Teng Xiao commited on
Commit
8e31bec
1 Parent(s): 2a4b6eb
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: alignment-handbook/zephyr-7b-sft-full
4
+ tags:
5
+ - alignment_handbook-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - HuggingFaceH4/ultrafeedback_binarized
9
+ model-index:
10
+ - name: zephyr-7b-MI-1-SELM
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # zephyr-7b-MI-1-SELM
18
+
19
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-07
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 16
45
+ - total_train_batch_size: 128
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 1
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.40.2
59
+ - Pytorch 2.1.2+cu121
60
+ - Datasets 2.14.6
61
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.998691442030882,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.8644854217705238,
5
+ "train_runtime": 7378.4782,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 8.286,
8
+ "train_steps_per_second": 0.065
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": "4.40.2",
24
+ "use_cache": true,
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": "4.40.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba08b20ac19ebf2b0d987ec66eaad2eda40493e5df15cf4f39139d09b6179a38
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21104ec7d9121ce0992c1759ff5ec736484b32277a8d683bc87e69814175007e
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da6e5cac8df15c7062836ee413b92ea1fc71979d1b663c81022fd832319d0cd
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": 0.998691442030882,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.8644854217705238,
5
+ "train_runtime": 7378.4782,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 8.286,
8
+ "train_steps_per_second": 0.065
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1455 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.998691442030882,
5
+ "eval_steps": 500,
6
+ "global_step": 477,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010468463752944255,
13
+ "grad_norm": 15.141688725114767,
14
+ "learning_rate": 5.208333333333333e-08,
15
+ "logits/chosen": -2.770766496658325,
16
+ "logits/rejected": -2.728191375732422,
17
+ "logps/chosen": -1.027971625328064,
18
+ "logps/rejected": -1.1730705499649048,
19
+ "loss": 2.0284,
20
+ "rewards/accuracies": 0.581250011920929,
21
+ "rewards/chosen": -1.027971625328064,
22
+ "rewards/margins": 0.14509883522987366,
23
+ "rewards/rejected": -1.1730705499649048,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.02093692750588851,
28
+ "grad_norm": 13.969517964651633,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -2.7511062622070312,
31
+ "logits/rejected": -2.7253737449645996,
32
+ "logps/chosen": -0.9954013824462891,
33
+ "logps/rejected": -1.0719196796417236,
34
+ "loss": 2.002,
35
+ "rewards/accuracies": 0.5,
36
+ "rewards/chosen": -0.9954013824462891,
37
+ "rewards/margins": 0.07651824504137039,
38
+ "rewards/rejected": -1.0719196796417236,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.031405391258832765,
43
+ "grad_norm": 13.915856984059875,
44
+ "learning_rate": 1.5624999999999999e-07,
45
+ "logits/chosen": -2.7306742668151855,
46
+ "logits/rejected": -2.697096347808838,
47
+ "logps/chosen": -0.9895243644714355,
48
+ "logps/rejected": -1.147679328918457,
49
+ "loss": 1.9874,
50
+ "rewards/accuracies": 0.643750011920929,
51
+ "rewards/chosen": -0.9895243644714355,
52
+ "rewards/margins": 0.15815496444702148,
53
+ "rewards/rejected": -1.147679328918457,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.04187385501177702,
58
+ "grad_norm": 13.588156017248505,
59
+ "learning_rate": 2.0833333333333333e-07,
60
+ "logits/chosen": -2.8030834197998047,
61
+ "logits/rejected": -2.709643602371216,
62
+ "logps/chosen": -1.0228091478347778,
63
+ "logps/rejected": -1.1238880157470703,
64
+ "loss": 2.0265,
65
+ "rewards/accuracies": 0.550000011920929,
66
+ "rewards/chosen": -1.0228091478347778,
67
+ "rewards/margins": 0.10107902437448502,
68
+ "rewards/rejected": -1.1238880157470703,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.05234231876472128,
73
+ "grad_norm": 14.042807702810773,
74
+ "learning_rate": 2.604166666666667e-07,
75
+ "logits/chosen": -2.7991013526916504,
76
+ "logits/rejected": -2.7758243083953857,
77
+ "logps/chosen": -1.0302048921585083,
78
+ "logps/rejected": -1.086944818496704,
79
+ "loss": 2.0091,
80
+ "rewards/accuracies": 0.5249999761581421,
81
+ "rewards/chosen": -1.0302048921585083,
82
+ "rewards/margins": 0.05673985555768013,
83
+ "rewards/rejected": -1.086944818496704,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06281078251766553,
88
+ "grad_norm": 15.069602245174066,
89
+ "learning_rate": 3.1249999999999997e-07,
90
+ "logits/chosen": -2.7733917236328125,
91
+ "logits/rejected": -2.7317938804626465,
92
+ "logps/chosen": -0.9855572581291199,
93
+ "logps/rejected": -1.0908451080322266,
94
+ "loss": 2.0118,
95
+ "rewards/accuracies": 0.5375000238418579,
96
+ "rewards/chosen": -0.9855572581291199,
97
+ "rewards/margins": 0.1052878275513649,
98
+ "rewards/rejected": -1.0908451080322266,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07327924627060979,
103
+ "grad_norm": 14.14588992747414,
104
+ "learning_rate": 3.645833333333333e-07,
105
+ "logits/chosen": -2.7773802280426025,
106
+ "logits/rejected": -2.6910452842712402,
107
+ "logps/chosen": -1.0310332775115967,
108
+ "logps/rejected": -1.1711452007293701,
109
+ "loss": 1.9903,
110
+ "rewards/accuracies": 0.581250011920929,
111
+ "rewards/chosen": -1.0310332775115967,
112
+ "rewards/margins": 0.1401120126247406,
113
+ "rewards/rejected": -1.1711452007293701,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08374771002355404,
118
+ "grad_norm": 20.106972236529245,
119
+ "learning_rate": 4.1666666666666667e-07,
120
+ "logits/chosen": -2.7931580543518066,
121
+ "logits/rejected": -2.6956787109375,
122
+ "logps/chosen": -1.011854887008667,
123
+ "logps/rejected": -1.2990570068359375,
124
+ "loss": 1.9463,
125
+ "rewards/accuracies": 0.668749988079071,
126
+ "rewards/chosen": -1.011854887008667,
127
+ "rewards/margins": 0.28720206022262573,
128
+ "rewards/rejected": -1.2990570068359375,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.0942161737764983,
133
+ "grad_norm": 15.19327904046142,
134
+ "learning_rate": 4.6874999999999996e-07,
135
+ "logits/chosen": -2.8017444610595703,
136
+ "logits/rejected": -2.7550606727600098,
137
+ "logps/chosen": -0.9639647603034973,
138
+ "logps/rejected": -1.142878770828247,
139
+ "loss": 1.9512,
140
+ "rewards/accuracies": 0.550000011920929,
141
+ "rewards/chosen": -0.9639647603034973,
142
+ "rewards/margins": 0.17891402542591095,
143
+ "rewards/rejected": -1.142878770828247,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.10468463752944256,
148
+ "grad_norm": 20.91684390311358,
149
+ "learning_rate": 4.999731868769026e-07,
150
+ "logits/chosen": -2.7584781646728516,
151
+ "logits/rejected": -2.6904306411743164,
152
+ "logps/chosen": -1.0117145776748657,
153
+ "logps/rejected": -1.30343496799469,
154
+ "loss": 1.9653,
155
+ "rewards/accuracies": 0.6000000238418579,
156
+ "rewards/chosen": -1.0117145776748657,
157
+ "rewards/margins": 0.2917203903198242,
158
+ "rewards/rejected": -1.30343496799469,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11515310128238682,
163
+ "grad_norm": 16.247858117319236,
164
+ "learning_rate": 4.996716052911017e-07,
165
+ "logits/chosen": -2.754804849624634,
166
+ "logits/rejected": -2.71933650970459,
167
+ "logps/chosen": -1.0166981220245361,
168
+ "logps/rejected": -1.268345832824707,
169
+ "loss": 1.9611,
170
+ "rewards/accuracies": 0.5375000238418579,
171
+ "rewards/chosen": -1.0166981220245361,
172
+ "rewards/margins": 0.25164780020713806,
173
+ "rewards/rejected": -1.268345832824707,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.12562156503533106,
178
+ "grad_norm": 16.39781017532518,
179
+ "learning_rate": 4.990353313429303e-07,
180
+ "logits/chosen": -2.8165841102600098,
181
+ "logits/rejected": -2.7710437774658203,
182
+ "logps/chosen": -1.049938440322876,
183
+ "logps/rejected": -1.2433346509933472,
184
+ "loss": 1.9164,
185
+ "rewards/accuracies": 0.6187499761581421,
186
+ "rewards/chosen": -1.049938440322876,
187
+ "rewards/margins": 0.19339624047279358,
188
+ "rewards/rejected": -1.2433346509933472,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.1360900287882753,
193
+ "grad_norm": 15.239254500208718,
194
+ "learning_rate": 4.980652179769217e-07,
195
+ "logits/chosen": -2.8142337799072266,
196
+ "logits/rejected": -2.6995322704315186,
197
+ "logps/chosen": -1.0191227197647095,
198
+ "logps/rejected": -1.544886827468872,
199
+ "loss": 1.9025,
200
+ "rewards/accuracies": 0.706250011920929,
201
+ "rewards/chosen": -1.0191227197647095,
202
+ "rewards/margins": 0.5257640480995178,
203
+ "rewards/rejected": -1.544886827468872,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.14655849254121958,
208
+ "grad_norm": 21.0566472158153,
209
+ "learning_rate": 4.967625656594781e-07,
210
+ "logits/chosen": -2.7174973487854004,
211
+ "logits/rejected": -2.6667487621307373,
212
+ "logps/chosen": -1.0492310523986816,
213
+ "logps/rejected": -1.3482974767684937,
214
+ "loss": 1.9091,
215
+ "rewards/accuracies": 0.5874999761581421,
216
+ "rewards/chosen": -1.0492310523986816,
217
+ "rewards/margins": 0.2990665137767792,
218
+ "rewards/rejected": -1.3482974767684937,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.15702695629416383,
223
+ "grad_norm": 30.761967865275885,
224
+ "learning_rate": 4.951291206355559e-07,
225
+ "logits/chosen": -2.773061752319336,
226
+ "logits/rejected": -2.698946952819824,
227
+ "logps/chosen": -0.9925507307052612,
228
+ "logps/rejected": -1.3563807010650635,
229
+ "loss": 1.8891,
230
+ "rewards/accuracies": 0.625,
231
+ "rewards/chosen": -0.9925507307052612,
232
+ "rewards/margins": 0.36382991075515747,
233
+ "rewards/rejected": -1.3563807010650635,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.16749542004710807,
238
+ "grad_norm": 31.297744502118277,
239
+ "learning_rate": 4.93167072587771e-07,
240
+ "logits/chosen": -2.738257884979248,
241
+ "logits/rejected": -2.6784729957580566,
242
+ "logps/chosen": -1.0087690353393555,
243
+ "logps/rejected": -1.4246900081634521,
244
+ "loss": 1.9382,
245
+ "rewards/accuracies": 0.668749988079071,
246
+ "rewards/chosen": -1.0087690353393555,
247
+ "rewards/margins": 0.4159211218357086,
248
+ "rewards/rejected": -1.4246900081634521,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.17796388380005235,
253
+ "grad_norm": 24.407477818447635,
254
+ "learning_rate": 4.908790517010636e-07,
255
+ "logits/chosen": -2.747776508331299,
256
+ "logits/rejected": -2.7003962993621826,
257
+ "logps/chosen": -0.9973554611206055,
258
+ "logps/rejected": -1.3728947639465332,
259
+ "loss": 1.9613,
260
+ "rewards/accuracies": 0.606249988079071,
261
+ "rewards/chosen": -0.9973554611206055,
262
+ "rewards/margins": 0.3755393624305725,
263
+ "rewards/rejected": -1.3728947639465332,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.1884323475529966,
268
+ "grad_norm": 31.20847987328103,
269
+ "learning_rate": 4.882681251368548e-07,
270
+ "logits/chosen": -2.705894708633423,
271
+ "logits/rejected": -2.6819891929626465,
272
+ "logps/chosen": -1.0237383842468262,
273
+ "logps/rejected": -1.404168725013733,
274
+ "loss": 1.88,
275
+ "rewards/accuracies": 0.675000011920929,
276
+ "rewards/chosen": -1.0237383842468262,
277
+ "rewards/margins": 0.3804302513599396,
278
+ "rewards/rejected": -1.404168725013733,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.19890081130594087,
283
+ "grad_norm": 30.65914852598083,
284
+ "learning_rate": 4.853377929214243e-07,
285
+ "logits/chosen": -2.776717185974121,
286
+ "logits/rejected": -2.6825289726257324,
287
+ "logps/chosen": -1.038529872894287,
288
+ "logps/rejected": -1.3572471141815186,
289
+ "loss": 1.9062,
290
+ "rewards/accuracies": 0.581250011920929,
291
+ "rewards/chosen": -1.038529872894287,
292
+ "rewards/margins": 0.31871724128723145,
293
+ "rewards/rejected": -1.3572471141815186,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.2093692750588851,
298
+ "grad_norm": 34.08856475096774,
299
+ "learning_rate": 4.820919832540181e-07,
300
+ "logits/chosen": -2.74165678024292,
301
+ "logits/rejected": -2.6503825187683105,
302
+ "logps/chosen": -1.051953673362732,
303
+ "logps/rejected": -1.4617860317230225,
304
+ "loss": 1.9147,
305
+ "rewards/accuracies": 0.581250011920929,
306
+ "rewards/chosen": -1.051953673362732,
307
+ "rewards/margins": 0.4098321497440338,
308
+ "rewards/rejected": -1.4617860317230225,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.21983773881182936,
313
+ "grad_norm": 28.24345375738832,
314
+ "learning_rate": 4.785350472409791e-07,
315
+ "logits/chosen": -2.743473529815674,
316
+ "logits/rejected": -2.7197020053863525,
317
+ "logps/chosen": -0.931172251701355,
318
+ "logps/rejected": -1.453914999961853,
319
+ "loss": 1.8781,
320
+ "rewards/accuracies": 0.6812499761581421,
321
+ "rewards/chosen": -0.931172251701355,
322
+ "rewards/margins": 0.522742748260498,
323
+ "rewards/rejected": -1.453914999961853,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23030620256477363,
328
+ "grad_norm": 35.845899664243596,
329
+ "learning_rate": 4.7467175306295647e-07,
330
+ "logits/chosen": -2.817007064819336,
331
+ "logits/rejected": -2.762336254119873,
332
+ "logps/chosen": -1.0500761270523071,
333
+ "logps/rejected": -1.4565006494522095,
334
+ "loss": 1.88,
335
+ "rewards/accuracies": 0.6312500238418579,
336
+ "rewards/chosen": -1.0500761270523071,
337
+ "rewards/margins": 0.40642452239990234,
338
+ "rewards/rejected": -1.4565006494522095,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.24077466631771788,
343
+ "grad_norm": 23.382933706781618,
344
+ "learning_rate": 4.70507279583015e-07,
345
+ "logits/chosen": -2.7697396278381348,
346
+ "logits/rejected": -2.710322856903076,
347
+ "logps/chosen": -1.0177266597747803,
348
+ "logps/rejected": -1.5666338205337524,
349
+ "loss": 1.868,
350
+ "rewards/accuracies": 0.71875,
351
+ "rewards/chosen": -1.0177266597747803,
352
+ "rewards/margins": 0.5489073991775513,
353
+ "rewards/rejected": -1.5666338205337524,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2512431300706621,
358
+ "grad_norm": 29.59771539393517,
359
+ "learning_rate": 4.6604720940421207e-07,
360
+ "logits/chosen": -2.7786221504211426,
361
+ "logits/rejected": -2.737684965133667,
362
+ "logps/chosen": -1.0584137439727783,
363
+ "logps/rejected": -1.4742605686187744,
364
+ "loss": 1.9062,
365
+ "rewards/accuracies": 0.6312500238418579,
366
+ "rewards/chosen": -1.0584137439727783,
367
+ "rewards/margins": 0.41584667563438416,
368
+ "rewards/rejected": -1.4742605686187744,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.26171159382360637,
373
+ "grad_norm": 24.555574989451102,
374
+ "learning_rate": 4.612975213859487e-07,
375
+ "logits/chosen": -2.8200080394744873,
376
+ "logits/rejected": -2.7997546195983887,
377
+ "logps/chosen": -1.058563470840454,
378
+ "logps/rejected": -1.3519017696380615,
379
+ "loss": 1.9069,
380
+ "rewards/accuracies": 0.574999988079071,
381
+ "rewards/chosen": -1.058563470840454,
382
+ "rewards/margins": 0.29333844780921936,
383
+ "rewards/rejected": -1.3519017696380615,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.2721800575765506,
388
+ "grad_norm": 26.634009671559898,
389
+ "learning_rate": 4.5626458262912735e-07,
390
+ "logits/chosen": -2.788752794265747,
391
+ "logits/rejected": -2.754631519317627,
392
+ "logps/chosen": -1.0312286615371704,
393
+ "logps/rejected": -1.2794463634490967,
394
+ "loss": 1.8977,
395
+ "rewards/accuracies": 0.59375,
396
+ "rewards/chosen": -1.0312286615371704,
397
+ "rewards/margins": 0.24821774661540985,
398
+ "rewards/rejected": -1.2794463634490967,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.2826485213294949,
403
+ "grad_norm": 32.240888174368,
404
+ "learning_rate": 4.5095513994085974e-07,
405
+ "logits/chosen": -2.7877840995788574,
406
+ "logits/rejected": -2.7001712322235107,
407
+ "logps/chosen": -1.0880383253097534,
408
+ "logps/rejected": -1.7845348119735718,
409
+ "loss": 1.8912,
410
+ "rewards/accuracies": 0.731249988079071,
411
+ "rewards/chosen": -1.0880383253097534,
412
+ "rewards/margins": 0.696496307849884,
413
+ "rewards/rejected": -1.7845348119735718,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.29311698508243916,
418
+ "grad_norm": 25.76204815720163,
419
+ "learning_rate": 4.453763107901675e-07,
420
+ "logits/chosen": -2.8313488960266113,
421
+ "logits/rejected": -2.780134677886963,
422
+ "logps/chosen": -0.9982128143310547,
423
+ "logps/rejected": -1.4504693746566772,
424
+ "loss": 1.8155,
425
+ "rewards/accuracies": 0.6937500238418579,
426
+ "rewards/chosen": -0.9982128143310547,
427
+ "rewards/margins": 0.4522566795349121,
428
+ "rewards/rejected": -1.4504693746566772,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.3035854488353834,
433
+ "grad_norm": 21.7794898263259,
434
+ "learning_rate": 4.395355737667985e-07,
435
+ "logits/chosen": -2.809255361557007,
436
+ "logits/rejected": -2.761308193206787,
437
+ "logps/chosen": -1.0206363201141357,
438
+ "logps/rejected": -1.419768214225769,
439
+ "loss": 1.8605,
440
+ "rewards/accuracies": 0.65625,
441
+ "rewards/chosen": -1.0206363201141357,
442
+ "rewards/margins": 0.39913198351860046,
443
+ "rewards/rejected": -1.419768214225769,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.31405391258832765,
448
+ "grad_norm": 26.507909597761785,
449
+ "learning_rate": 4.3344075855595097e-07,
450
+ "logits/chosen": -2.849714517593384,
451
+ "logits/rejected": -2.8313772678375244,
452
+ "logps/chosen": -0.9701302647590637,
453
+ "logps/rejected": -1.3971799612045288,
454
+ "loss": 1.8345,
455
+ "rewards/accuracies": 0.6000000238418579,
456
+ "rewards/chosen": -0.9701302647590637,
457
+ "rewards/margins": 0.42704978585243225,
458
+ "rewards/rejected": -1.3971799612045288,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.3245223763412719,
463
+ "grad_norm": 28.367719379820283,
464
+ "learning_rate": 4.271000354423425e-07,
465
+ "logits/chosen": -2.7890210151672363,
466
+ "logits/rejected": -2.757753849029541,
467
+ "logps/chosen": -1.0669995546340942,
468
+ "logps/rejected": -1.4297670125961304,
469
+ "loss": 1.894,
470
+ "rewards/accuracies": 0.643750011920929,
471
+ "rewards/chosen": -1.0669995546340942,
472
+ "rewards/margins": 0.36276736855506897,
473
+ "rewards/rejected": -1.4297670125961304,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.33499084009421615,
478
+ "grad_norm": 32.029509535293904,
479
+ "learning_rate": 4.2052190435769554e-07,
480
+ "logits/chosen": -2.7710726261138916,
481
+ "logits/rejected": -2.7451701164245605,
482
+ "logps/chosen": -1.0376036167144775,
483
+ "logps/rejected": -1.4104793071746826,
484
+ "loss": 1.8838,
485
+ "rewards/accuracies": 0.643750011920929,
486
+ "rewards/chosen": -1.0376036167144775,
487
+ "rewards/margins": 0.37287575006484985,
488
+ "rewards/rejected": -1.4104793071746826,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.34545930384716045,
493
+ "grad_norm": 25.20687040858121,
494
+ "learning_rate": 4.137151834863213e-07,
495
+ "logits/chosen": -2.7923319339752197,
496
+ "logits/rejected": -2.707219362258911,
497
+ "logps/chosen": -0.9815086126327515,
498
+ "logps/rejected": -1.4057986736297607,
499
+ "loss": 1.8435,
500
+ "rewards/accuracies": 0.625,
501
+ "rewards/chosen": -0.9815086126327515,
502
+ "rewards/margins": 0.4242900311946869,
503
+ "rewards/rejected": -1.4057986736297607,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3559277676001047,
508
+ "grad_norm": 28.006785803959723,
509
+ "learning_rate": 4.0668899744407567e-07,
510
+ "logits/chosen": -2.8175511360168457,
511
+ "logits/rejected": -2.752450466156006,
512
+ "logps/chosen": -1.0611494779586792,
513
+ "logps/rejected": -1.5021220445632935,
514
+ "loss": 1.8575,
515
+ "rewards/accuracies": 0.6499999761581421,
516
+ "rewards/chosen": -1.0611494779586792,
517
+ "rewards/margins": 0.4409725069999695,
518
+ "rewards/rejected": -1.5021220445632935,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.36639623135304894,
523
+ "grad_norm": 25.596200434230976,
524
+ "learning_rate": 3.994527650465352e-07,
525
+ "logits/chosen": -2.7964577674865723,
526
+ "logits/rejected": -2.709230661392212,
527
+ "logps/chosen": -1.1404192447662354,
528
+ "logps/rejected": -1.6063992977142334,
529
+ "loss": 1.9076,
530
+ "rewards/accuracies": 0.625,
531
+ "rewards/chosen": -1.1404192447662354,
532
+ "rewards/margins": 0.4659802317619324,
533
+ "rewards/rejected": -1.6063992977142334,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.3768646951059932,
538
+ "grad_norm": 25.892094106029592,
539
+ "learning_rate": 3.920161866827889e-07,
540
+ "logits/chosen": -2.7817273139953613,
541
+ "logits/rejected": -2.7617640495300293,
542
+ "logps/chosen": -1.0391079187393188,
543
+ "logps/rejected": -1.5876353979110718,
544
+ "loss": 1.8544,
545
+ "rewards/accuracies": 0.6875,
546
+ "rewards/chosen": -1.0391079187393188,
547
+ "rewards/margins": 0.5485275387763977,
548
+ "rewards/rejected": -1.5876353979110718,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.38733315885893743,
553
+ "grad_norm": 29.42463620034665,
554
+ "learning_rate": 3.8438923131177237e-07,
555
+ "logits/chosen": -2.7785096168518066,
556
+ "logits/rejected": -2.6860692501068115,
557
+ "logps/chosen": -1.0492454767227173,
558
+ "logps/rejected": -1.6226046085357666,
559
+ "loss": 1.8247,
560
+ "rewards/accuracies": 0.6625000238418579,
561
+ "rewards/chosen": -1.0492454767227173,
562
+ "rewards/margins": 0.573358952999115,
563
+ "rewards/rejected": -1.6226046085357666,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.39780162261188173,
568
+ "grad_norm": 27.921360264789193,
569
+ "learning_rate": 3.765821230985757e-07,
570
+ "logits/chosen": -2.7853875160217285,
571
+ "logits/rejected": -2.7454705238342285,
572
+ "logps/chosen": -1.0294712781906128,
573
+ "logps/rejected": -1.4654343128204346,
574
+ "loss": 1.9244,
575
+ "rewards/accuracies": 0.625,
576
+ "rewards/chosen": -1.0294712781906128,
577
+ "rewards/margins": 0.4359629154205322,
578
+ "rewards/rejected": -1.4654343128204346,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.408270086364826,
583
+ "grad_norm": 29.87078620394206,
584
+ "learning_rate": 3.6860532770864005e-07,
585
+ "logits/chosen": -2.701105833053589,
586
+ "logits/rejected": -2.6695313453674316,
587
+ "logps/chosen": -1.098097324371338,
588
+ "logps/rejected": -1.4831833839416504,
589
+ "loss": 1.899,
590
+ "rewards/accuracies": 0.668749988079071,
591
+ "rewards/chosen": -1.098097324371338,
592
+ "rewards/margins": 0.3850858509540558,
593
+ "rewards/rejected": -1.4831833839416504,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.4187385501177702,
598
+ "grad_norm": 28.048650935368237,
599
+ "learning_rate": 3.604695382782159e-07,
600
+ "logits/chosen": -2.738492250442505,
601
+ "logits/rejected": -2.7187023162841797,
602
+ "logps/chosen": -1.0665818452835083,
603
+ "logps/rejected": -1.46578049659729,
604
+ "loss": 1.8737,
605
+ "rewards/accuracies": 0.637499988079071,
606
+ "rewards/chosen": -1.0665818452835083,
607
+ "rewards/margins": 0.39919885993003845,
608
+ "rewards/rejected": -1.46578049659729,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.42920701387071447,
613
+ "grad_norm": 27.850087928191183,
614
+ "learning_rate": 3.5218566107988867e-07,
615
+ "logits/chosen": -2.6582818031311035,
616
+ "logits/rejected": -2.5809996128082275,
617
+ "logps/chosen": -0.9890678524971008,
618
+ "logps/rejected": -1.4678758382797241,
619
+ "loss": 1.8403,
620
+ "rewards/accuracies": 0.606249988079071,
621
+ "rewards/chosen": -0.9890678524971008,
622
+ "rewards/margins": 0.47880783677101135,
623
+ "rewards/rejected": -1.4678758382797241,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.4396754776236587,
628
+ "grad_norm": 29.109484926295075,
629
+ "learning_rate": 3.4376480090239047e-07,
630
+ "logits/chosen": -2.6842644214630127,
631
+ "logits/rejected": -2.627836227416992,
632
+ "logps/chosen": -1.075455665588379,
633
+ "logps/rejected": -1.4202773571014404,
634
+ "loss": 1.8863,
635
+ "rewards/accuracies": 0.606249988079071,
636
+ "rewards/chosen": -1.075455665588379,
637
+ "rewards/margins": 0.34482160210609436,
638
+ "rewards/rejected": -1.4202773571014404,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.45014394137660296,
643
+ "grad_norm": 23.99752736324705,
644
+ "learning_rate": 3.3521824616429284e-07,
645
+ "logits/chosen": -2.716024875640869,
646
+ "logits/rejected": -2.6916396617889404,
647
+ "logps/chosen": -1.0032670497894287,
648
+ "logps/rejected": -1.5087072849273682,
649
+ "loss": 1.8264,
650
+ "rewards/accuracies": 0.78125,
651
+ "rewards/chosen": -1.0032670497894287,
652
+ "rewards/margins": 0.5054404139518738,
653
+ "rewards/rejected": -1.5087072849273682,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.46061240512954726,
658
+ "grad_norm": 31.21916182230841,
659
+ "learning_rate": 3.265574537815398e-07,
660
+ "logits/chosen": -2.742882013320923,
661
+ "logits/rejected": -2.658285617828369,
662
+ "logps/chosen": -1.033542275428772,
663
+ "logps/rejected": -1.5640771389007568,
664
+ "loss": 1.8307,
665
+ "rewards/accuracies": 0.6625000238418579,
666
+ "rewards/chosen": -1.033542275428772,
667
+ "rewards/margins": 0.5305347442626953,
668
+ "rewards/rejected": -1.5640771389007568,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.4710808688824915,
673
+ "grad_norm": 26.98263419792695,
674
+ "learning_rate": 3.1779403380910425e-07,
675
+ "logits/chosen": -2.7341504096984863,
676
+ "logits/rejected": -2.6276047229766846,
677
+ "logps/chosen": -0.988808810710907,
678
+ "logps/rejected": -1.5687158107757568,
679
+ "loss": 1.8334,
680
+ "rewards/accuracies": 0.6312500238418579,
681
+ "rewards/chosen": -0.988808810710907,
682
+ "rewards/margins": 0.5799070596694946,
683
+ "rewards/rejected": -1.5687158107757568,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.48154933263543576,
688
+ "grad_norm": 29.311922113138767,
689
+ "learning_rate": 3.0893973387735683e-07,
690
+ "logits/chosen": -2.74092698097229,
691
+ "logits/rejected": -2.6369271278381348,
692
+ "logps/chosen": -1.009143352508545,
693
+ "logps/rejected": -1.665408730506897,
694
+ "loss": 1.8283,
695
+ "rewards/accuracies": 0.699999988079071,
696
+ "rewards/chosen": -1.009143352508545,
697
+ "rewards/margins": 0.6562654376029968,
698
+ "rewards/rejected": -1.665408730506897,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.49201779638838,
703
+ "grad_norm": 32.62916846952035,
704
+ "learning_rate": 3.000064234440111e-07,
705
+ "logits/chosen": -2.729424476623535,
706
+ "logits/rejected": -2.672799587249756,
707
+ "logps/chosen": -1.0022896528244019,
708
+ "logps/rejected": -1.5322816371917725,
709
+ "loss": 1.86,
710
+ "rewards/accuracies": 0.731249988079071,
711
+ "rewards/chosen": -1.0022896528244019,
712
+ "rewards/margins": 0.5299919247627258,
713
+ "rewards/rejected": -1.5322816371917725,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5024862601413242,
718
+ "grad_norm": 25.60849652215575,
719
+ "learning_rate": 2.910060778827554e-07,
720
+ "logits/chosen": -2.666738986968994,
721
+ "logits/rejected": -2.6147377490997314,
722
+ "logps/chosen": -1.0380260944366455,
723
+ "logps/rejected": -1.5499128103256226,
724
+ "loss": 1.8806,
725
+ "rewards/accuracies": 0.668749988079071,
726
+ "rewards/chosen": -1.0380260944366455,
727
+ "rewards/margins": 0.5118868947029114,
728
+ "rewards/rejected": -1.5499128103256226,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5129547238942685,
733
+ "grad_norm": 23.307769710548996,
734
+ "learning_rate": 2.8195076242990116e-07,
735
+ "logits/chosen": -2.7083492279052734,
736
+ "logits/rejected": -2.608227014541626,
737
+ "logps/chosen": -1.1102759838104248,
738
+ "logps/rejected": -1.5368731021881104,
739
+ "loss": 1.8599,
740
+ "rewards/accuracies": 0.6312500238418579,
741
+ "rewards/chosen": -1.1102759838104248,
742
+ "rewards/margins": 0.42659682035446167,
743
+ "rewards/rejected": -1.5368731021881104,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.5234231876472127,
748
+ "grad_norm": 30.713855522791444,
749
+ "learning_rate": 2.7285261601056697e-07,
750
+ "logits/chosen": -2.621891498565674,
751
+ "logits/rejected": -2.572918653488159,
752
+ "logps/chosen": -1.0056602954864502,
753
+ "logps/rejected": -1.5289640426635742,
754
+ "loss": 1.8611,
755
+ "rewards/accuracies": 0.6812499761581421,
756
+ "rewards/chosen": -1.0056602954864502,
757
+ "rewards/margins": 0.5233036875724792,
758
+ "rewards/rejected": -1.5289640426635742,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.533891651400157,
763
+ "grad_norm": 21.027582284131125,
764
+ "learning_rate": 2.6372383496608186e-07,
765
+ "logits/chosen": -2.679741859436035,
766
+ "logits/rejected": -2.588026762008667,
767
+ "logps/chosen": -1.0767912864685059,
768
+ "logps/rejected": -1.6802423000335693,
769
+ "loss": 1.7962,
770
+ "rewards/accuracies": 0.6499999761581421,
771
+ "rewards/chosen": -1.0767912864685059,
772
+ "rewards/margins": 0.603451132774353,
773
+ "rewards/rejected": -1.6802423000335693,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5443601151531012,
778
+ "grad_norm": 21.083992579626138,
779
+ "learning_rate": 2.5457665670441937e-07,
780
+ "logits/chosen": -2.639758825302124,
781
+ "logits/rejected": -2.539482831954956,
782
+ "logps/chosen": -0.9617997407913208,
783
+ "logps/rejected": -1.643094778060913,
784
+ "loss": 1.8469,
785
+ "rewards/accuracies": 0.699999988079071,
786
+ "rewards/chosen": -0.9617997407913208,
787
+ "rewards/margins": 0.6812952160835266,
788
+ "rewards/rejected": -1.643094778060913,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5548285789060455,
793
+ "grad_norm": 34.336932322095805,
794
+ "learning_rate": 2.454233432955807e-07,
795
+ "logits/chosen": -2.6934094429016113,
796
+ "logits/rejected": -2.635524034500122,
797
+ "logps/chosen": -1.0399844646453857,
798
+ "logps/rejected": -1.3895108699798584,
799
+ "loss": 1.8185,
800
+ "rewards/accuracies": 0.6625000238418579,
801
+ "rewards/chosen": -1.0399844646453857,
802
+ "rewards/margins": 0.3495265543460846,
803
+ "rewards/rejected": -1.3895108699798584,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.5652970426589898,
808
+ "grad_norm": 35.56183499916552,
809
+ "learning_rate": 2.3627616503391812e-07,
810
+ "logits/chosen": -2.678424596786499,
811
+ "logits/rejected": -2.6192078590393066,
812
+ "logps/chosen": -1.1347005367279053,
813
+ "logps/rejected": -1.5019694566726685,
814
+ "loss": 1.8876,
815
+ "rewards/accuracies": 0.6812499761581421,
816
+ "rewards/chosen": -1.1347005367279053,
817
+ "rewards/margins": 0.36726871132850647,
818
+ "rewards/rejected": -1.5019694566726685,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.575765506411934,
823
+ "grad_norm": 21.13133035084058,
824
+ "learning_rate": 2.2714738398943308e-07,
825
+ "logits/chosen": -2.749488592147827,
826
+ "logits/rejected": -2.629812717437744,
827
+ "logps/chosen": -1.0328668355941772,
828
+ "logps/rejected": -1.6207387447357178,
829
+ "loss": 1.833,
830
+ "rewards/accuracies": 0.675000011920929,
831
+ "rewards/chosen": -1.0328668355941772,
832
+ "rewards/margins": 0.5878719091415405,
833
+ "rewards/rejected": -1.6207387447357178,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.5862339701648783,
838
+ "grad_norm": 27.44411354972676,
839
+ "learning_rate": 2.1804923757009882e-07,
840
+ "logits/chosen": -2.7630438804626465,
841
+ "logits/rejected": -2.692211866378784,
842
+ "logps/chosen": -0.968722939491272,
843
+ "logps/rejected": -1.3731743097305298,
844
+ "loss": 1.8453,
845
+ "rewards/accuracies": 0.668749988079071,
846
+ "rewards/chosen": -0.968722939491272,
847
+ "rewards/margins": 0.40445131063461304,
848
+ "rewards/rejected": -1.3731743097305298,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.5967024339178225,
853
+ "grad_norm": 32.499361452307625,
854
+ "learning_rate": 2.089939221172446e-07,
855
+ "logits/chosen": -2.682573080062866,
856
+ "logits/rejected": -2.678396224975586,
857
+ "logps/chosen": -1.0675628185272217,
858
+ "logps/rejected": -1.5514373779296875,
859
+ "loss": 1.8267,
860
+ "rewards/accuracies": 0.699999988079071,
861
+ "rewards/chosen": -1.0675628185272217,
862
+ "rewards/margins": 0.4838746190071106,
863
+ "rewards/rejected": -1.5514373779296875,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6071708976707668,
868
+ "grad_norm": 34.51002212540645,
869
+ "learning_rate": 1.9999357655598891e-07,
870
+ "logits/chosen": -2.7195992469787598,
871
+ "logits/rejected": -2.6691336631774902,
872
+ "logps/chosen": -1.0737675428390503,
873
+ "logps/rejected": -1.6511163711547852,
874
+ "loss": 1.8055,
875
+ "rewards/accuracies": 0.6812499761581421,
876
+ "rewards/chosen": -1.0737675428390503,
877
+ "rewards/margins": 0.5773489475250244,
878
+ "rewards/rejected": -1.6511163711547852,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6176393614237111,
883
+ "grad_norm": 34.81875700322843,
884
+ "learning_rate": 1.9106026612264315e-07,
885
+ "logits/chosen": -2.7475931644439697,
886
+ "logits/rejected": -2.661341667175293,
887
+ "logps/chosen": -1.0815327167510986,
888
+ "logps/rejected": -1.6415588855743408,
889
+ "loss": 1.8548,
890
+ "rewards/accuracies": 0.706250011920929,
891
+ "rewards/chosen": -1.0815327167510986,
892
+ "rewards/margins": 0.5600259900093079,
893
+ "rewards/rejected": -1.6415588855743408,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6281078251766553,
898
+ "grad_norm": 39.656088577829394,
899
+ "learning_rate": 1.8220596619089573e-07,
900
+ "logits/chosen": -2.650444507598877,
901
+ "logits/rejected": -2.601776123046875,
902
+ "logps/chosen": -1.0726263523101807,
903
+ "logps/rejected": -1.5858640670776367,
904
+ "loss": 1.8352,
905
+ "rewards/accuracies": 0.699999988079071,
906
+ "rewards/chosen": -1.0726263523101807,
907
+ "rewards/margins": 0.5132376551628113,
908
+ "rewards/rejected": -1.5858640670776367,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6385762889295996,
913
+ "grad_norm": 34.266407421018876,
914
+ "learning_rate": 1.7344254621846017e-07,
915
+ "logits/chosen": -2.6358659267425537,
916
+ "logits/rejected": -2.589916944503784,
917
+ "logps/chosen": -1.0825355052947998,
918
+ "logps/rejected": -1.695123314857483,
919
+ "loss": 1.8122,
920
+ "rewards/accuracies": 0.6937500238418579,
921
+ "rewards/chosen": -1.0825355052947998,
922
+ "rewards/margins": 0.6125878691673279,
923
+ "rewards/rejected": -1.695123314857483,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6490447526825438,
928
+ "grad_norm": 29.29392494715919,
929
+ "learning_rate": 1.647817538357072e-07,
930
+ "logits/chosen": -2.6732287406921387,
931
+ "logits/rejected": -2.6671674251556396,
932
+ "logps/chosen": -0.9606215357780457,
933
+ "logps/rejected": -1.507188081741333,
934
+ "loss": 1.8154,
935
+ "rewards/accuracies": 0.699999988079071,
936
+ "rewards/chosen": -0.9606215357780457,
937
+ "rewards/margins": 0.5465664863586426,
938
+ "rewards/rejected": -1.507188081741333,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6595132164354881,
943
+ "grad_norm": 30.886215191002822,
944
+ "learning_rate": 1.562351990976095e-07,
945
+ "logits/chosen": -2.6945061683654785,
946
+ "logits/rejected": -2.6447794437408447,
947
+ "logps/chosen": -0.9400749206542969,
948
+ "logps/rejected": -1.5918124914169312,
949
+ "loss": 1.8296,
950
+ "rewards/accuracies": 0.71875,
951
+ "rewards/chosen": -0.9400749206542969,
952
+ "rewards/margins": 0.651737630367279,
953
+ "rewards/rejected": -1.5918124914169312,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6699816801884323,
958
+ "grad_norm": 40.31455490523793,
959
+ "learning_rate": 1.478143389201113e-07,
960
+ "logits/chosen": -2.6877899169921875,
961
+ "logits/rejected": -2.6543657779693604,
962
+ "logps/chosen": -1.0309157371520996,
963
+ "logps/rejected": -1.5069587230682373,
964
+ "loss": 1.7854,
965
+ "rewards/accuracies": 0.65625,
966
+ "rewards/chosen": -1.0309157371520996,
967
+ "rewards/margins": 0.47604283690452576,
968
+ "rewards/rejected": -1.5069587230682373,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.6804501439413766,
973
+ "grad_norm": 33.29916453849858,
974
+ "learning_rate": 1.3953046172178413e-07,
975
+ "logits/chosen": -2.712068557739258,
976
+ "logits/rejected": -2.6253581047058105,
977
+ "logps/chosen": -1.0362852811813354,
978
+ "logps/rejected": -1.6363003253936768,
979
+ "loss": 1.7979,
980
+ "rewards/accuracies": 0.668749988079071,
981
+ "rewards/chosen": -1.0362852811813354,
982
+ "rewards/margins": 0.6000149846076965,
983
+ "rewards/rejected": -1.6363003253936768,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.6909186076943209,
988
+ "grad_norm": 28.615351737244207,
989
+ "learning_rate": 1.3139467229135998e-07,
990
+ "logits/chosen": -2.672591209411621,
991
+ "logits/rejected": -2.624178886413574,
992
+ "logps/chosen": -1.0226625204086304,
993
+ "logps/rejected": -1.4031275510787964,
994
+ "loss": 1.8499,
995
+ "rewards/accuracies": 0.625,
996
+ "rewards/chosen": -1.0226625204086304,
997
+ "rewards/margins": 0.38046500086784363,
998
+ "rewards/rejected": -1.4031275510787964,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7013870714472651,
1003
+ "grad_norm": 31.872437043858163,
1004
+ "learning_rate": 1.2341787690142435e-07,
1005
+ "logits/chosen": -2.783500909805298,
1006
+ "logits/rejected": -2.7123568058013916,
1007
+ "logps/chosen": -0.9628676176071167,
1008
+ "logps/rejected": -1.5226846933364868,
1009
+ "loss": 1.8281,
1010
+ "rewards/accuracies": 0.6937500238418579,
1011
+ "rewards/chosen": -0.9628676176071167,
1012
+ "rewards/margins": 0.5598170161247253,
1013
+ "rewards/rejected": -1.5226846933364868,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7118555352002094,
1018
+ "grad_norm": 27.878376041354297,
1019
+ "learning_rate": 1.1561076868822755e-07,
1020
+ "logits/chosen": -2.7173564434051514,
1021
+ "logits/rejected": -2.6413800716400146,
1022
+ "logps/chosen": -1.1935253143310547,
1023
+ "logps/rejected": -1.5975086688995361,
1024
+ "loss": 1.8896,
1025
+ "rewards/accuracies": 0.6875,
1026
+ "rewards/chosen": -1.1935253143310547,
1027
+ "rewards/margins": 0.40398329496383667,
1028
+ "rewards/rejected": -1.5975086688995361,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.7223239989531536,
1033
+ "grad_norm": 36.976534101742224,
1034
+ "learning_rate": 1.0798381331721107e-07,
1035
+ "logits/chosen": -2.7495174407958984,
1036
+ "logits/rejected": -2.700282573699951,
1037
+ "logps/chosen": -1.0389212369918823,
1038
+ "logps/rejected": -1.5958582162857056,
1039
+ "loss": 1.8433,
1040
+ "rewards/accuracies": 0.625,
1041
+ "rewards/chosen": -1.0389212369918823,
1042
+ "rewards/margins": 0.5569368600845337,
1043
+ "rewards/rejected": -1.5958582162857056,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7327924627060979,
1048
+ "grad_norm": 30.288124940758514,
1049
+ "learning_rate": 1.0054723495346482e-07,
1050
+ "logits/chosen": -2.7106757164001465,
1051
+ "logits/rejected": -2.687342882156372,
1052
+ "logps/chosen": -1.0641244649887085,
1053
+ "logps/rejected": -1.5430529117584229,
1054
+ "loss": 1.8735,
1055
+ "rewards/accuracies": 0.6187499761581421,
1056
+ "rewards/chosen": -1.0641244649887085,
1057
+ "rewards/margins": 0.47892847657203674,
1058
+ "rewards/rejected": -1.5430529117584229,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7432609264590422,
1063
+ "grad_norm": 30.72874948597524,
1064
+ "learning_rate": 9.331100255592436e-08,
1065
+ "logits/chosen": -2.7169158458709717,
1066
+ "logits/rejected": -2.66363787651062,
1067
+ "logps/chosen": -0.9323965311050415,
1068
+ "logps/rejected": -1.5993990898132324,
1069
+ "loss": 1.7736,
1070
+ "rewards/accuracies": 0.75,
1071
+ "rewards/chosen": -0.9323965311050415,
1072
+ "rewards/margins": 0.6670026779174805,
1073
+ "rewards/rejected": -1.5993990898132324,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7537293902119864,
1078
+ "grad_norm": 22.0079277817506,
1079
+ "learning_rate": 8.628481651367875e-08,
1080
+ "logits/chosen": -2.746021270751953,
1081
+ "logits/rejected": -2.6950621604919434,
1082
+ "logps/chosen": -0.9703041315078735,
1083
+ "logps/rejected": -1.4327679872512817,
1084
+ "loss": 1.783,
1085
+ "rewards/accuracies": 0.65625,
1086
+ "rewards/chosen": -0.9703041315078735,
1087
+ "rewards/margins": 0.4624637961387634,
1088
+ "rewards/rejected": -1.4327679872512817,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.7641978539649307,
1093
+ "grad_norm": 33.139790420388316,
1094
+ "learning_rate": 7.947809564230445e-08,
1095
+ "logits/chosen": -2.6830432415008545,
1096
+ "logits/rejected": -2.5992660522460938,
1097
+ "logps/chosen": -1.0758744478225708,
1098
+ "logps/rejected": -1.6359386444091797,
1099
+ "loss": 1.8553,
1100
+ "rewards/accuracies": 0.7124999761581421,
1101
+ "rewards/chosen": -1.0758744478225708,
1102
+ "rewards/margins": 0.5600640773773193,
1103
+ "rewards/rejected": -1.6359386444091797,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7746663177178749,
1108
+ "grad_norm": 42.978648090018346,
1109
+ "learning_rate": 7.289996455765748e-08,
1110
+ "logits/chosen": -2.7361717224121094,
1111
+ "logits/rejected": -2.6721107959747314,
1112
+ "logps/chosen": -1.0527479648590088,
1113
+ "logps/rejected": -1.7067893743515015,
1114
+ "loss": 1.8183,
1115
+ "rewards/accuracies": 0.699999988079071,
1116
+ "rewards/chosen": -1.0527479648590088,
1117
+ "rewards/margins": 0.6540414094924927,
1118
+ "rewards/rejected": -1.7067893743515015,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.7851347814708192,
1123
+ "grad_norm": 24.61410992203062,
1124
+ "learning_rate": 6.655924144404906e-08,
1125
+ "logits/chosen": -2.715893268585205,
1126
+ "logits/rejected": -2.7327394485473633,
1127
+ "logps/chosen": -1.0623342990875244,
1128
+ "logps/rejected": -1.5285212993621826,
1129
+ "loss": 1.8189,
1130
+ "rewards/accuracies": 0.6187499761581421,
1131
+ "rewards/chosen": -1.0623342990875244,
1132
+ "rewards/margins": 0.4661870002746582,
1133
+ "rewards/rejected": -1.5285212993621826,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.7956032452237635,
1138
+ "grad_norm": 29.084948650681554,
1139
+ "learning_rate": 6.046442623320145e-08,
1140
+ "logits/chosen": -2.7230355739593506,
1141
+ "logits/rejected": -2.665907621383667,
1142
+ "logps/chosen": -1.0696966648101807,
1143
+ "logps/rejected": -1.5225203037261963,
1144
+ "loss": 1.7794,
1145
+ "rewards/accuracies": 0.6812499761581421,
1146
+ "rewards/chosen": -1.0696966648101807,
1147
+ "rewards/margins": 0.4528239369392395,
1148
+ "rewards/rejected": -1.5225203037261963,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.8060717089767077,
1153
+ "grad_norm": 25.930022257563827,
1154
+ "learning_rate": 5.4623689209832484e-08,
1155
+ "logits/chosen": -2.7370214462280273,
1156
+ "logits/rejected": -2.6596484184265137,
1157
+ "logps/chosen": -1.0190281867980957,
1158
+ "logps/rejected": -1.4870203733444214,
1159
+ "loss": 1.8012,
1160
+ "rewards/accuracies": 0.6187499761581421,
1161
+ "rewards/chosen": -1.0190281867980957,
1162
+ "rewards/margins": 0.46799221634864807,
1163
+ "rewards/rejected": -1.4870203733444214,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.816540172729652,
1168
+ "grad_norm": 30.16253644602296,
1169
+ "learning_rate": 4.904486005914027e-08,
1170
+ "logits/chosen": -2.755403518676758,
1171
+ "logits/rejected": -2.6998536586761475,
1172
+ "logps/chosen": -1.0058339834213257,
1173
+ "logps/rejected": -1.6741714477539062,
1174
+ "loss": 1.7816,
1175
+ "rewards/accuracies": 0.71875,
1176
+ "rewards/chosen": -1.0058339834213257,
1177
+ "rewards/margins": 0.6683375239372253,
1178
+ "rewards/rejected": -1.6741714477539062,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8270086364825961,
1183
+ "grad_norm": 32.100503895364014,
1184
+ "learning_rate": 4.373541737087263e-08,
1185
+ "logits/chosen": -2.6867947578430176,
1186
+ "logits/rejected": -2.6116786003112793,
1187
+ "logps/chosen": -0.9958473443984985,
1188
+ "logps/rejected": -1.5259888172149658,
1189
+ "loss": 1.8098,
1190
+ "rewards/accuracies": 0.737500011920929,
1191
+ "rewards/chosen": -0.9958473443984985,
1192
+ "rewards/margins": 0.5301414132118225,
1193
+ "rewards/rejected": -1.5259888172149658,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8374771002355405,
1198
+ "grad_norm": 39.50777886532678,
1199
+ "learning_rate": 3.8702478614051345e-08,
1200
+ "logits/chosen": -2.6500821113586426,
1201
+ "logits/rejected": -2.587491273880005,
1202
+ "logps/chosen": -0.9868978261947632,
1203
+ "logps/rejected": -1.5105135440826416,
1204
+ "loss": 1.81,
1205
+ "rewards/accuracies": 0.6812499761581421,
1206
+ "rewards/chosen": -0.9868978261947632,
1207
+ "rewards/margins": 0.523615837097168,
1208
+ "rewards/rejected": -1.5105135440826416,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8479455639884846,
1213
+ "grad_norm": 39.172472564486576,
1214
+ "learning_rate": 3.3952790595787986e-08,
1215
+ "logits/chosen": -2.7077910900115967,
1216
+ "logits/rejected": -2.671496868133545,
1217
+ "logps/chosen": -1.0807896852493286,
1218
+ "logps/rejected": -1.6041944026947021,
1219
+ "loss": 1.8475,
1220
+ "rewards/accuracies": 0.643750011920929,
1221
+ "rewards/chosen": -1.0807896852493286,
1222
+ "rewards/margins": 0.5234047174453735,
1223
+ "rewards/rejected": -1.6041944026947021,
1224
+ "step": 405
1225
+ },
1226
+ {
1227
+ "epoch": 0.8584140277414289,
1228
+ "grad_norm": 34.16755927550673,
1229
+ "learning_rate": 2.9492720416985e-08,
1230
+ "logits/chosen": -2.729513645172119,
1231
+ "logits/rejected": -2.68589448928833,
1232
+ "logps/chosen": -0.9558256268501282,
1233
+ "logps/rejected": -1.4403427839279175,
1234
+ "loss": 1.8083,
1235
+ "rewards/accuracies": 0.65625,
1236
+ "rewards/chosen": -0.9558256268501282,
1237
+ "rewards/margins": 0.4845171868801117,
1238
+ "rewards/rejected": -1.4403427839279175,
1239
+ "step": 410
1240
+ },
1241
+ {
1242
+ "epoch": 0.8688824914943732,
1243
+ "grad_norm": 27.600146859315487,
1244
+ "learning_rate": 2.5328246937043525e-08,
1245
+ "logits/chosen": -2.758931875228882,
1246
+ "logits/rejected": -2.693338394165039,
1247
+ "logps/chosen": -1.004372239112854,
1248
+ "logps/rejected": -1.6196565628051758,
1249
+ "loss": 1.7709,
1250
+ "rewards/accuracies": 0.6937500238418579,
1251
+ "rewards/chosen": -1.004372239112854,
1252
+ "rewards/margins": 0.615284264087677,
1253
+ "rewards/rejected": -1.6196565628051758,
1254
+ "step": 415
1255
+ },
1256
+ {
1257
+ "epoch": 0.8793509552473174,
1258
+ "grad_norm": 26.767731856804396,
1259
+ "learning_rate": 2.1464952759020856e-08,
1260
+ "logits/chosen": -2.7129735946655273,
1261
+ "logits/rejected": -2.6572775840759277,
1262
+ "logps/chosen": -0.9905831217765808,
1263
+ "logps/rejected": -1.5554085969924927,
1264
+ "loss": 1.8411,
1265
+ "rewards/accuracies": 0.6312500238418579,
1266
+ "rewards/chosen": -0.9905831217765808,
1267
+ "rewards/margins": 0.5648255944252014,
1268
+ "rewards/rejected": -1.5554085969924927,
1269
+ "step": 420
1270
+ },
1271
+ {
1272
+ "epoch": 0.8898194190002617,
1273
+ "grad_norm": 32.1190541072846,
1274
+ "learning_rate": 1.7908016745981856e-08,
1275
+ "logits/chosen": -2.656250476837158,
1276
+ "logits/rejected": -2.645900249481201,
1277
+ "logps/chosen": -1.1461454629898071,
1278
+ "logps/rejected": -1.604714035987854,
1279
+ "loss": 1.8218,
1280
+ "rewards/accuracies": 0.6312500238418579,
1281
+ "rewards/chosen": -1.1461454629898071,
1282
+ "rewards/margins": 0.45856842398643494,
1283
+ "rewards/rejected": -1.604714035987854,
1284
+ "step": 425
1285
+ },
1286
+ {
1287
+ "epoch": 0.9002878827532059,
1288
+ "grad_norm": 38.87548467523877,
1289
+ "learning_rate": 1.4662207078575684e-08,
1290
+ "logits/chosen": -2.661616325378418,
1291
+ "logits/rejected": -2.617453098297119,
1292
+ "logps/chosen": -1.1022528409957886,
1293
+ "logps/rejected": -1.628826379776001,
1294
+ "loss": 1.8088,
1295
+ "rewards/accuracies": 0.643750011920929,
1296
+ "rewards/chosen": -1.1022528409957886,
1297
+ "rewards/margins": 0.5265735387802124,
1298
+ "rewards/rejected": -1.628826379776001,
1299
+ "step": 430
1300
+ },
1301
+ {
1302
+ "epoch": 0.9107563465061502,
1303
+ "grad_norm": 34.292720836263,
1304
+ "learning_rate": 1.1731874863145142e-08,
1305
+ "logits/chosen": -2.7260875701904297,
1306
+ "logits/rejected": -2.685364246368408,
1307
+ "logps/chosen": -1.0480232238769531,
1308
+ "logps/rejected": -1.6929914951324463,
1309
+ "loss": 1.8315,
1310
+ "rewards/accuracies": 0.6875,
1311
+ "rewards/chosen": -1.0480232238769531,
1312
+ "rewards/margins": 0.6449683308601379,
1313
+ "rewards/rejected": -1.6929914951324463,
1314
+ "step": 435
1315
+ },
1316
+ {
1317
+ "epoch": 0.9212248102590945,
1318
+ "grad_norm": 36.60770449520838,
1319
+ "learning_rate": 9.12094829893642e-09,
1320
+ "logits/chosen": -2.6789753437042236,
1321
+ "logits/rejected": -2.6536145210266113,
1322
+ "logps/chosen": -1.0216642618179321,
1323
+ "logps/rejected": -1.547012448310852,
1324
+ "loss": 1.8478,
1325
+ "rewards/accuracies": 0.637499988079071,
1326
+ "rewards/chosen": -1.0216642618179321,
1327
+ "rewards/margins": 0.5253482460975647,
1328
+ "rewards/rejected": -1.547012448310852,
1329
+ "step": 440
1330
+ },
1331
+ {
1332
+ "epoch": 0.9316932740120387,
1333
+ "grad_norm": 34.43665423362751,
1334
+ "learning_rate": 6.832927412229017e-09,
1335
+ "logits/chosen": -2.721832752227783,
1336
+ "logits/rejected": -2.660407781600952,
1337
+ "logps/chosen": -1.0646559000015259,
1338
+ "logps/rejected": -1.554300308227539,
1339
+ "loss": 1.8533,
1340
+ "rewards/accuracies": 0.65625,
1341
+ "rewards/chosen": -1.0646559000015259,
1342
+ "rewards/margins": 0.4896443486213684,
1343
+ "rewards/rejected": -1.554300308227539,
1344
+ "step": 445
1345
+ },
1346
+ {
1347
+ "epoch": 0.942161737764983,
1348
+ "grad_norm": 30.770535415455328,
1349
+ "learning_rate": 4.8708793644441086e-09,
1350
+ "logits/chosen": -2.6228880882263184,
1351
+ "logits/rejected": -2.5837976932525635,
1352
+ "logps/chosen": -1.0409653186798096,
1353
+ "logps/rejected": -1.537603735923767,
1354
+ "loss": 1.7905,
1355
+ "rewards/accuracies": 0.675000011920929,
1356
+ "rewards/chosen": -1.0409653186798096,
1357
+ "rewards/margins": 0.4966384768486023,
1358
+ "rewards/rejected": -1.537603735923767,
1359
+ "step": 450
1360
+ },
1361
+ {
1362
+ "epoch": 0.9526302015179272,
1363
+ "grad_norm": 27.915122014592697,
1364
+ "learning_rate": 3.2374343405217884e-09,
1365
+ "logits/chosen": -2.6800639629364014,
1366
+ "logits/rejected": -2.6128344535827637,
1367
+ "logps/chosen": -1.132541298866272,
1368
+ "logps/rejected": -1.5116033554077148,
1369
+ "loss": 1.825,
1370
+ "rewards/accuracies": 0.668749988079071,
1371
+ "rewards/chosen": -1.132541298866272,
1372
+ "rewards/margins": 0.3790620267391205,
1373
+ "rewards/rejected": -1.5116033554077148,
1374
+ "step": 455
1375
+ },
1376
+ {
1377
+ "epoch": 0.9630986652708715,
1378
+ "grad_norm": 31.401214396279837,
1379
+ "learning_rate": 1.9347820230782295e-09,
1380
+ "logits/chosen": -2.6828560829162598,
1381
+ "logits/rejected": -2.6430163383483887,
1382
+ "logps/chosen": -0.9926983118057251,
1383
+ "logps/rejected": -1.5756382942199707,
1384
+ "loss": 1.7905,
1385
+ "rewards/accuracies": 0.7124999761581421,
1386
+ "rewards/chosen": -0.9926983118057251,
1387
+ "rewards/margins": 0.5829401612281799,
1388
+ "rewards/rejected": -1.5756382942199707,
1389
+ "step": 460
1390
+ },
1391
+ {
1392
+ "epoch": 0.9735671290238157,
1393
+ "grad_norm": 38.51782864695839,
1394
+ "learning_rate": 9.64668657069706e-10,
1395
+ "logits/chosen": -2.7383384704589844,
1396
+ "logits/rejected": -2.6524176597595215,
1397
+ "logps/chosen": -1.0901256799697876,
1398
+ "logps/rejected": -1.620060682296753,
1399
+ "loss": 1.8476,
1400
+ "rewards/accuracies": 0.706250011920929,
1401
+ "rewards/chosen": -1.0901256799697876,
1402
+ "rewards/margins": 0.5299350023269653,
1403
+ "rewards/rejected": -1.620060682296753,
1404
+ "step": 465
1405
+ },
1406
+ {
1407
+ "epoch": 0.98403559277676,
1408
+ "grad_norm": 27.923910450585048,
1409
+ "learning_rate": 3.2839470889836627e-10,
1410
+ "logits/chosen": -2.7122910022735596,
1411
+ "logits/rejected": -2.6457693576812744,
1412
+ "logps/chosen": -0.9990774393081665,
1413
+ "logps/rejected": -1.4476706981658936,
1414
+ "loss": 1.8714,
1415
+ "rewards/accuracies": 0.668749988079071,
1416
+ "rewards/chosen": -0.9990774393081665,
1417
+ "rewards/margins": 0.4485931396484375,
1418
+ "rewards/rejected": -1.4476706981658936,
1419
+ "step": 470
1420
+ },
1421
+ {
1422
+ "epoch": 0.9945040565297043,
1423
+ "grad_norm": 33.978087151320835,
1424
+ "learning_rate": 2.6813123097352287e-11,
1425
+ "logits/chosen": -2.7624480724334717,
1426
+ "logits/rejected": -2.6619315147399902,
1427
+ "logps/chosen": -1.042180061340332,
1428
+ "logps/rejected": -1.5233901739120483,
1429
+ "loss": 1.8233,
1430
+ "rewards/accuracies": 0.606249988079071,
1431
+ "rewards/chosen": -1.042180061340332,
1432
+ "rewards/margins": 0.4812101721763611,
1433
+ "rewards/rejected": -1.5233901739120483,
1434
+ "step": 475
1435
+ },
1436
+ {
1437
+ "epoch": 0.998691442030882,
1438
+ "step": 477,
1439
+ "total_flos": 0.0,
1440
+ "train_loss": 1.8644854217705238,
1441
+ "train_runtime": 7378.4782,
1442
+ "train_samples_per_second": 8.286,
1443
+ "train_steps_per_second": 0.065
1444
+ }
1445
+ ],
1446
+ "logging_steps": 5,
1447
+ "max_steps": 477,
1448
+ "num_input_tokens_seen": 0,
1449
+ "num_train_epochs": 1,
1450
+ "save_steps": 1000000,
1451
+ "total_flos": 0.0,
1452
+ "train_batch_size": 2,
1453
+ "trial_name": null,
1454
+ "trial_params": null
1455
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1566c6850ed286617593bc0f0a3520f3b18f6ea3c6c7c83ad58bd9856178c1a5
3
+ size 7160