78.2017593383789,
1598
+ "rewards/rejected": -150.5263214111328,
1599
+ "step": 1050
1600
+ },
1601
+ {
1602
+ "epoch": 0.8320251177394035,
1603
+ "grad_norm": 45.4415767546636,
1604
+ "learning_rate": 4.180003568187776e-08,
1605
+ "logits/chosen": 6939.8369140625,
1606
+ "logits/rejected": 5414.35107421875,
1607
+ "logps/chosen": -385.07904052734375,
1608
+ "logps/rejected": -401.9789733886719,
1609
+ "loss": 0.6282,
1610
+ "rewards/accuracies": 0.6916666626930237,
1611
+ "rewards/chosen": -77.1563491821289,
1612
+ "rewards/margins": 60.28764724731445,
1613
+ "rewards/rejected": -137.44400024414062,
1614
+ "step": 1060
1615
+ },
1616
+ {
1617
+ "epoch": 0.8398744113029827,
1618
+ "grad_norm": 18.747827810509367,
1619
+ "learning_rate": 3.8084879051612144e-08,
1620
+ "logits/chosen": 5741.5634765625,
1621
+ "logits/rejected": 5204.7333984375,
1622
+ "logps/chosen": -347.3013916015625,
1623
+ "logps/rejected": -386.94561767578125,
1624
+ "loss": 0.6164,
1625
+ "rewards/accuracies": 0.7750000357627869,
1626
+ "rewards/chosen": -74.4090576171875,
1627
+ "rewards/margins": 75.30126953125,
1628
+ "rewards/rejected": -149.7103271484375,
1629
+ "step": 1070
1630
+ },
1631
+ {
1632
+ "epoch": 0.847723704866562,
1633
+ "grad_norm": 12.659356648082168,
1634
+ "learning_rate": 3.452896722091128e-08,
1635
+ "logits/chosen": 6310.4208984375,
1636
+ "logits/rejected": 4834.76171875,
1637
+ "logps/chosen": -383.05096435546875,
1638
+ "logps/rejected": -395.0693359375,
1639
+ "loss": 0.6029,
1640
+ "rewards/accuracies": 0.8083333969116211,
1641
+ "rewards/chosen": -70.56317901611328,
1642
+ "rewards/margins": 83.26502990722656,
1643
+ "rewards/rejected": -153.82821655273438,
1644
+ "step": 1080
1645
+ },
1646
+ {
1647
+ "epoch": 0.8555729984301413,
1648
+ "grad_norm": 16.859762113459805,
1649
+ "learning_rate": 3.11349722995527e-08,
1650
+ "logits/chosen": 6297.42236328125,
1651
+ "logits/rejected": 4726.97802734375,
1652
+ "logps/chosen": -357.27203369140625,
1653
+ "logps/rejected": -393.133056640625,
1654
+ "loss": 0.6114,
1655
+ "rewards/accuracies": 0.7166666984558105,
1656
+ "rewards/chosen": -83.47435760498047,
1657
+ "rewards/margins": 59.989906311035156,
1658
+ "rewards/rejected": -143.46426391601562,
1659
+ "step": 1090
1660
+ },
1661
+ {
1662
+ "epoch": 0.8634222919937206,
1663
+ "grad_norm": 14.876276968043816,
1664
+ "learning_rate": 2.7905444723949762e-08,
1665
+ "logits/chosen": 6136.54248046875,
1666
+ "logits/rejected": 5038.2431640625,
1667
+ "logps/chosen": -369.5342712402344,
1668
+ "logps/rejected": -407.952392578125,
1669
+ "loss": 0.6182,
1670
+ "rewards/accuracies": 0.7666666507720947,
1671
+ "rewards/chosen": -86.31148529052734,
1672
+ "rewards/margins": 89.53190612792969,
1673
+ "rewards/rejected": -175.84341430664062,
1674
+ "step": 1100
1675
+ },
1676
+ {
1677
+ "epoch": 0.8712715855572999,
1678
+ "grad_norm": 23.19077581996903,
1679
+ "learning_rate": 2.484281134061142e-08,
1680
+ "logits/chosen": 6493.39794921875,
1681
+ "logits/rejected": 5203.970703125,
1682
+ "logps/chosen": -395.83636474609375,
1683
+ "logps/rejected": -427.874267578125,
1684
+ "loss": 0.616,
1685
+ "rewards/accuracies": 0.7833333015441895,
1686
+ "rewards/chosen": -86.56200408935547,
1687
+ "rewards/margins": 78.59150695800781,
1688
+ "rewards/rejected": -165.1535186767578,
1689
+ "step": 1110
1690
+ },
1691
+ {
1692
+ "epoch": 0.8791208791208791,
1693
+ "grad_norm": 20.803959092397093,
1694
+ "learning_rate": 2.194937358247506e-08,
1695
+ "logits/chosen": 6390.1259765625,
1696
+ "logits/rejected": 5163.4169921875,
1697
+ "logps/chosen": -380.3614807128906,
1698
+ "logps/rejected": -423.82916259765625,
1699
+ "loss": 0.613,
1700
+ "rewards/accuracies": 0.7583333253860474,
1701
+ "rewards/chosen": -89.02333068847656,
1702
+ "rewards/margins": 75.32238006591797,
1703
+ "rewards/rejected": -164.34573364257812,
1704
+ "step": 1120
1705
+ },
1706
+ {
1707
+ "epoch": 0.8869701726844584,
1708
+ "grad_norm": 18.963504933195512,
1709
+ "learning_rate": 1.9227305739481612e-08,
1710
+ "logits/chosen": 5820.75146484375,
1711
+ "logits/rejected": 4510.7939453125,
1712
+ "logps/chosen": -349.5916442871094,
1713
+ "logps/rejected": -381.07916259765625,
1714
+ "loss": 0.6091,
1715
+ "rewards/accuracies": 0.7833333015441895,
1716
+ "rewards/chosen": -71.02159118652344,
1717
+ "rewards/margins": 85.45536804199219,
1718
+ "rewards/rejected": -156.47695922851562,
1719
+ "step": 1130
1720
+ },
1721
+ {
1722
+ "epoch": 0.8948194662480377,
1723
+ "grad_norm": 19.01457656059988,
1724
+ "learning_rate": 1.6678653324693787e-08,
1725
+ "logits/chosen": 6429.29443359375,
1726
+ "logits/rejected": 5148.3701171875,
1727
+ "logps/chosen": -384.94915771484375,
1728
+ "logps/rejected": -422.2733459472656,
1729
+ "loss": 0.6034,
1730
+ "rewards/accuracies": 0.7666667103767395,
1731
+ "rewards/chosen": -79.50971984863281,
1732
+ "rewards/margins": 81.15669250488281,
1733
+ "rewards/rejected": -160.66641235351562,
1734
+ "step": 1140
1735
+ },
1736
+ {
1737
+ "epoch": 0.902668759811617,
1738
+ "grad_norm": 12.376640085144242,
1739
+ "learning_rate": 1.4305331537183384e-08,
1740
+ "logits/chosen": 5704.4609375,
1741
+ "logits/rejected": 5148.77978515625,
1742
+ "logps/chosen": -352.7065124511719,
1743
+ "logps/rejected": -419.0628356933594,
1744
+ "loss": 0.6087,
1745
+ "rewards/accuracies": 0.6833333373069763,
1746
+ "rewards/chosen": -85.51119232177734,
1747
+ "rewards/margins": 70.08112335205078,
1748
+ "rewards/rejected": -155.59231567382812,
1749
+ "step": 1150
1750
+ },
1751
+ {
1752
+ "epoch": 0.9105180533751962,
1753
+ "grad_norm": 17.251075451707592,
1754
+ "learning_rate": 1.2109123822844653e-08,
1755
+ "logits/chosen": 5839.08251953125,
1756
+ "logits/rejected": 4554.01220703125,
1757
+ "logps/chosen": -359.0191955566406,
1758
+ "logps/rejected": -391.0977783203125,
1759
+ "loss": 0.6133,
1760
+ "rewards/accuracies": 0.783333420753479,
1761
+ "rewards/chosen": -88.34132385253906,
1762
+ "rewards/margins": 68.73795318603516,
1763
+ "rewards/rejected": -157.07925415039062,
1764
+ "step": 1160
1765
+ },
1766
+ {
1767
+ "epoch": 0.9183673469387755,
1768
+ "grad_norm": 30.790909367368283,
1769
+ "learning_rate": 1.0091680534213387e-08,
1770
+ "logits/chosen": 6360.50146484375,
1771
+ "logits/rejected": 6086.1513671875,
1772
+ "logps/chosen": -374.38970947265625,
1773
+ "logps/rejected": -467.6603088378906,
1774
+ "loss": 0.6196,
1775
+ "rewards/accuracies": 0.7416666746139526,
1776
+ "rewards/chosen": -82.26263427734375,
1777
+ "rewards/margins": 81.5895767211914,
1778
+ "rewards/rejected": -163.85220336914062,
1779
+ "step": 1170
1780
+ },
1781
+ {
1782
+ "epoch": 0.9262166405023547,
1783
+ "grad_norm": 20.905568866608686,
1784
+ "learning_rate": 8.254517690300944e-09,
1785
+ "logits/chosen": 5604.05419921875,
1786
+ "logits/rejected": 4998.599609375,
1787
+ "logps/chosen": -350.8424377441406,
1788
+ "logps/rejected": -412.19940185546875,
1789
+ "loss": 0.6124,
1790
+ "rewards/accuracies": 0.7749999761581421,
1791
+ "rewards/chosen": -71.8908920288086,
1792
+ "rewards/margins": 81.49540710449219,
1793
+ "rewards/rejected": -153.3863067626953,
1794
+ "step": 1180
1795
+ },
1796
+ {
1797
+ "epoch": 0.9340659340659341,
1798
+ "grad_norm": 10.88103318658427,
1799
+ "learning_rate": 6.599015837372907e-09,
1800
+ "logits/chosen": 6126.52734375,
1801
+ "logits/rejected": 5268.48828125,
1802
+ "logps/chosen": -392.8667907714844,
1803
+ "logps/rejected": -439.15972900390625,
1804
+ "loss": 0.6196,
1805
+ "rewards/accuracies": 0.7083333730697632,
1806
+ "rewards/chosen": -100.54813385009766,
1807
+ "rewards/margins": 74.77506256103516,
1808
+ "rewards/rejected": -175.32318115234375,
1809
+ "step": 1190
1810
+ },
1811
+ {
1812
+ "epoch": 0.9419152276295133,
1813
+ "grad_norm": 20.539083448288594,
1814
+ "learning_rate": 5.126419011529992e-09,
1815
+ "logits/chosen": 6356.4951171875,
1816
+ "logits/rejected": 5332.37353515625,
1817
+ "logps/chosen": -379.75885009765625,
1818
+ "logps/rejected": -432.0904846191406,
1819
+ "loss": 0.6032,
1820
+ "rewards/accuracies": 0.8666666150093079,
1821
+ "rewards/chosen": -75.01070404052734,
1822
+ "rewards/margins": 98.93077850341797,
1823
+ "rewards/rejected": -173.9414825439453,
1824
+ "step": 1200
1825
+ },
1826
+ {
1827
+ "epoch": 0.9497645211930926,
1828
+ "grad_norm": 20.433280187267762,
1829
+ "learning_rate": 3.837833803870177e-09,
1830
+ "logits/chosen": 5961.4970703125,
1831
+ "logits/rejected": 5186.04833984375,
1832
+ "logps/chosen": -368.67034912109375,
1833
+ "logps/rejected": -424.91131591796875,
1834
+ "loss": 0.6183,
1835
+ "rewards/accuracies": 0.7500000596046448,
1836
+ "rewards/chosen": -88.86743927001953,
1837
+ "rewards/margins": 83.7270736694336,
1838
+ "rewards/rejected": -172.59451293945312,
1839
+ "step": 1210
1840
+ },
1841
+ {
1842
+ "epoch": 0.957613814756672,
1843
+ "grad_norm": 25.913384367594333,
1844
+ "learning_rate": 2.734228528934679e-09,
1845
+ "logits/chosen": 7407.4306640625,
1846
+ "logits/rejected": 5385.08544921875,
1847
+ "logps/chosen": -437.97711181640625,
1848
+ "logps/rejected": -454.0513610839844,
1849
+ "loss": 0.6148,
1850
+ "rewards/accuracies": 0.7416666746139526,
1851
+ "rewards/chosen": -91.56160736083984,
1852
+ "rewards/margins": 77.19084167480469,
1853
+ "rewards/rejected": -168.75247192382812,
1854
+ "step": 1220
1855
+ },
1856
+ {
1857
+ "epoch": 0.9654631083202512,
1858
+ "grad_norm": 18.893977958471503,
1859
+ "learning_rate": 1.8164324970625645e-09,
1860
+ "logits/chosen": 6518.923828125,
1861
+ "logits/rejected": 5050.20166015625,
1862
+ "logps/chosen": -388.9313659667969,
1863
+ "logps/rejected": -423.03558349609375,
1864
+ "loss": 0.6311,
1865
+ "rewards/accuracies": 0.7583333253860474,
1866
+ "rewards/chosen": -80.57595825195312,
1867
+ "rewards/margins": 77.39918518066406,
1868
+ "rewards/rejected": -157.9751739501953,
1869
+ "step": 1230
1870
+ },
1871
+ {
1872
+ "epoch": 0.9733124018838305,
1873
+ "grad_norm": 16.390918429518635,
1874
+ "learning_rate": 1.0851353912008642e-09,
1875
+ "logits/chosen": 5605.1982421875,
1876
+ "logits/rejected": 5138.8681640625,
1877
+ "logps/chosen": -363.85174560546875,
1878
+ "logps/rejected": -445.0411682128906,
1879
+ "loss": 0.6098,
1880
+ "rewards/accuracies": 0.7666667103767395,
1881
+ "rewards/chosen": -90.89818572998047,
1882
+ "rewards/margins": 77.92682647705078,
1883
+ "rewards/rejected": -168.8250274658203,
1884
+ "step": 1240
1885
+ },
1886
+ {
1887
+ "epoch": 0.9811616954474097,
1888
+ "grad_norm": 13.229811746138825,
1889
+ "learning_rate": 5.408867486384471e-10,
1890
+ "logits/chosen": 5726.5830078125,
1891
+ "logits/rejected": 4779.26123046875,
1892
+ "logps/chosen": -346.5870361328125,
1893
+ "logps/rejected": -380.5937805175781,
1894
+ "loss": 0.6114,
1895
+ "rewards/accuracies": 0.7833333015441895,
1896
+ "rewards/chosen": -76.1484375,
1897
+ "rewards/margins": 81.09263610839844,
1898
+ "rewards/rejected": -157.24107360839844,
1899
+ "step": 1250
1900
+ },
1901
+ {
1902
+ "epoch": 0.989010989010989,
1903
+ "grad_norm": 23.115150939597314,
1904
+ "learning_rate": 1.840955480532924e-10,
1905
+ "logits/chosen": 5498.7197265625,
1906
+ "logits/rejected": 5114.80615234375,
1907
+ "logps/chosen": -348.0476989746094,
1908
+ "logps/rejected": -414.744140625,
1909
+ "loss": 0.6073,
1910
+ "rewards/accuracies": 0.7583333253860474,
1911
+ "rewards/chosen": -81.39493560791016,
1912
+ "rewards/margins": 75.64277648925781,
1913
+ "rewards/rejected": -157.0377197265625,
1914
+ "step": 1260
1915
+ },
1916
+ {
1917
+ "epoch": 0.9968602825745683,
1918
+ "grad_norm": 17.978099246101902,
1919
+ "learning_rate": 1.502990218302247e-11,
1920
+ "logits/chosen": 5703.56787109375,
1921
+ "logits/rejected": 4572.5458984375,
1922
+ "logps/chosen": -350.7594299316406,
1923
+ "logps/rejected": -395.73187255859375,
1924
+ "loss": 0.6146,
1925
+ "rewards/accuracies": 0.8083332777023315,
1926
+ "rewards/chosen": -89.28590393066406,
1927
+ "rewards/margins": 78.2876968383789,
1928
+ "rewards/rejected": -167.5736083984375,
1929
+ "step": 1270
1930
+ },
1931
+ {
1932
+ "epoch": 1.0,
1933
+ "step": 1274,
1934
+ "total_flos": 0.0,
1935
+ "train_loss": 0.6310614222072919,
1936
+ "train_runtime": 13007.3728,
1937
+ "train_samples_per_second": 4.7,
1938
+ "train_steps_per_second": 0.098
1939
+ }
1940
+ ],
1941
+ "logging_steps": 10,
1942
+ "max_steps": 1274,
1943
+ "num_input_tokens_seen": 0,
1944
+ "num_train_epochs": 1,
1945
+ "save_steps": 2000,
1946
+ "stateful_callbacks": {
1947
+ "TrainerControl": {
1948
+ "args": {
1949
+ "should_epoch_stop": false,
1950
+ "should_evaluate": false,
1951
+ "should_log": false,
1952
+ "should_save": false,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42cbf7f7de8b9aee43144201688c9e486c674c719d9f674723572bd424291b6
3
+ size 7352