Teng Xiao commited on
Commit
a27e1ce
1 Parent(s): 714876b
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-MI1-SELM3
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-MI1-SELM3
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": 1.8633759126723188,
5
+ "train_runtime": 7578.2385,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 8.067,
8
+ "train_steps_per_second": 0.063
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 sha256:3a07fa3cc5b045fb88bc7a49b1b8a5318d539ee5ae841bfe46dbc0a977bfed73
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a77c59044e03ebe7cff21a024e97e4b4ad06f229fd17cfd4ae208e6a1457c9e
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403294c6a18e514f695684d622a0541579fb415562cbb13ebfe1e18fa51032dc
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": 1.8633759126723188,
5
+ "train_runtime": 7578.2385,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 8.067,
8
+ "train_steps_per_second": 0.063
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": 15.176345540381961,
14
+ "learning_rate": 5.208333333333333e-08,
15
+ "logits/chosen": -2.7708451747894287,
16
+ "logits/rejected": -2.7284560203552246,
17
+ "logps/chosen": -1.0280715227127075,
18
+ "logps/rejected": -1.1731975078582764,
19
+ "loss": 2.0284,
20
+ "rewards/accuracies": 0.574999988079071,
21
+ "rewards/chosen": -1.0280715227127075,
22
+ "rewards/margins": 0.14512601494789124,
23
+ "rewards/rejected": -1.1731975078582764,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.02093692750588851,
28
+ "grad_norm": 13.877817908572124,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -2.7508482933044434,
31
+ "logits/rejected": -2.725215196609497,
32
+ "logps/chosen": -0.9954730868339539,
33
+ "logps/rejected": -1.071991205215454,
34
+ "loss": 2.002,
35
+ "rewards/accuracies": 0.5,
36
+ "rewards/chosen": -0.9954730868339539,
37
+ "rewards/margins": 0.0765179991722107,
38
+ "rewards/rejected": -1.071991205215454,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.031405391258832765,
43
+ "grad_norm": 13.915470437591527,
44
+ "learning_rate": 1.5624999999999999e-07,
45
+ "logits/chosen": -2.730905294418335,
46
+ "logits/rejected": -2.697235584259033,
47
+ "logps/chosen": -0.9896604418754578,
48
+ "logps/rejected": -1.1480659246444702,
49
+ "loss": 1.9874,
50
+ "rewards/accuracies": 0.643750011920929,
51
+ "rewards/chosen": -0.9896604418754578,
52
+ "rewards/margins": 0.15840543806552887,
53
+ "rewards/rejected": -1.1480659246444702,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.04187385501177702,
58
+ "grad_norm": 13.632313250241245,
59
+ "learning_rate": 2.0833333333333333e-07,
60
+ "logits/chosen": -2.8031985759735107,
61
+ "logits/rejected": -2.7098159790039062,
62
+ "logps/chosen": -1.022659420967102,
63
+ "logps/rejected": -1.1234548091888428,
64
+ "loss": 2.0265,
65
+ "rewards/accuracies": 0.550000011920929,
66
+ "rewards/chosen": -1.022659420967102,
67
+ "rewards/margins": 0.10079552233219147,
68
+ "rewards/rejected": -1.1234548091888428,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.05234231876472128,
73
+ "grad_norm": 14.107067164134795,
74
+ "learning_rate": 2.604166666666667e-07,
75
+ "logits/chosen": -2.799668073654175,
76
+ "logits/rejected": -2.7763009071350098,
77
+ "logps/chosen": -1.0291378498077393,
78
+ "logps/rejected": -1.086358904838562,
79
+ "loss": 2.0092,
80
+ "rewards/accuracies": 0.512499988079071,
81
+ "rewards/chosen": -1.0291378498077393,
82
+ "rewards/margins": 0.0572209358215332,
83
+ "rewards/rejected": -1.086358904838562,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06281078251766553,
88
+ "grad_norm": 15.048800842708138,
89
+ "learning_rate": 3.1249999999999997e-07,
90
+ "logits/chosen": -2.7735042572021484,
91
+ "logits/rejected": -2.731670379638672,
92
+ "logps/chosen": -0.9846929311752319,
93
+ "logps/rejected": -1.0904910564422607,
94
+ "loss": 2.0118,
95
+ "rewards/accuracies": 0.5375000238418579,
96
+ "rewards/chosen": -0.9846929311752319,
97
+ "rewards/margins": 0.10579802095890045,
98
+ "rewards/rejected": -1.0904910564422607,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07327924627060979,
103
+ "grad_norm": 14.073259274006203,
104
+ "learning_rate": 3.645833333333333e-07,
105
+ "logits/chosen": -2.777062177658081,
106
+ "logits/rejected": -2.690617084503174,
107
+ "logps/chosen": -1.0319979190826416,
108
+ "logps/rejected": -1.1718026399612427,
109
+ "loss": 1.9903,
110
+ "rewards/accuracies": 0.574999988079071,
111
+ "rewards/chosen": -1.0319979190826416,
112
+ "rewards/margins": 0.13980472087860107,
113
+ "rewards/rejected": -1.1718026399612427,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08374771002355404,
118
+ "grad_norm": 19.704149826171133,
119
+ "learning_rate": 4.1666666666666667e-07,
120
+ "logits/chosen": -2.7942392826080322,
121
+ "logits/rejected": -2.697408437728882,
122
+ "logps/chosen": -1.011974573135376,
123
+ "logps/rejected": -1.2997562885284424,
124
+ "loss": 1.9462,
125
+ "rewards/accuracies": 0.668749988079071,
126
+ "rewards/chosen": -1.011974573135376,
127
+ "rewards/margins": 0.28778162598609924,
128
+ "rewards/rejected": -1.2997562885284424,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.0942161737764983,
133
+ "grad_norm": 15.255628868525834,
134
+ "learning_rate": 4.6874999999999996e-07,
135
+ "logits/chosen": -2.805002450942993,
136
+ "logits/rejected": -2.7587850093841553,
137
+ "logps/chosen": -0.963559627532959,
138
+ "logps/rejected": -1.1423972845077515,
139
+ "loss": 1.9511,
140
+ "rewards/accuracies": 0.550000011920929,
141
+ "rewards/chosen": -0.963559627532959,
142
+ "rewards/margins": 0.17883776128292084,
143
+ "rewards/rejected": -1.1423972845077515,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.10468463752944256,
148
+ "grad_norm": 20.885465849075064,
149
+ "learning_rate": 4.999731868769026e-07,
150
+ "logits/chosen": -2.761730194091797,
151
+ "logits/rejected": -2.693643093109131,
152
+ "logps/chosen": -1.0126588344573975,
153
+ "logps/rejected": -1.3037517070770264,
154
+ "loss": 1.9653,
155
+ "rewards/accuracies": 0.6000000238418579,
156
+ "rewards/chosen": -1.0126588344573975,
157
+ "rewards/margins": 0.2910929024219513,
158
+ "rewards/rejected": -1.3037517070770264,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11515310128238682,
163
+ "grad_norm": 16.254626281156803,
164
+ "learning_rate": 4.996716052911017e-07,
165
+ "logits/chosen": -2.7590675354003906,
166
+ "logits/rejected": -2.723374843597412,
167
+ "logps/chosen": -1.0168770551681519,
168
+ "logps/rejected": -1.268347978591919,
169
+ "loss": 1.9612,
170
+ "rewards/accuracies": 0.5375000238418579,
171
+ "rewards/chosen": -1.0168770551681519,
172
+ "rewards/margins": 0.25147074460983276,
173
+ "rewards/rejected": -1.268347978591919,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.12562156503533106,
178
+ "grad_norm": 16.222896740457696,
179
+ "learning_rate": 4.990353313429303e-07,
180
+ "logits/chosen": -2.809765338897705,
181
+ "logits/rejected": -2.7633471488952637,
182
+ "logps/chosen": -1.0493232011795044,
183
+ "logps/rejected": -1.2437658309936523,
184
+ "loss": 1.9157,
185
+ "rewards/accuracies": 0.6187499761581421,
186
+ "rewards/chosen": -1.0493232011795044,
187
+ "rewards/margins": 0.1944427341222763,
188
+ "rewards/rejected": -1.2437658309936523,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.1360900287882753,
193
+ "grad_norm": 15.145405551888192,
194
+ "learning_rate": 4.980652179769217e-07,
195
+ "logits/chosen": -2.8015551567077637,
196
+ "logits/rejected": -2.6827645301818848,
197
+ "logps/chosen": -1.0214020013809204,
198
+ "logps/rejected": -1.5461061000823975,
199
+ "loss": 1.9028,
200
+ "rewards/accuracies": 0.706250011920929,
201
+ "rewards/chosen": -1.0214020013809204,
202
+ "rewards/margins": 0.524704098701477,
203
+ "rewards/rejected": -1.5461061000823975,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.14655849254121958,
208
+ "grad_norm": 20.7647978251983,
209
+ "learning_rate": 4.967625656594781e-07,
210
+ "logits/chosen": -2.6961591243743896,
211
+ "logits/rejected": -2.6422698497772217,
212
+ "logps/chosen": -1.0481222867965698,
213
+ "logps/rejected": -1.3449742794036865,
214
+ "loss": 1.9095,
215
+ "rewards/accuracies": 0.5874999761581421,
216
+ "rewards/chosen": -1.0481222867965698,
217
+ "rewards/margins": 0.29685190320014954,
218
+ "rewards/rejected": -1.3449742794036865,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.15702695629416383,
223
+ "grad_norm": 29.67977958863066,
224
+ "learning_rate": 4.951291206355559e-07,
225
+ "logits/chosen": -2.7507481575012207,
226
+ "logits/rejected": -2.6747162342071533,
227
+ "logps/chosen": -0.9930871725082397,
228
+ "logps/rejected": -1.354509711265564,
229
+ "loss": 1.8891,
230
+ "rewards/accuracies": 0.637499988079071,
231
+ "rewards/chosen": -0.9930871725082397,
232
+ "rewards/margins": 0.36142244935035706,
233
+ "rewards/rejected": -1.354509711265564,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.16749542004710807,
238
+ "grad_norm": 22.015004964913427,
239
+ "learning_rate": 4.93167072587771e-07,
240
+ "logits/chosen": -2.709141254425049,
241
+ "logits/rejected": -2.6435017585754395,
242
+ "logps/chosen": -0.9975327253341675,
243
+ "logps/rejected": -1.4075746536254883,
244
+ "loss": 1.9339,
245
+ "rewards/accuracies": 0.6625000238418579,
246
+ "rewards/chosen": -0.9975327253341675,
247
+ "rewards/margins": 0.4100419878959656,
248
+ "rewards/rejected": -1.4075746536254883,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.17796388380005235,
253
+ "grad_norm": 22.42041956383337,
254
+ "learning_rate": 4.908790517010636e-07,
255
+ "logits/chosen": -2.7113754749298096,
256
+ "logits/rejected": -2.6602649688720703,
257
+ "logps/chosen": -0.9959508776664734,
258
+ "logps/rejected": -1.3768701553344727,
259
+ "loss": 1.9555,
260
+ "rewards/accuracies": 0.6187499761581421,
261
+ "rewards/chosen": -0.9959508776664734,
262
+ "rewards/margins": 0.3809191882610321,
263
+ "rewards/rejected": -1.3768701553344727,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.1884323475529966,
268
+ "grad_norm": 21.065770503793715,
269
+ "learning_rate": 4.882681251368548e-07,
270
+ "logits/chosen": -2.689040184020996,
271
+ "logits/rejected": -2.6611132621765137,
272
+ "logps/chosen": -1.0262080430984497,
273
+ "logps/rejected": -1.4091228246688843,
274
+ "loss": 1.8793,
275
+ "rewards/accuracies": 0.675000011920929,
276
+ "rewards/chosen": -1.0262080430984497,
277
+ "rewards/margins": 0.38291481137275696,
278
+ "rewards/rejected": -1.4091228246688843,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.19890081130594087,
283
+ "grad_norm": 31.8448042024589,
284
+ "learning_rate": 4.853377929214243e-07,
285
+ "logits/chosen": -2.7642765045166016,
286
+ "logits/rejected": -2.6598925590515137,
287
+ "logps/chosen": -1.0126625299453735,
288
+ "logps/rejected": -1.3561102151870728,
289
+ "loss": 1.9092,
290
+ "rewards/accuracies": 0.59375,
291
+ "rewards/chosen": -1.0126625299453735,
292
+ "rewards/margins": 0.34344789385795593,
293
+ "rewards/rejected": -1.3561102151870728,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.2093692750588851,
298
+ "grad_norm": 25.05097837239479,
299
+ "learning_rate": 4.820919832540181e-07,
300
+ "logits/chosen": -2.6988279819488525,
301
+ "logits/rejected": -2.597813844680786,
302
+ "logps/chosen": -1.0824997425079346,
303
+ "logps/rejected": -1.5376174449920654,
304
+ "loss": 1.9333,
305
+ "rewards/accuracies": 0.5874999761581421,
306
+ "rewards/chosen": -1.0824997425079346,
307
+ "rewards/margins": 0.45511776208877563,
308
+ "rewards/rejected": -1.5376174449920654,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.21983773881182936,
313
+ "grad_norm": 26.762526766885564,
314
+ "learning_rate": 4.785350472409791e-07,
315
+ "logits/chosen": -2.709327220916748,
316
+ "logits/rejected": -2.6909279823303223,
317
+ "logps/chosen": -0.9367496371269226,
318
+ "logps/rejected": -1.3381364345550537,
319
+ "loss": 1.8988,
320
+ "rewards/accuracies": 0.6499999761581421,
321
+ "rewards/chosen": -0.9367496371269226,
322
+ "rewards/margins": 0.40138688683509827,
323
+ "rewards/rejected": -1.3381364345550537,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23030620256477363,
328
+ "grad_norm": 24.759397812808643,
329
+ "learning_rate": 4.7467175306295647e-07,
330
+ "logits/chosen": -2.785827398300171,
331
+ "logits/rejected": -2.7306325435638428,
332
+ "logps/chosen": -1.0359995365142822,
333
+ "logps/rejected": -1.4377586841583252,
334
+ "loss": 1.8787,
335
+ "rewards/accuracies": 0.6312500238418579,
336
+ "rewards/chosen": -1.0359995365142822,
337
+ "rewards/margins": 0.40175899863243103,
338
+ "rewards/rejected": -1.4377586841583252,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.24077466631771788,
343
+ "grad_norm": 22.275954156633127,
344
+ "learning_rate": 4.70507279583015e-07,
345
+ "logits/chosen": -2.734710693359375,
346
+ "logits/rejected": -2.67667818069458,
347
+ "logps/chosen": -1.0577763319015503,
348
+ "logps/rejected": -1.6186084747314453,
349
+ "loss": 1.875,
350
+ "rewards/accuracies": 0.7250000238418579,
351
+ "rewards/chosen": -1.0577763319015503,
352
+ "rewards/margins": 0.560832142829895,
353
+ "rewards/rejected": -1.6186084747314453,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2512431300706621,
358
+ "grad_norm": 31.253706152387053,
359
+ "learning_rate": 4.6604720940421207e-07,
360
+ "logits/chosen": -2.747194766998291,
361
+ "logits/rejected": -2.7159297466278076,
362
+ "logps/chosen": -1.061531662940979,
363
+ "logps/rejected": -1.4542839527130127,
364
+ "loss": 1.8991,
365
+ "rewards/accuracies": 0.6312500238418579,
366
+ "rewards/chosen": -1.061531662940979,
367
+ "rewards/margins": 0.39275234937667847,
368
+ "rewards/rejected": -1.4542839527130127,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.26171159382360637,
373
+ "grad_norm": 24.012313672135768,
374
+ "learning_rate": 4.612975213859487e-07,
375
+ "logits/chosen": -2.809326648712158,
376
+ "logits/rejected": -2.786160707473755,
377
+ "logps/chosen": -1.0037329196929932,
378
+ "logps/rejected": -1.2904164791107178,
379
+ "loss": 1.9171,
380
+ "rewards/accuracies": 0.59375,
381
+ "rewards/chosen": -1.0037329196929932,
382
+ "rewards/margins": 0.28668367862701416,
383
+ "rewards/rejected": -1.2904164791107178,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.2721800575765506,
388
+ "grad_norm": 27.105267597546742,
389
+ "learning_rate": 4.5626458262912735e-07,
390
+ "logits/chosen": -2.7714219093322754,
391
+ "logits/rejected": -2.7451789379119873,
392
+ "logps/chosen": -1.0449589490890503,
393
+ "logps/rejected": -1.2745070457458496,
394
+ "loss": 1.9054,
395
+ "rewards/accuracies": 0.6000000238418579,
396
+ "rewards/chosen": -1.0449589490890503,
397
+ "rewards/margins": 0.22954817116260529,
398
+ "rewards/rejected": -1.2745070457458496,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.2826485213294949,
403
+ "grad_norm": 34.82290559167317,
404
+ "learning_rate": 4.5095513994085974e-07,
405
+ "logits/chosen": -2.783876419067383,
406
+ "logits/rejected": -2.67991304397583,
407
+ "logps/chosen": -1.1126677989959717,
408
+ "logps/rejected": -1.8345043659210205,
409
+ "loss": 1.8811,
410
+ "rewards/accuracies": 0.7437499761581421,
411
+ "rewards/chosen": -1.1126677989959717,
412
+ "rewards/margins": 0.7218365669250488,
413
+ "rewards/rejected": -1.8345043659210205,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.29311698508243916,
418
+ "grad_norm": 25.33210409531245,
419
+ "learning_rate": 4.453763107901675e-07,
420
+ "logits/chosen": -2.8026270866394043,
421
+ "logits/rejected": -2.7463619709014893,
422
+ "logps/chosen": -1.0125950574874878,
423
+ "logps/rejected": -1.5290297269821167,
424
+ "loss": 1.815,
425
+ "rewards/accuracies": 0.699999988079071,
426
+ "rewards/chosen": -1.0125950574874878,
427
+ "rewards/margins": 0.5164345502853394,
428
+ "rewards/rejected": -1.5290297269821167,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.3035854488353834,
433
+ "grad_norm": 25.346225453192677,
434
+ "learning_rate": 4.395355737667985e-07,
435
+ "logits/chosen": -2.775475025177002,
436
+ "logits/rejected": -2.719919204711914,
437
+ "logps/chosen": -0.9933168292045593,
438
+ "logps/rejected": -1.3926680088043213,
439
+ "loss": 1.8662,
440
+ "rewards/accuracies": 0.65625,
441
+ "rewards/chosen": -0.9933168292045593,
442
+ "rewards/margins": 0.3993511199951172,
443
+ "rewards/rejected": -1.3926680088043213,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.31405391258832765,
448
+ "grad_norm": 25.05252990164211,
449
+ "learning_rate": 4.3344075855595097e-07,
450
+ "logits/chosen": -2.8103270530700684,
451
+ "logits/rejected": -2.7926547527313232,
452
+ "logps/chosen": -0.9610552787780762,
453
+ "logps/rejected": -1.3762198686599731,
454
+ "loss": 1.8355,
455
+ "rewards/accuracies": 0.59375,
456
+ "rewards/chosen": -0.9610552787780762,
457
+ "rewards/margins": 0.4151645302772522,
458
+ "rewards/rejected": -1.3762198686599731,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.3245223763412719,
463
+ "grad_norm": 27.37807184294238,
464
+ "learning_rate": 4.271000354423425e-07,
465
+ "logits/chosen": -2.7627320289611816,
466
+ "logits/rejected": -2.735795497894287,
467
+ "logps/chosen": -1.078357458114624,
468
+ "logps/rejected": -1.435006856918335,
469
+ "loss": 1.8878,
470
+ "rewards/accuracies": 0.6312500238418579,
471
+ "rewards/chosen": -1.078357458114624,
472
+ "rewards/margins": 0.3566494882106781,
473
+ "rewards/rejected": -1.435006856918335,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.33499084009421615,
478
+ "grad_norm": 31.453776336135004,
479
+ "learning_rate": 4.2052190435769554e-07,
480
+ "logits/chosen": -2.744175434112549,
481
+ "logits/rejected": -2.718656063079834,
482
+ "logps/chosen": -1.1089026927947998,
483
+ "logps/rejected": -1.5105451345443726,
484
+ "loss": 1.893,
485
+ "rewards/accuracies": 0.637499988079071,
486
+ "rewards/chosen": -1.1089026927947998,
487
+ "rewards/margins": 0.4016422629356384,
488
+ "rewards/rejected": -1.5105451345443726,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.34545930384716045,
493
+ "grad_norm": 25.427022864790626,
494
+ "learning_rate": 4.137151834863213e-07,
495
+ "logits/chosen": -2.7565693855285645,
496
+ "logits/rejected": -2.6773271560668945,
497
+ "logps/chosen": -0.9760361909866333,
498
+ "logps/rejected": -1.4186967611312866,
499
+ "loss": 1.8368,
500
+ "rewards/accuracies": 0.6187499761581421,
501
+ "rewards/chosen": -0.9760361909866333,
502
+ "rewards/margins": 0.4426605701446533,
503
+ "rewards/rejected": -1.4186967611312866,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3559277676001047,
508
+ "grad_norm": 25.0313872723157,
509
+ "learning_rate": 4.0668899744407567e-07,
510
+ "logits/chosen": -2.7782142162323,
511
+ "logits/rejected": -2.706545829772949,
512
+ "logps/chosen": -1.0534151792526245,
513
+ "logps/rejected": -1.450411081314087,
514
+ "loss": 1.8695,
515
+ "rewards/accuracies": 0.637499988079071,
516
+ "rewards/chosen": -1.0534151792526245,
517
+ "rewards/margins": 0.39699599146842957,
518
+ "rewards/rejected": -1.450411081314087,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.36639623135304894,
523
+ "grad_norm": 22.99470630834903,
524
+ "learning_rate": 3.994527650465352e-07,
525
+ "logits/chosen": -2.7585906982421875,
526
+ "logits/rejected": -2.6691181659698486,
527
+ "logps/chosen": -1.0702944993972778,
528
+ "logps/rejected": -1.4621968269348145,
529
+ "loss": 1.8958,
530
+ "rewards/accuracies": 0.6187499761581421,
531
+ "rewards/chosen": -1.0702944993972778,
532
+ "rewards/margins": 0.39190229773521423,
533
+ "rewards/rejected": -1.4621968269348145,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.3768646951059932,
538
+ "grad_norm": 25.69330171727391,
539
+ "learning_rate": 3.920161866827889e-07,
540
+ "logits/chosen": -2.740964889526367,
541
+ "logits/rejected": -2.7247314453125,
542
+ "logps/chosen": -1.0360349416732788,
543
+ "logps/rejected": -1.5588700771331787,
544
+ "loss": 1.8488,
545
+ "rewards/accuracies": 0.6625000238418579,
546
+ "rewards/chosen": -1.0360349416732788,
547
+ "rewards/margins": 0.5228349566459656,
548
+ "rewards/rejected": -1.5588700771331787,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.38733315885893743,
553
+ "grad_norm": 26.206907546340837,
554
+ "learning_rate": 3.8438923131177237e-07,
555
+ "logits/chosen": -2.7401633262634277,
556
+ "logits/rejected": -2.637202501296997,
557
+ "logps/chosen": -1.0996856689453125,
558
+ "logps/rejected": -1.7466999292373657,
559
+ "loss": 1.8192,
560
+ "rewards/accuracies": 0.643750011920929,
561
+ "rewards/chosen": -1.0996856689453125,
562
+ "rewards/margins": 0.6470142602920532,
563
+ "rewards/rejected": -1.7466999292373657,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.39780162261188173,
568
+ "grad_norm": 27.521588311939052,
569
+ "learning_rate": 3.765821230985757e-07,
570
+ "logits/chosen": -2.743375301361084,
571
+ "logits/rejected": -2.69993257522583,
572
+ "logps/chosen": -1.086106300354004,
573
+ "logps/rejected": -1.5462232828140259,
574
+ "loss": 1.9254,
575
+ "rewards/accuracies": 0.643750011920929,
576
+ "rewards/chosen": -1.086106300354004,
577
+ "rewards/margins": 0.4601168632507324,
578
+ "rewards/rejected": -1.5462232828140259,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.408270086364826,
583
+ "grad_norm": 27.446157471379898,
584
+ "learning_rate": 3.6860532770864005e-07,
585
+ "logits/chosen": -2.684860944747925,
586
+ "logits/rejected": -2.650524616241455,
587
+ "logps/chosen": -1.0963340997695923,
588
+ "logps/rejected": -1.4702621698379517,
589
+ "loss": 1.8975,
590
+ "rewards/accuracies": 0.65625,
591
+ "rewards/chosen": -1.0963340997695923,
592
+ "rewards/margins": 0.3739281892776489,
593
+ "rewards/rejected": -1.4702621698379517,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.4187385501177702,
598
+ "grad_norm": 24.602486055800032,
599
+ "learning_rate": 3.604695382782159e-07,
600
+ "logits/chosen": -2.7188162803649902,
601
+ "logits/rejected": -2.712054967880249,
602
+ "logps/chosen": -1.0557594299316406,
603
+ "logps/rejected": -1.4215106964111328,
604
+ "loss": 1.8755,
605
+ "rewards/accuracies": 0.6312500238418579,
606
+ "rewards/chosen": -1.0557594299316406,
607
+ "rewards/margins": 0.36575111746788025,
608
+ "rewards/rejected": -1.4215106964111328,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.42920701387071447,
613
+ "grad_norm": 27.200176778512795,
614
+ "learning_rate": 3.5218566107988867e-07,
615
+ "logits/chosen": -2.6477105617523193,
616
+ "logits/rejected": -2.5724520683288574,
617
+ "logps/chosen": -0.9946632385253906,
618
+ "logps/rejected": -1.4712902307510376,
619
+ "loss": 1.8403,
620
+ "rewards/accuracies": 0.625,
621
+ "rewards/chosen": -0.9946632385253906,
622
+ "rewards/margins": 0.4766268730163574,
623
+ "rewards/rejected": -1.4712902307510376,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.4396754776236587,
628
+ "grad_norm": 36.0559472403249,
629
+ "learning_rate": 3.4376480090239047e-07,
630
+ "logits/chosen": -2.657755136489868,
631
+ "logits/rejected": -2.61205792427063,
632
+ "logps/chosen": -1.0976860523223877,
633
+ "logps/rejected": -1.4535160064697266,
634
+ "loss": 1.8803,
635
+ "rewards/accuracies": 0.606249988079071,
636
+ "rewards/chosen": -1.0976860523223877,
637
+ "rewards/margins": 0.35582998394966125,
638
+ "rewards/rejected": -1.4535160064697266,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.45014394137660296,
643
+ "grad_norm": 22.419086184833272,
644
+ "learning_rate": 3.3521824616429284e-07,
645
+ "logits/chosen": -2.690389633178711,
646
+ "logits/rejected": -2.669494152069092,
647
+ "logps/chosen": -0.9983667135238647,
648
+ "logps/rejected": -1.5212194919586182,
649
+ "loss": 1.8208,
650
+ "rewards/accuracies": 0.800000011920929,
651
+ "rewards/chosen": -0.9983667135238647,
652
+ "rewards/margins": 0.5228530168533325,
653
+ "rewards/rejected": -1.5212194919586182,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.46061240512954726,
658
+ "grad_norm": 30.606607589341355,
659
+ "learning_rate": 3.265574537815398e-07,
660
+ "logits/chosen": -2.7263293266296387,
661
+ "logits/rejected": -2.649702787399292,
662
+ "logps/chosen": -1.0452382564544678,
663
+ "logps/rejected": -1.5576632022857666,
664
+ "loss": 1.8431,
665
+ "rewards/accuracies": 0.65625,
666
+ "rewards/chosen": -1.0452382564544678,
667
+ "rewards/margins": 0.5124249458312988,
668
+ "rewards/rejected": -1.5576632022857666,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.4710808688824915,
673
+ "grad_norm": 27.672871069441197,
674
+ "learning_rate": 3.1779403380910425e-07,
675
+ "logits/chosen": -2.7160162925720215,
676
+ "logits/rejected": -2.6121773719787598,
677
+ "logps/chosen": -1.0075920820236206,
678
+ "logps/rejected": -1.576601505279541,
679
+ "loss": 1.8271,
680
+ "rewards/accuracies": 0.6312500238418579,
681
+ "rewards/chosen": -1.0075920820236206,
682
+ "rewards/margins": 0.5690094232559204,
683
+ "rewards/rejected": -1.576601505279541,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.48154933263543576,
688
+ "grad_norm": 25.08698759897845,
689
+ "learning_rate": 3.0893973387735683e-07,
690
+ "logits/chosen": -2.7268662452697754,
691
+ "logits/rejected": -2.6340160369873047,
692
+ "logps/chosen": -1.0295268297195435,
693
+ "logps/rejected": -1.7138006687164307,
694
+ "loss": 1.8333,
695
+ "rewards/accuracies": 0.706250011920929,
696
+ "rewards/chosen": -1.0295268297195435,
697
+ "rewards/margins": 0.6842738389968872,
698
+ "rewards/rejected": -1.7138006687164307,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.49201779638838,
703
+ "grad_norm": 24.9727125758065,
704
+ "learning_rate": 3.000064234440111e-07,
705
+ "logits/chosen": -2.7256393432617188,
706
+ "logits/rejected": -2.67500638961792,
707
+ "logps/chosen": -1.0034698247909546,
708
+ "logps/rejected": -1.5250154733657837,
709
+ "loss": 1.8603,
710
+ "rewards/accuracies": 0.7250000238418579,
711
+ "rewards/chosen": -1.0034698247909546,
712
+ "rewards/margins": 0.5215455889701843,
713
+ "rewards/rejected": -1.5250154733657837,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5024862601413242,
718
+ "grad_norm": 23.709236995530965,
719
+ "learning_rate": 2.910060778827554e-07,
720
+ "logits/chosen": -2.667459011077881,
721
+ "logits/rejected": -2.622892379760742,
722
+ "logps/chosen": -0.998893141746521,
723
+ "logps/rejected": -1.5178442001342773,
724
+ "loss": 1.8707,
725
+ "rewards/accuracies": 0.6499999761581421,
726
+ "rewards/chosen": -0.998893141746521,
727
+ "rewards/margins": 0.5189512372016907,
728
+ "rewards/rejected": -1.5178442001342773,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5129547238942685,
733
+ "grad_norm": 23.55356072022147,
734
+ "learning_rate": 2.8195076242990116e-07,
735
+ "logits/chosen": -2.6935830116271973,
736
+ "logits/rejected": -2.5973896980285645,
737
+ "logps/chosen": -1.1026113033294678,
738
+ "logps/rejected": -1.5293716192245483,
739
+ "loss": 1.8533,
740
+ "rewards/accuracies": 0.637499988079071,
741
+ "rewards/chosen": -1.1026113033294678,
742
+ "rewards/margins": 0.4267602562904358,
743
+ "rewards/rejected": -1.5293716192245483,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.5234231876472127,
748
+ "grad_norm": 33.32048093164131,
749
+ "learning_rate": 2.7285261601056697e-07,
750
+ "logits/chosen": -2.5986247062683105,
751
+ "logits/rejected": -2.545224905014038,
752
+ "logps/chosen": -1.019071340560913,
753
+ "logps/rejected": -1.5590027570724487,
754
+ "loss": 1.8581,
755
+ "rewards/accuracies": 0.6812499761581421,
756
+ "rewards/chosen": -1.019071340560913,
757
+ "rewards/margins": 0.5399314761161804,
758
+ "rewards/rejected": -1.5590027570724487,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.533891651400157,
763
+ "grad_norm": 24.969288713955503,
764
+ "learning_rate": 2.6372383496608186e-07,
765
+ "logits/chosen": -2.647831678390503,
766
+ "logits/rejected": -2.5525565147399902,
767
+ "logps/chosen": -1.0960899591445923,
768
+ "logps/rejected": -1.7084300518035889,
769
+ "loss": 1.7984,
770
+ "rewards/accuracies": 0.668749988079071,
771
+ "rewards/chosen": -1.0960899591445923,
772
+ "rewards/margins": 0.6123402714729309,
773
+ "rewards/rejected": -1.7084300518035889,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5443601151531012,
778
+ "grad_norm": 24.978593158166646,
779
+ "learning_rate": 2.5457665670441937e-07,
780
+ "logits/chosen": -2.6099724769592285,
781
+ "logits/rejected": -2.503551959991455,
782
+ "logps/chosen": -0.94499671459198,
783
+ "logps/rejected": -1.6384252309799194,
784
+ "loss": 1.8396,
785
+ "rewards/accuracies": 0.699999988079071,
786
+ "rewards/chosen": -0.94499671459198,
787
+ "rewards/margins": 0.6934284567832947,
788
+ "rewards/rejected": -1.6384252309799194,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5548285789060455,
793
+ "grad_norm": 27.898305291163492,
794
+ "learning_rate": 2.454233432955807e-07,
795
+ "logits/chosen": -2.661271095275879,
796
+ "logits/rejected": -2.6026952266693115,
797
+ "logps/chosen": -1.0296385288238525,
798
+ "logps/rejected": -1.382299780845642,
799
+ "loss": 1.8101,
800
+ "rewards/accuracies": 0.6812499761581421,
801
+ "rewards/chosen": -1.0296385288238525,
802
+ "rewards/margins": 0.3526611924171448,
803
+ "rewards/rejected": -1.382299780845642,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.5652970426589898,
808
+ "grad_norm": 35.74021390544709,
809
+ "learning_rate": 2.3627616503391812e-07,
810
+ "logits/chosen": -2.6500651836395264,
811
+ "logits/rejected": -2.5953967571258545,
812
+ "logps/chosen": -1.1358740329742432,
813
+ "logps/rejected": -1.5125305652618408,
814
+ "loss": 1.8849,
815
+ "rewards/accuracies": 0.6625000238418579,
816
+ "rewards/chosen": -1.1358740329742432,
817
+ "rewards/margins": 0.376656711101532,
818
+ "rewards/rejected": -1.5125305652618408,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.575765506411934,
823
+ "grad_norm": 25.432184339952187,
824
+ "learning_rate": 2.2714738398943308e-07,
825
+ "logits/chosen": -2.7251439094543457,
826
+ "logits/rejected": -2.6094861030578613,
827
+ "logps/chosen": -1.018061637878418,
828
+ "logps/rejected": -1.627947449684143,
829
+ "loss": 1.8328,
830
+ "rewards/accuracies": 0.675000011920929,
831
+ "rewards/chosen": -1.018061637878418,
832
+ "rewards/margins": 0.6098858118057251,
833
+ "rewards/rejected": -1.627947449684143,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.5862339701648783,
838
+ "grad_norm": 23.87099932259008,
839
+ "learning_rate": 2.1804923757009882e-07,
840
+ "logits/chosen": -2.746220827102661,
841
+ "logits/rejected": -2.6774742603302,
842
+ "logps/chosen": -0.9781770706176758,
843
+ "logps/rejected": -1.3979579210281372,
844
+ "loss": 1.8368,
845
+ "rewards/accuracies": 0.6812499761581421,
846
+ "rewards/chosen": -0.9781770706176758,
847
+ "rewards/margins": 0.4197807312011719,
848
+ "rewards/rejected": -1.3979579210281372,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.5967024339178225,
853
+ "grad_norm": 26.340595120664386,
854
+ "learning_rate": 2.089939221172446e-07,
855
+ "logits/chosen": -2.6835036277770996,
856
+ "logits/rejected": -2.6886842250823975,
857
+ "logps/chosen": -1.0875818729400635,
858
+ "logps/rejected": -1.583901047706604,
859
+ "loss": 1.8233,
860
+ "rewards/accuracies": 0.6937500238418579,
861
+ "rewards/chosen": -1.0875818729400635,
862
+ "rewards/margins": 0.49631914496421814,
863
+ "rewards/rejected": -1.583901047706604,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6071708976707668,
868
+ "grad_norm": 29.695224998335657,
869
+ "learning_rate": 1.9999357655598891e-07,
870
+ "logits/chosen": -2.7280991077423096,
871
+ "logits/rejected": -2.6861159801483154,
872
+ "logps/chosen": -1.0748018026351929,
873
+ "logps/rejected": -1.6494481563568115,
874
+ "loss": 1.8022,
875
+ "rewards/accuracies": 0.668749988079071,
876
+ "rewards/chosen": -1.0748018026351929,
877
+ "rewards/margins": 0.5746463537216187,
878
+ "rewards/rejected": -1.6494481563568115,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6176393614237111,
883
+ "grad_norm": 29.67617284412597,
884
+ "learning_rate": 1.9106026612264315e-07,
885
+ "logits/chosen": -2.7601213455200195,
886
+ "logits/rejected": -2.6855008602142334,
887
+ "logps/chosen": -1.0902409553527832,
888
+ "logps/rejected": -1.6281505823135376,
889
+ "loss": 1.8578,
890
+ "rewards/accuracies": 0.706250011920929,
891
+ "rewards/chosen": -1.0902409553527832,
892
+ "rewards/margins": 0.5379096269607544,
893
+ "rewards/rejected": -1.6281505823135376,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6281078251766553,
898
+ "grad_norm": 27.162465615999373,
899
+ "learning_rate": 1.8220596619089573e-07,
900
+ "logits/chosen": -2.66314435005188,
901
+ "logits/rejected": -2.6144497394561768,
902
+ "logps/chosen": -1.0360552072525024,
903
+ "logps/rejected": -1.5152963399887085,
904
+ "loss": 1.8344,
905
+ "rewards/accuracies": 0.6937500238418579,
906
+ "rewards/chosen": -1.0360552072525024,
907
+ "rewards/margins": 0.47924113273620605,
908
+ "rewards/rejected": -1.5152963399887085,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6385762889295996,
913
+ "grad_norm": 31.001026793963305,
914
+ "learning_rate": 1.7344254621846017e-07,
915
+ "logits/chosen": -2.6350555419921875,
916
+ "logits/rejected": -2.5956974029541016,
917
+ "logps/chosen": -1.0529329776763916,
918
+ "logps/rejected": -1.6219732761383057,
919
+ "loss": 1.8196,
920
+ "rewards/accuracies": 0.6875,
921
+ "rewards/chosen": -1.0529329776763916,
922
+ "rewards/margins": 0.5690402388572693,
923
+ "rewards/rejected": -1.6219732761383057,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6490447526825438,
928
+ "grad_norm": 27.186267806704134,
929
+ "learning_rate": 1.647817538357072e-07,
930
+ "logits/chosen": -2.646355390548706,
931
+ "logits/rejected": -2.649137258529663,
932
+ "logps/chosen": -0.9727001190185547,
933
+ "logps/rejected": -1.5282304286956787,
934
+ "loss": 1.8154,
935
+ "rewards/accuracies": 0.699999988079071,
936
+ "rewards/chosen": -0.9727001190185547,
937
+ "rewards/margins": 0.5555303692817688,
938
+ "rewards/rejected": -1.5282304286956787,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6595132164354881,
943
+ "grad_norm": 33.037660975429695,
944
+ "learning_rate": 1.562351990976095e-07,
945
+ "logits/chosen": -2.666133403778076,
946
+ "logits/rejected": -2.6141715049743652,
947
+ "logps/chosen": -0.9768770933151245,
948
+ "logps/rejected": -1.6563736200332642,
949
+ "loss": 1.819,
950
+ "rewards/accuracies": 0.731249988079071,
951
+ "rewards/chosen": -0.9768770933151245,
952
+ "rewards/margins": 0.6794965863227844,
953
+ "rewards/rejected": -1.6563736200332642,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6699816801884323,
958
+ "grad_norm": 37.124618715177,
959
+ "learning_rate": 1.478143389201113e-07,
960
+ "logits/chosen": -2.6524291038513184,
961
+ "logits/rejected": -2.6353344917297363,
962
+ "logps/chosen": -1.0379709005355835,
963
+ "logps/rejected": -1.5560357570648193,
964
+ "loss": 1.7814,
965
+ "rewards/accuracies": 0.6812499761581421,
966
+ "rewards/chosen": -1.0379709005355835,
967
+ "rewards/margins": 0.5180650353431702,
968
+ "rewards/rejected": -1.5560357570648193,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.6804501439413766,
973
+ "grad_norm": 29.546811615709533,
974
+ "learning_rate": 1.3953046172178413e-07,
975
+ "logits/chosen": -2.6703402996063232,
976
+ "logits/rejected": -2.5877861976623535,
977
+ "logps/chosen": -1.0295711755752563,
978
+ "logps/rejected": -1.6383397579193115,
979
+ "loss": 1.7933,
980
+ "rewards/accuracies": 0.675000011920929,
981
+ "rewards/chosen": -1.0295711755752563,
982
+ "rewards/margins": 0.6087687611579895,
983
+ "rewards/rejected": -1.6383397579193115,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.6909186076943209,
988
+ "grad_norm": 27.130577131118542,
989
+ "learning_rate": 1.3139467229135998e-07,
990
+ "logits/chosen": -2.6374616622924805,
991
+ "logits/rejected": -2.5912885665893555,
992
+ "logps/chosen": -1.0082510709762573,
993
+ "logps/rejected": -1.3762824535369873,
994
+ "loss": 1.8378,
995
+ "rewards/accuracies": 0.625,
996
+ "rewards/chosen": -1.0082510709762573,
997
+ "rewards/margins": 0.36803150177001953,
998
+ "rewards/rejected": -1.3762824535369873,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7013870714472651,
1003
+ "grad_norm": 26.495064774873583,
1004
+ "learning_rate": 1.2341787690142435e-07,
1005
+ "logits/chosen": -2.751105308532715,
1006
+ "logits/rejected": -2.673309564590454,
1007
+ "logps/chosen": -0.9556055068969727,
1008
+ "logps/rejected": -1.5157105922698975,
1009
+ "loss": 1.8293,
1010
+ "rewards/accuracies": 0.6812499761581421,
1011
+ "rewards/chosen": -0.9556055068969727,
1012
+ "rewards/margins": 0.56010502576828,
1013
+ "rewards/rejected": -1.5157105922698975,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7118555352002094,
1018
+ "grad_norm": 26.629021066262204,
1019
+ "learning_rate": 1.1561076868822755e-07,
1020
+ "logits/chosen": -2.6683545112609863,
1021
+ "logits/rejected": -2.600292921066284,
1022
+ "logps/chosen": -1.1952508687973022,
1023
+ "logps/rejected": -1.6229918003082275,
1024
+ "loss": 1.8878,
1025
+ "rewards/accuracies": 0.6812499761581421,
1026
+ "rewards/chosen": -1.1952508687973022,
1027
+ "rewards/margins": 0.4277407228946686,
1028
+ "rewards/rejected": -1.6229918003082275,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.7223239989531536,
1033
+ "grad_norm": 34.902511984640945,
1034
+ "learning_rate": 1.0798381331721107e-07,
1035
+ "logits/chosen": -2.702152729034424,
1036
+ "logits/rejected": -2.656289577484131,
1037
+ "logps/chosen": -1.0419316291809082,
1038
+ "logps/rejected": -1.6374496221542358,
1039
+ "loss": 1.8455,
1040
+ "rewards/accuracies": 0.625,
1041
+ "rewards/chosen": -1.0419316291809082,
1042
+ "rewards/margins": 0.5955179929733276,
1043
+ "rewards/rejected": -1.6374496221542358,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7327924627060979,
1048
+ "grad_norm": 30.383520283042905,
1049
+ "learning_rate": 1.0054723495346482e-07,
1050
+ "logits/chosen": -2.6637139320373535,
1051
+ "logits/rejected": -2.640423536300659,
1052
+ "logps/chosen": -1.0635532140731812,
1053
+ "logps/rejected": -1.55173659324646,
1054
+ "loss": 1.8762,
1055
+ "rewards/accuracies": 0.6312500238418579,
1056
+ "rewards/chosen": -1.0635532140731812,
1057
+ "rewards/margins": 0.4881834387779236,
1058
+ "rewards/rejected": -1.55173659324646,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7432609264590422,
1063
+ "grad_norm": 28.202614006747883,
1064
+ "learning_rate": 9.331100255592436e-08,
1065
+ "logits/chosen": -2.672135591506958,
1066
+ "logits/rejected": -2.614642858505249,
1067
+ "logps/chosen": -0.9285499453544617,
1068
+ "logps/rejected": -1.6109098196029663,
1069
+ "loss": 1.7749,
1070
+ "rewards/accuracies": 0.75,
1071
+ "rewards/chosen": -0.9285499453544617,
1072
+ "rewards/margins": 0.6823598146438599,
1073
+ "rewards/rejected": -1.6109098196029663,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7537293902119864,
1078
+ "grad_norm": 23.48852239281184,
1079
+ "learning_rate": 8.628481651367875e-08,
1080
+ "logits/chosen": -2.701026439666748,
1081
+ "logits/rejected": -2.645697832107544,
1082
+ "logps/chosen": -0.9583543539047241,
1083
+ "logps/rejected": -1.4256336688995361,
1084
+ "loss": 1.7696,
1085
+ "rewards/accuracies": 0.6625000238418579,
1086
+ "rewards/chosen": -0.9583543539047241,
1087
+ "rewards/margins": 0.46727919578552246,
1088
+ "rewards/rejected": -1.4256336688995361,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.7641978539649307,
1093
+ "grad_norm": 29.4764609142287,
1094
+ "learning_rate": 7.947809564230445e-08,
1095
+ "logits/chosen": -2.6285886764526367,
1096
+ "logits/rejected": -2.5465035438537598,
1097
+ "logps/chosen": -1.07431960105896,
1098
+ "logps/rejected": -1.6673939228057861,
1099
+ "loss": 1.854,
1100
+ "rewards/accuracies": 0.7250000238418579,
1101
+ "rewards/chosen": -1.07431960105896,
1102
+ "rewards/margins": 0.5930741429328918,
1103
+ "rewards/rejected": -1.6673939228057861,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7746663177178749,
1108
+ "grad_norm": 32.53243633682995,
1109
+ "learning_rate": 7.289996455765748e-08,
1110
+ "logits/chosen": -2.672539234161377,
1111
+ "logits/rejected": -2.612757682800293,
1112
+ "logps/chosen": -1.0804438591003418,
1113
+ "logps/rejected": -1.7286722660064697,
1114
+ "loss": 1.8244,
1115
+ "rewards/accuracies": 0.699999988079071,
1116
+ "rewards/chosen": -1.0804438591003418,
1117
+ "rewards/margins": 0.6482284069061279,
1118
+ "rewards/rejected": -1.7286722660064697,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.7851347814708192,
1123
+ "grad_norm": 26.086052446415493,
1124
+ "learning_rate": 6.655924144404906e-08,
1125
+ "logits/chosen": -2.656698226928711,
1126
+ "logits/rejected": -2.681257724761963,
1127
+ "logps/chosen": -1.0645740032196045,
1128
+ "logps/rejected": -1.5776240825653076,
1129
+ "loss": 1.8108,
1130
+ "rewards/accuracies": 0.612500011920929,
1131
+ "rewards/chosen": -1.0645740032196045,
1132
+ "rewards/margins": 0.5130501985549927,
1133
+ "rewards/rejected": -1.5776240825653076,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.7956032452237635,
1138
+ "grad_norm": 29.301563375037563,
1139
+ "learning_rate": 6.046442623320145e-08,
1140
+ "logits/chosen": -2.6668169498443604,
1141
+ "logits/rejected": -2.6132140159606934,
1142
+ "logps/chosen": -1.0790109634399414,
1143
+ "logps/rejected": -1.5554571151733398,
1144
+ "loss": 1.782,
1145
+ "rewards/accuracies": 0.675000011920929,
1146
+ "rewards/chosen": -1.0790109634399414,
1147
+ "rewards/margins": 0.47644609212875366,
1148
+ "rewards/rejected": -1.5554571151733398,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.8060717089767077,
1153
+ "grad_norm": 24.668280208736856,
1154
+ "learning_rate": 5.4623689209832484e-08,
1155
+ "logits/chosen": -2.677908420562744,
1156
+ "logits/rejected": -2.607048511505127,
1157
+ "logps/chosen": -1.0273312330245972,
1158
+ "logps/rejected": -1.5443226099014282,
1159
+ "loss": 1.7947,
1160
+ "rewards/accuracies": 0.6187499761581421,
1161
+ "rewards/chosen": -1.0273312330245972,
1162
+ "rewards/margins": 0.5169912576675415,
1163
+ "rewards/rejected": -1.5443226099014282,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.816540172729652,
1168
+ "grad_norm": 27.191462805016396,
1169
+ "learning_rate": 4.904486005914027e-08,
1170
+ "logits/chosen": -2.7038891315460205,
1171
+ "logits/rejected": -2.6414623260498047,
1172
+ "logps/chosen": -1.0105482339859009,
1173
+ "logps/rejected": -1.7210209369659424,
1174
+ "loss": 1.7734,
1175
+ "rewards/accuracies": 0.71875,
1176
+ "rewards/chosen": -1.0105482339859009,
1177
+ "rewards/margins": 0.7104724645614624,
1178
+ "rewards/rejected": -1.7210209369659424,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8270086364825961,
1183
+ "grad_norm": 31.43323955162571,
1184
+ "learning_rate": 4.373541737087263e-08,
1185
+ "logits/chosen": -2.636841058731079,
1186
+ "logits/rejected": -2.556833267211914,
1187
+ "logps/chosen": -1.0063461065292358,
1188
+ "logps/rejected": -1.5682775974273682,
1189
+ "loss": 1.8075,
1190
+ "rewards/accuracies": 0.7437499761581421,
1191
+ "rewards/chosen": -1.0063461065292358,
1192
+ "rewards/margins": 0.5619313716888428,
1193
+ "rewards/rejected": -1.5682775974273682,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8374771002355405,
1198
+ "grad_norm": 39.225726689241675,
1199
+ "learning_rate": 3.8702478614051345e-08,
1200
+ "logits/chosen": -2.6019065380096436,
1201
+ "logits/rejected": -2.5374197959899902,
1202
+ "logps/chosen": -0.9893720746040344,
1203
+ "logps/rejected": -1.5351721048355103,
1204
+ "loss": 1.8109,
1205
+ "rewards/accuracies": 0.6812499761581421,
1206
+ "rewards/chosen": -0.9893720746040344,
1207
+ "rewards/margins": 0.5458000898361206,
1208
+ "rewards/rejected": -1.5351721048355103,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8479455639884846,
1213
+ "grad_norm": 42.21715206184894,
1214
+ "learning_rate": 3.3952790595787986e-08,
1215
+ "logits/chosen": -2.6662096977233887,
1216
+ "logits/rejected": -2.62931489944458,
1217
+ "logps/chosen": -1.0822862386703491,
1218
+ "logps/rejected": -1.6576595306396484,
1219
+ "loss": 1.8405,
1220
+ "rewards/accuracies": 0.637499988079071,
1221
+ "rewards/chosen": -1.0822862386703491,
1222
+ "rewards/margins": 0.5753732323646545,
1223
+ "rewards/rejected": -1.6576595306396484,
1224
+ "step": 405
1225
+ },
1226
+ {
1227
+ "epoch": 0.8584140277414289,
1228
+ "grad_norm": 35.10610264317854,
1229
+ "learning_rate": 2.9492720416985e-08,
1230
+ "logits/chosen": -2.678342819213867,
1231
+ "logits/rejected": -2.634387493133545,
1232
+ "logps/chosen": -0.9690961837768555,
1233
+ "logps/rejected": -1.4596083164215088,
1234
+ "loss": 1.8145,
1235
+ "rewards/accuracies": 0.65625,
1236
+ "rewards/chosen": -0.9690961837768555,
1237
+ "rewards/margins": 0.4905119836330414,
1238
+ "rewards/rejected": -1.4596083164215088,
1239
+ "step": 410
1240
+ },
1241
+ {
1242
+ "epoch": 0.8688824914943732,
1243
+ "grad_norm": 27.87180494304035,
1244
+ "learning_rate": 2.5328246937043525e-08,
1245
+ "logits/chosen": -2.702768564224243,
1246
+ "logits/rejected": -2.636719226837158,
1247
+ "logps/chosen": -1.0192323923110962,
1248
+ "logps/rejected": -1.6251684427261353,
1249
+ "loss": 1.77,
1250
+ "rewards/accuracies": 0.6875,
1251
+ "rewards/chosen": -1.0192323923110962,
1252
+ "rewards/margins": 0.6059359312057495,
1253
+ "rewards/rejected": -1.6251684427261353,
1254
+ "step": 415
1255
+ },
1256
+ {
1257
+ "epoch": 0.8793509552473174,
1258
+ "grad_norm": 25.60878775790235,
1259
+ "learning_rate": 2.1464952759020856e-08,
1260
+ "logits/chosen": -2.6637589931488037,
1261
+ "logits/rejected": -2.6058096885681152,
1262
+ "logps/chosen": -1.0046476125717163,
1263
+ "logps/rejected": -1.5859066247940063,
1264
+ "loss": 1.8408,
1265
+ "rewards/accuracies": 0.65625,
1266
+ "rewards/chosen": -1.0046476125717163,
1267
+ "rewards/margins": 0.5812588930130005,
1268
+ "rewards/rejected": -1.5859066247940063,
1269
+ "step": 420
1270
+ },
1271
+ {
1272
+ "epoch": 0.8898194190002617,
1273
+ "grad_norm": 34.39189970937955,
1274
+ "learning_rate": 1.7908016745981856e-08,
1275
+ "logits/chosen": -2.6160888671875,
1276
+ "logits/rejected": -2.5980353355407715,
1277
+ "logps/chosen": -1.1391981840133667,
1278
+ "logps/rejected": -1.5944236516952515,
1279
+ "loss": 1.8251,
1280
+ "rewards/accuracies": 0.625,
1281
+ "rewards/chosen": -1.1391981840133667,
1282
+ "rewards/margins": 0.4552256464958191,
1283
+ "rewards/rejected": -1.5944236516952515,
1284
+ "step": 425
1285
+ },
1286
+ {
1287
+ "epoch": 0.9002878827532059,
1288
+ "grad_norm": 33.16075597765061,
1289
+ "learning_rate": 1.4662207078575684e-08,
1290
+ "logits/chosen": -2.6214401721954346,
1291
+ "logits/rejected": -2.570112705230713,
1292
+ "logps/chosen": -1.0948253870010376,
1293
+ "logps/rejected": -1.6313488483428955,
1294
+ "loss": 1.8008,
1295
+ "rewards/accuracies": 0.65625,
1296
+ "rewards/chosen": -1.0948253870010376,
1297
+ "rewards/margins": 0.5365234613418579,
1298
+ "rewards/rejected": -1.6313488483428955,
1299
+ "step": 430
1300
+ },
1301
+ {
1302
+ "epoch": 0.9107563465061502,
1303
+ "grad_norm": 33.93315468108953,
1304
+ "learning_rate": 1.1731874863145142e-08,
1305
+ "logits/chosen": -2.6755282878875732,
1306
+ "logits/rejected": -2.637303590774536,
1307
+ "logps/chosen": -1.0409172773361206,
1308
+ "logps/rejected": -1.7293403148651123,
1309
+ "loss": 1.8172,
1310
+ "rewards/accuracies": 0.6812499761581421,
1311
+ "rewards/chosen": -1.0409172773361206,
1312
+ "rewards/margins": 0.6884229779243469,
1313
+ "rewards/rejected": -1.7293403148651123,
1314
+ "step": 435
1315
+ },
1316
+ {
1317
+ "epoch": 0.9212248102590945,
1318
+ "grad_norm": 32.567789743092646,
1319
+ "learning_rate": 9.12094829893642e-09,
1320
+ "logits/chosen": -2.617215871810913,
1321
+ "logits/rejected": -2.5979318618774414,
1322
+ "logps/chosen": -1.0106241703033447,
1323
+ "logps/rejected": -1.5670998096466064,
1324
+ "loss": 1.8428,
1325
+ "rewards/accuracies": 0.643750011920929,
1326
+ "rewards/chosen": -1.0106241703033447,
1327
+ "rewards/margins": 0.5564756989479065,
1328
+ "rewards/rejected": -1.5670998096466064,
1329
+ "step": 440
1330
+ },
1331
+ {
1332
+ "epoch": 0.9316932740120387,
1333
+ "grad_norm": 30.42876501735674,
1334
+ "learning_rate": 6.832927412229017e-09,
1335
+ "logits/chosen": -2.681229591369629,
1336
+ "logits/rejected": -2.612400531768799,
1337
+ "logps/chosen": -1.06952965259552,
1338
+ "logps/rejected": -1.5481148958206177,
1339
+ "loss": 1.8604,
1340
+ "rewards/accuracies": 0.6625000238418579,
1341
+ "rewards/chosen": -1.06952965259552,
1342
+ "rewards/margins": 0.4785851836204529,
1343
+ "rewards/rejected": -1.5481148958206177,
1344
+ "step": 445
1345
+ },
1346
+ {
1347
+ "epoch": 0.942161737764983,
1348
+ "grad_norm": 27.381238378090455,
1349
+ "learning_rate": 4.8708793644441086e-09,
1350
+ "logits/chosen": -2.579571485519409,
1351
+ "logits/rejected": -2.544320821762085,
1352
+ "logps/chosen": -1.0337889194488525,
1353
+ "logps/rejected": -1.5412318706512451,
1354
+ "loss": 1.7854,
1355
+ "rewards/accuracies": 0.706250011920929,
1356
+ "rewards/chosen": -1.0337889194488525,
1357
+ "rewards/margins": 0.5074428915977478,
1358
+ "rewards/rejected": -1.5412318706512451,
1359
+ "step": 450
1360
+ },
1361
+ {
1362
+ "epoch": 0.9526302015179272,
1363
+ "grad_norm": 31.78517016150814,
1364
+ "learning_rate": 3.2374343405217884e-09,
1365
+ "logits/chosen": -2.6410415172576904,
1366
+ "logits/rejected": -2.5741779804229736,
1367
+ "logps/chosen": -1.1349095106124878,
1368
+ "logps/rejected": -1.5367697477340698,
1369
+ "loss": 1.8237,
1370
+ "rewards/accuracies": 0.668749988079071,
1371
+ "rewards/chosen": -1.1349095106124878,
1372
+ "rewards/margins": 0.40186023712158203,
1373
+ "rewards/rejected": -1.5367697477340698,
1374
+ "step": 455
1375
+ },
1376
+ {
1377
+ "epoch": 0.9630986652708715,
1378
+ "grad_norm": 29.1380242330253,
1379
+ "learning_rate": 1.9347820230782295e-09,
1380
+ "logits/chosen": -2.6333887577056885,
1381
+ "logits/rejected": -2.594615936279297,
1382
+ "logps/chosen": -0.9948427081108093,
1383
+ "logps/rejected": -1.598851203918457,
1384
+ "loss": 1.7821,
1385
+ "rewards/accuracies": 0.6875,
1386
+ "rewards/chosen": -0.9948427081108093,
1387
+ "rewards/margins": 0.6040085554122925,
1388
+ "rewards/rejected": -1.598851203918457,
1389
+ "step": 460
1390
+ },
1391
+ {
1392
+ "epoch": 0.9735671290238157,
1393
+ "grad_norm": 34.467412911376215,
1394
+ "learning_rate": 9.64668657069706e-10,
1395
+ "logits/chosen": -2.69240140914917,
1396
+ "logits/rejected": -2.6058619022369385,
1397
+ "logps/chosen": -1.087109923362732,
1398
+ "logps/rejected": -1.6203782558441162,
1399
+ "loss": 1.8436,
1400
+ "rewards/accuracies": 0.6937500238418579,
1401
+ "rewards/chosen": -1.087109923362732,
1402
+ "rewards/margins": 0.5332685112953186,
1403
+ "rewards/rejected": -1.6203782558441162,
1404
+ "step": 465
1405
+ },
1406
+ {
1407
+ "epoch": 0.98403559277676,
1408
+ "grad_norm": 27.439754854696236,
1409
+ "learning_rate": 3.2839470889836627e-10,
1410
+ "logits/chosen": -2.6679489612579346,
1411
+ "logits/rejected": -2.603280544281006,
1412
+ "logps/chosen": -0.9998431205749512,
1413
+ "logps/rejected": -1.458508849143982,
1414
+ "loss": 1.8712,
1415
+ "rewards/accuracies": 0.65625,
1416
+ "rewards/chosen": -0.9998431205749512,
1417
+ "rewards/margins": 0.45866554975509644,
1418
+ "rewards/rejected": -1.458508849143982,
1419
+ "step": 470
1420
+ },
1421
+ {
1422
+ "epoch": 0.9945040565297043,
1423
+ "grad_norm": 31.225346161878143,
1424
+ "learning_rate": 2.6813123097352287e-11,
1425
+ "logits/chosen": -2.714961290359497,
1426
+ "logits/rejected": -2.6193995475769043,
1427
+ "logps/chosen": -1.041459083557129,
1428
+ "logps/rejected": -1.5316205024719238,
1429
+ "loss": 1.8186,
1430
+ "rewards/accuracies": 0.6000000238418579,
1431
+ "rewards/chosen": -1.041459083557129,
1432
+ "rewards/margins": 0.4901614189147949,
1433
+ "rewards/rejected": -1.5316205024719238,
1434
+ "step": 475
1435
+ },
1436
+ {
1437
+ "epoch": 0.998691442030882,
1438
+ "step": 477,
1439
+ "total_flos": 0.0,
1440
+ "train_loss": 1.8633759126723188,
1441
+ "train_runtime": 7578.2385,
1442
+ "train_samples_per_second": 8.067,
1443
+ "train_steps_per_second": 0.063
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 sha256:7b15e90725946374457c43aa3328635d55489356d3e8841c5b8336d56d4d2d42
3
+ size 7160