Teng Xiao commited on
Commit
87641fc
1 Parent(s): 817ce52
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-Cal-DPO-1-001-False
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-Cal-DPO-1-001-False
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": 114854.6911687631,
5
+ "train_runtime": 7479.76,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 8.173,
8
+ "train_steps_per_second": 0.064
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:df402522469c33d7b32e6064252f24e75e040ee32cfbefef658e8d6fa4394537
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:fd928c1f875ee4afd3ba9062bd626b6c05213a718f9aab283124b1d283402fbc
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809b7b96bffdc6766d94c595181101d7598014523583db1f9a9e0ca45ea933f7
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": 114854.6911687631,
5
+ "train_runtime": 7479.76,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 8.173,
8
+ "train_steps_per_second": 0.064
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": 522503.4218003003,
14
+ "learning_rate": 5.208333333333333e-08,
15
+ "logits/chosen": -2.7708499431610107,
16
+ "logits/rejected": -2.7286171913146973,
17
+ "logps/chosen": -253.5421142578125,
18
+ "logps/rejected": -244.00076293945312,
19
+ "loss": 125000.2375,
20
+ "rewards/accuracies": 0.44999998807907104,
21
+ "rewards/chosen": -253.5421142578125,
22
+ "rewards/margins": -9.541345596313477,
23
+ "rewards/rejected": -244.00076293945312,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.02093692750588851,
28
+ "grad_norm": 409413.4458768586,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -2.7510223388671875,
31
+ "logits/rejected": -2.7252488136291504,
32
+ "logps/chosen": -268.2208557128906,
33
+ "logps/rejected": -243.4846649169922,
34
+ "loss": 124997.8,
35
+ "rewards/accuracies": 0.44999998807907104,
36
+ "rewards/chosen": -268.2208557128906,
37
+ "rewards/margins": -24.73613929748535,
38
+ "rewards/rejected": -243.4846649169922,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.031405391258832765,
43
+ "grad_norm": 414950.26842560945,
44
+ "learning_rate": 1.5624999999999999e-07,
45
+ "logits/chosen": -2.730611562728882,
46
+ "logits/rejected": -2.6970362663269043,
47
+ "logps/chosen": -236.9029541015625,
48
+ "logps/rejected": -273.0437316894531,
49
+ "loss": 124982.75,
50
+ "rewards/accuracies": 0.5375000238418579,
51
+ "rewards/chosen": -236.9029541015625,
52
+ "rewards/margins": 36.140785217285156,
53
+ "rewards/rejected": -273.0437316894531,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.04187385501177702,
58
+ "grad_norm": 718250.9758832247,
59
+ "learning_rate": 2.0833333333333333e-07,
60
+ "logits/chosen": -2.802532434463501,
61
+ "logits/rejected": -2.7090563774108887,
62
+ "logps/chosen": -301.2122802734375,
63
+ "logps/rejected": -269.02008056640625,
64
+ "loss": 124929.4,
65
+ "rewards/accuracies": 0.46875,
66
+ "rewards/chosen": -301.2122802734375,
67
+ "rewards/margins": -32.19221496582031,
68
+ "rewards/rejected": -269.02008056640625,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.05234231876472128,
73
+ "grad_norm": 444864.8327529458,
74
+ "learning_rate": 2.604166666666667e-07,
75
+ "logits/chosen": -2.796382188796997,
76
+ "logits/rejected": -2.7728114128112793,
77
+ "logps/chosen": -274.8233947753906,
78
+ "logps/rejected": -246.075927734375,
79
+ "loss": 124820.5,
80
+ "rewards/accuracies": 0.4437499940395355,
81
+ "rewards/chosen": -274.8233947753906,
82
+ "rewards/margins": -28.747509002685547,
83
+ "rewards/rejected": -246.075927734375,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06281078251766553,
88
+ "grad_norm": 458498.66919273353,
89
+ "learning_rate": 3.1249999999999997e-07,
90
+ "logits/chosen": -2.7689995765686035,
91
+ "logits/rejected": -2.7268056869506836,
92
+ "logps/chosen": -240.1889190673828,
93
+ "logps/rejected": -226.0777587890625,
94
+ "loss": 124675.575,
95
+ "rewards/accuracies": 0.4749999940395355,
96
+ "rewards/chosen": -240.1889190673828,
97
+ "rewards/margins": -14.111166000366211,
98
+ "rewards/rejected": -226.0777587890625,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07327924627060979,
103
+ "grad_norm": 450902.00202128256,
104
+ "learning_rate": 3.645833333333333e-07,
105
+ "logits/chosen": -2.7725298404693604,
106
+ "logits/rejected": -2.6864283084869385,
107
+ "logps/chosen": -274.01287841796875,
108
+ "logps/rejected": -278.74652099609375,
109
+ "loss": 124375.275,
110
+ "rewards/accuracies": 0.48750001192092896,
111
+ "rewards/chosen": -274.01287841796875,
112
+ "rewards/margins": 4.733607292175293,
113
+ "rewards/rejected": -278.74652099609375,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08374771002355404,
118
+ "grad_norm": 417057.7715157791,
119
+ "learning_rate": 4.1666666666666667e-07,
120
+ "logits/chosen": -2.7862133979797363,
121
+ "logits/rejected": -2.6889536380767822,
122
+ "logps/chosen": -294.39178466796875,
123
+ "logps/rejected": -261.9639892578125,
124
+ "loss": 123992.45,
125
+ "rewards/accuracies": 0.4749999940395355,
126
+ "rewards/chosen": -294.39178466796875,
127
+ "rewards/margins": -32.427791595458984,
128
+ "rewards/rejected": -261.9639892578125,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.0942161737764983,
133
+ "grad_norm": 466508.70788908063,
134
+ "learning_rate": 4.6874999999999996e-07,
135
+ "logits/chosen": -2.7797024250030518,
136
+ "logits/rejected": -2.731426477432251,
137
+ "logps/chosen": -278.8966979980469,
138
+ "logps/rejected": -264.8343200683594,
139
+ "loss": 123537.05,
140
+ "rewards/accuracies": 0.48750001192092896,
141
+ "rewards/chosen": -278.8966979980469,
142
+ "rewards/margins": -14.062413215637207,
143
+ "rewards/rejected": -264.8343200683594,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.10468463752944256,
148
+ "grad_norm": 559270.5129260804,
149
+ "learning_rate": 4.999731868769026e-07,
150
+ "logits/chosen": -2.708888053894043,
151
+ "logits/rejected": -2.639033079147339,
152
+ "logps/chosen": -292.9398498535156,
153
+ "logps/rejected": -284.3505554199219,
154
+ "loss": 122464.5875,
155
+ "rewards/accuracies": 0.512499988079071,
156
+ "rewards/chosen": -292.9398498535156,
157
+ "rewards/margins": -8.58930492401123,
158
+ "rewards/rejected": -284.3505554199219,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11515310128238682,
163
+ "grad_norm": 521515.212841857,
164
+ "learning_rate": 4.996716052911017e-07,
165
+ "logits/chosen": -2.685326099395752,
166
+ "logits/rejected": -2.643601894378662,
167
+ "logps/chosen": -283.38983154296875,
168
+ "logps/rejected": -281.60528564453125,
169
+ "loss": 122310.025,
170
+ "rewards/accuracies": 0.512499988079071,
171
+ "rewards/chosen": -283.38983154296875,
172
+ "rewards/margins": -1.784542441368103,
173
+ "rewards/rejected": -281.60528564453125,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.12562156503533106,
178
+ "grad_norm": 729100.4219221757,
179
+ "learning_rate": 4.990353313429303e-07,
180
+ "logits/chosen": -2.724234104156494,
181
+ "logits/rejected": -2.681450605392456,
182
+ "logps/chosen": -270.0491027832031,
183
+ "logps/rejected": -281.71820068359375,
184
+ "loss": 121167.4375,
185
+ "rewards/accuracies": 0.5562499761581421,
186
+ "rewards/chosen": -270.0491027832031,
187
+ "rewards/margins": 11.669103622436523,
188
+ "rewards/rejected": -281.71820068359375,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.1360900287882753,
193
+ "grad_norm": 961680.3751689971,
194
+ "learning_rate": 4.980652179769217e-07,
195
+ "logits/chosen": -2.718280792236328,
196
+ "logits/rejected": -2.597512722015381,
197
+ "logps/chosen": -310.9617004394531,
198
+ "logps/rejected": -293.2528381347656,
199
+ "loss": 119799.15,
200
+ "rewards/accuracies": 0.518750011920929,
201
+ "rewards/chosen": -310.9617004394531,
202
+ "rewards/margins": -17.708873748779297,
203
+ "rewards/rejected": -293.2528381347656,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.14655849254121958,
208
+ "grad_norm": 783593.0959446996,
209
+ "learning_rate": 4.967625656594781e-07,
210
+ "logits/chosen": -2.6035261154174805,
211
+ "logits/rejected": -2.5565543174743652,
212
+ "logps/chosen": -290.8232421875,
213
+ "logps/rejected": -287.1130065917969,
214
+ "loss": 119810.2,
215
+ "rewards/accuracies": 0.518750011920929,
216
+ "rewards/chosen": -290.8232421875,
217
+ "rewards/margins": -3.710245132446289,
218
+ "rewards/rejected": -287.1130065917969,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.15702695629416383,
223
+ "grad_norm": 745801.2137469078,
224
+ "learning_rate": 4.951291206355559e-07,
225
+ "logits/chosen": -2.7136483192443848,
226
+ "logits/rejected": -2.6402573585510254,
227
+ "logps/chosen": -291.23773193359375,
228
+ "logps/rejected": -318.0777587890625,
229
+ "loss": 119278.1375,
230
+ "rewards/accuracies": 0.5625,
231
+ "rewards/chosen": -291.23773193359375,
232
+ "rewards/margins": 26.84000015258789,
233
+ "rewards/rejected": -318.0777587890625,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.16749542004710807,
238
+ "grad_norm": 907046.1955290881,
239
+ "learning_rate": 4.93167072587771e-07,
240
+ "logits/chosen": -2.718100070953369,
241
+ "logits/rejected": -2.6574056148529053,
242
+ "logps/chosen": -292.93060302734375,
243
+ "logps/rejected": -307.5615234375,
244
+ "loss": 119745.725,
245
+ "rewards/accuracies": 0.5249999761581421,
246
+ "rewards/chosen": -292.93060302734375,
247
+ "rewards/margins": 14.630932807922363,
248
+ "rewards/rejected": -307.5615234375,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.17796388380005235,
253
+ "grad_norm": 860624.0897837883,
254
+ "learning_rate": 4.908790517010636e-07,
255
+ "logits/chosen": -2.757253408432007,
256
+ "logits/rejected": -2.69834566116333,
257
+ "logps/chosen": -295.21539306640625,
258
+ "logps/rejected": -327.061767578125,
259
+ "loss": 118244.975,
260
+ "rewards/accuracies": 0.518750011920929,
261
+ "rewards/chosen": -295.21539306640625,
262
+ "rewards/margins": 31.846384048461914,
263
+ "rewards/rejected": -327.061767578125,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.1884323475529966,
268
+ "grad_norm": 1180769.397532202,
269
+ "learning_rate": 4.882681251368548e-07,
270
+ "logits/chosen": -2.7516987323760986,
271
+ "logits/rejected": -2.7340774536132812,
272
+ "logps/chosen": -311.9580993652344,
273
+ "logps/rejected": -325.9947814941406,
274
+ "loss": 118380.25,
275
+ "rewards/accuracies": 0.5249999761581421,
276
+ "rewards/chosen": -311.9580993652344,
277
+ "rewards/margins": 14.036661148071289,
278
+ "rewards/rejected": -325.9947814941406,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.19890081130594087,
283
+ "grad_norm": 1435209.2727647137,
284
+ "learning_rate": 4.853377929214243e-07,
285
+ "logits/chosen": -2.7984097003936768,
286
+ "logits/rejected": -2.713646411895752,
287
+ "logps/chosen": -308.3005676269531,
288
+ "logps/rejected": -312.81201171875,
289
+ "loss": 116816.6,
290
+ "rewards/accuracies": 0.48750001192092896,
291
+ "rewards/chosen": -308.3005676269531,
292
+ "rewards/margins": 4.5114593505859375,
293
+ "rewards/rejected": -312.81201171875,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.2093692750588851,
298
+ "grad_norm": 1728193.4126168345,
299
+ "learning_rate": 4.820919832540181e-07,
300
+ "logits/chosen": -2.70627498626709,
301
+ "logits/rejected": -2.6122021675109863,
302
+ "logps/chosen": -283.68487548828125,
303
+ "logps/rejected": -284.87298583984375,
304
+ "loss": 118125.7625,
305
+ "rewards/accuracies": 0.53125,
306
+ "rewards/chosen": -283.68487548828125,
307
+ "rewards/margins": 1.188114881515503,
308
+ "rewards/rejected": -284.87298583984375,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.21983773881182936,
313
+ "grad_norm": 1249095.5568791889,
314
+ "learning_rate": 4.785350472409791e-07,
315
+ "logits/chosen": -2.555546283721924,
316
+ "logits/rejected": -2.499777317047119,
317
+ "logps/chosen": -262.59674072265625,
318
+ "logps/rejected": -337.804931640625,
319
+ "loss": 116391.2,
320
+ "rewards/accuracies": 0.6312500238418579,
321
+ "rewards/chosen": -262.59674072265625,
322
+ "rewards/margins": 75.20821380615234,
323
+ "rewards/rejected": -337.804931640625,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23030620256477363,
328
+ "grad_norm": 1324636.8678255256,
329
+ "learning_rate": 4.7467175306295647e-07,
330
+ "logits/chosen": -2.2604401111602783,
331
+ "logits/rejected": -2.107639789581299,
332
+ "logps/chosen": -314.15606689453125,
333
+ "logps/rejected": -354.67578125,
334
+ "loss": 115764.325,
335
+ "rewards/accuracies": 0.5874999761581421,
336
+ "rewards/chosen": -314.15606689453125,
337
+ "rewards/margins": 40.519737243652344,
338
+ "rewards/rejected": -354.67578125,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.24077466631771788,
343
+ "grad_norm": 2088676.398368818,
344
+ "learning_rate": 4.70507279583015e-07,
345
+ "logits/chosen": -2.022336959838867,
346
+ "logits/rejected": -1.7513967752456665,
347
+ "logps/chosen": -331.6026611328125,
348
+ "logps/rejected": -372.3267517089844,
349
+ "loss": 115322.7375,
350
+ "rewards/accuracies": 0.5562499761581421,
351
+ "rewards/chosen": -331.6026611328125,
352
+ "rewards/margins": 40.724082946777344,
353
+ "rewards/rejected": -372.3267517089844,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2512431300706621,
358
+ "grad_norm": 1807091.2744565222,
359
+ "learning_rate": 4.6604720940421207e-07,
360
+ "logits/chosen": -1.804964303970337,
361
+ "logits/rejected": -1.5805766582489014,
362
+ "logps/chosen": -315.6778869628906,
363
+ "logps/rejected": -387.36260986328125,
364
+ "loss": 115043.6,
365
+ "rewards/accuracies": 0.606249988079071,
366
+ "rewards/chosen": -315.6778869628906,
367
+ "rewards/margins": 71.68473052978516,
368
+ "rewards/rejected": -387.36260986328125,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.26171159382360637,
373
+ "grad_norm": 1582536.6614139078,
374
+ "learning_rate": 4.612975213859487e-07,
375
+ "logits/chosen": -2.094388961791992,
376
+ "logits/rejected": -1.9840008020401,
377
+ "logps/chosen": -285.61419677734375,
378
+ "logps/rejected": -304.2431335449219,
379
+ "loss": 116704.675,
380
+ "rewards/accuracies": 0.5562499761581421,
381
+ "rewards/chosen": -285.61419677734375,
382
+ "rewards/margins": 18.628963470458984,
383
+ "rewards/rejected": -304.2431335449219,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.2721800575765506,
388
+ "grad_norm": 1405438.3906735398,
389
+ "learning_rate": 4.5626458262912735e-07,
390
+ "logits/chosen": -2.012509822845459,
391
+ "logits/rejected": -1.8286924362182617,
392
+ "logps/chosen": -295.90277099609375,
393
+ "logps/rejected": -341.51812744140625,
394
+ "loss": 116832.5,
395
+ "rewards/accuracies": 0.550000011920929,
396
+ "rewards/chosen": -295.90277099609375,
397
+ "rewards/margins": 45.61534881591797,
398
+ "rewards/rejected": -341.51812744140625,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.2826485213294949,
403
+ "grad_norm": 2166459.423278389,
404
+ "learning_rate": 4.5095513994085974e-07,
405
+ "logits/chosen": -1.7868998050689697,
406
+ "logits/rejected": -1.1601707935333252,
407
+ "logps/chosen": -296.5223693847656,
408
+ "logps/rejected": -369.28326416015625,
409
+ "loss": 115705.0,
410
+ "rewards/accuracies": 0.6000000238418579,
411
+ "rewards/chosen": -296.5223693847656,
412
+ "rewards/margins": 72.76090240478516,
413
+ "rewards/rejected": -369.28326416015625,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.29311698508243916,
418
+ "grad_norm": 1788707.2451489503,
419
+ "learning_rate": 4.453763107901675e-07,
420
+ "logits/chosen": -1.2310272455215454,
421
+ "logits/rejected": -0.7306966781616211,
422
+ "logps/chosen": -284.04351806640625,
423
+ "logps/rejected": -365.6307678222656,
424
+ "loss": 112320.4,
425
+ "rewards/accuracies": 0.6499999761581421,
426
+ "rewards/chosen": -284.04351806640625,
427
+ "rewards/margins": 81.58724975585938,
428
+ "rewards/rejected": -365.6307678222656,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.3035854488353834,
433
+ "grad_norm": 2512886.744124689,
434
+ "learning_rate": 4.395355737667985e-07,
435
+ "logits/chosen": -1.370542049407959,
436
+ "logits/rejected": -0.847873330116272,
437
+ "logps/chosen": -295.51165771484375,
438
+ "logps/rejected": -344.68634033203125,
439
+ "loss": 116938.0875,
440
+ "rewards/accuracies": 0.5874999761581421,
441
+ "rewards/chosen": -295.51165771484375,
442
+ "rewards/margins": 49.174705505371094,
443
+ "rewards/rejected": -344.68634033203125,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.31405391258832765,
448
+ "grad_norm": 2459660.1241130554,
449
+ "learning_rate": 4.3344075855595097e-07,
450
+ "logits/chosen": -1.8194392919540405,
451
+ "logits/rejected": -1.4853712320327759,
452
+ "logps/chosen": -293.786865234375,
453
+ "logps/rejected": -332.8251953125,
454
+ "loss": 112010.725,
455
+ "rewards/accuracies": 0.5687500238418579,
456
+ "rewards/chosen": -293.786865234375,
457
+ "rewards/margins": 39.03831100463867,
458
+ "rewards/rejected": -332.8251953125,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.3245223763412719,
463
+ "grad_norm": 4807009.727933751,
464
+ "learning_rate": 4.271000354423425e-07,
465
+ "logits/chosen": -1.3470885753631592,
466
+ "logits/rejected": -0.8607180714607239,
467
+ "logps/chosen": -337.14300537109375,
468
+ "logps/rejected": -391.9334716796875,
469
+ "loss": 115519.375,
470
+ "rewards/accuracies": 0.5687500238418579,
471
+ "rewards/chosen": -337.14300537109375,
472
+ "rewards/margins": 54.79045867919922,
473
+ "rewards/rejected": -391.9334716796875,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.33499084009421615,
478
+ "grad_norm": 2699245.2043745625,
479
+ "learning_rate": 4.2052190435769554e-07,
480
+ "logits/chosen": -1.7011409997940063,
481
+ "logits/rejected": -1.335893988609314,
482
+ "logps/chosen": -274.394287109375,
483
+ "logps/rejected": -330.22100830078125,
484
+ "loss": 114255.0875,
485
+ "rewards/accuracies": 0.6000000238418579,
486
+ "rewards/chosen": -274.394287109375,
487
+ "rewards/margins": 55.82673263549805,
488
+ "rewards/rejected": -330.22100830078125,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.34545930384716045,
493
+ "grad_norm": 840943.395175269,
494
+ "learning_rate": 4.137151834863213e-07,
495
+ "logits/chosen": -2.163696527481079,
496
+ "logits/rejected": -1.7751731872558594,
497
+ "logps/chosen": -273.88092041015625,
498
+ "logps/rejected": -331.56085205078125,
499
+ "loss": 116034.3125,
500
+ "rewards/accuracies": 0.550000011920929,
501
+ "rewards/chosen": -273.88092041015625,
502
+ "rewards/margins": 57.679969787597656,
503
+ "rewards/rejected": -331.56085205078125,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3559277676001047,
508
+ "grad_norm": 1277262.6579787417,
509
+ "learning_rate": 4.0668899744407567e-07,
510
+ "logits/chosen": -1.8461663722991943,
511
+ "logits/rejected": -1.260231852531433,
512
+ "logps/chosen": -303.04083251953125,
513
+ "logps/rejected": -325.74371337890625,
514
+ "loss": 114209.3125,
515
+ "rewards/accuracies": 0.518750011920929,
516
+ "rewards/chosen": -303.04083251953125,
517
+ "rewards/margins": 22.702842712402344,
518
+ "rewards/rejected": -325.74371337890625,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.36639623135304894,
523
+ "grad_norm": 1135243.1010669412,
524
+ "learning_rate": 3.994527650465352e-07,
525
+ "logits/chosen": -1.029491901397705,
526
+ "logits/rejected": -0.0737704187631607,
527
+ "logps/chosen": -286.8111877441406,
528
+ "logps/rejected": -299.5812072753906,
529
+ "loss": 115237.225,
530
+ "rewards/accuracies": 0.53125,
531
+ "rewards/chosen": -286.8111877441406,
532
+ "rewards/margins": 12.770014762878418,
533
+ "rewards/rejected": -299.5812072753906,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.3768646951059932,
538
+ "grad_norm": 1925685.8821038436,
539
+ "learning_rate": 3.920161866827889e-07,
540
+ "logits/chosen": -0.454359769821167,
541
+ "logits/rejected": -0.02063882350921631,
542
+ "logps/chosen": -297.41461181640625,
543
+ "logps/rejected": -369.3190002441406,
544
+ "loss": 113950.1,
545
+ "rewards/accuracies": 0.606249988079071,
546
+ "rewards/chosen": -297.41461181640625,
547
+ "rewards/margins": 71.90437316894531,
548
+ "rewards/rejected": -369.3190002441406,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.38733315885893743,
553
+ "grad_norm": 2698235.0873295115,
554
+ "learning_rate": 3.8438923131177237e-07,
555
+ "logits/chosen": -0.5734198689460754,
556
+ "logits/rejected": 0.27511700987815857,
557
+ "logps/chosen": -316.64971923828125,
558
+ "logps/rejected": -350.3505554199219,
559
+ "loss": 113131.425,
560
+ "rewards/accuracies": 0.606249988079071,
561
+ "rewards/chosen": -316.64971923828125,
562
+ "rewards/margins": 33.700801849365234,
563
+ "rewards/rejected": -350.3505554199219,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.39780162261188173,
568
+ "grad_norm": 2263250.8365393346,
569
+ "learning_rate": 3.765821230985757e-07,
570
+ "logits/chosen": -0.4672353267669678,
571
+ "logits/rejected": -0.028242725878953934,
572
+ "logps/chosen": -283.13873291015625,
573
+ "logps/rejected": -305.73968505859375,
574
+ "loss": 115869.625,
575
+ "rewards/accuracies": 0.625,
576
+ "rewards/chosen": -283.13873291015625,
577
+ "rewards/margins": 22.600967407226562,
578
+ "rewards/rejected": -305.73968505859375,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.408270086364826,
583
+ "grad_norm": 2336859.8229430458,
584
+ "learning_rate": 3.6860532770864005e-07,
585
+ "logits/chosen": -0.3446078598499298,
586
+ "logits/rejected": 0.17580614984035492,
587
+ "logps/chosen": -345.1635437011719,
588
+ "logps/rejected": -373.7042236328125,
589
+ "loss": 115610.2375,
590
+ "rewards/accuracies": 0.5874999761581421,
591
+ "rewards/chosen": -345.1635437011719,
592
+ "rewards/margins": 28.540664672851562,
593
+ "rewards/rejected": -373.7042236328125,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.4187385501177702,
598
+ "grad_norm": 2875002.890975931,
599
+ "learning_rate": 3.604695382782159e-07,
600
+ "logits/chosen": -0.3627869188785553,
601
+ "logits/rejected": -0.14643223583698273,
602
+ "logps/chosen": -305.51885986328125,
603
+ "logps/rejected": -352.6678466796875,
604
+ "loss": 116295.75,
605
+ "rewards/accuracies": 0.612500011920929,
606
+ "rewards/chosen": -305.51885986328125,
607
+ "rewards/margins": 47.14897537231445,
608
+ "rewards/rejected": -352.6678466796875,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.42920701387071447,
613
+ "grad_norm": 1400861.091712678,
614
+ "learning_rate": 3.5218566107988867e-07,
615
+ "logits/chosen": -0.8571730852127075,
616
+ "logits/rejected": -0.25482162833213806,
617
+ "logps/chosen": -296.7934875488281,
618
+ "logps/rejected": -329.7360534667969,
619
+ "loss": 114386.15,
620
+ "rewards/accuracies": 0.53125,
621
+ "rewards/chosen": -296.7934875488281,
622
+ "rewards/margins": 32.94261932373047,
623
+ "rewards/rejected": -329.7360534667969,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.4396754776236587,
628
+ "grad_norm": 2247391.450727784,
629
+ "learning_rate": 3.4376480090239047e-07,
630
+ "logits/chosen": -0.7361810803413391,
631
+ "logits/rejected": -0.26914888620376587,
632
+ "logps/chosen": -324.780517578125,
633
+ "logps/rejected": -346.3909606933594,
634
+ "loss": 115300.375,
635
+ "rewards/accuracies": 0.48750001192092896,
636
+ "rewards/chosen": -324.780517578125,
637
+ "rewards/margins": 21.61046028137207,
638
+ "rewards/rejected": -346.3909606933594,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.45014394137660296,
643
+ "grad_norm": 1942071.0568026109,
644
+ "learning_rate": 3.3521824616429284e-07,
645
+ "logits/chosen": -0.7115877270698547,
646
+ "logits/rejected": -0.16935975849628448,
647
+ "logps/chosen": -306.1327819824219,
648
+ "logps/rejected": -375.35125732421875,
649
+ "loss": 113532.725,
650
+ "rewards/accuracies": 0.643750011920929,
651
+ "rewards/chosen": -306.1327819824219,
652
+ "rewards/margins": 69.21846008300781,
653
+ "rewards/rejected": -375.35125732421875,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.46061240512954726,
658
+ "grad_norm": 1880893.803266421,
659
+ "learning_rate": 3.265574537815398e-07,
660
+ "logits/chosen": -0.7726610898971558,
661
+ "logits/rejected": 0.11326490342617035,
662
+ "logps/chosen": -315.4923095703125,
663
+ "logps/rejected": -381.5898132324219,
664
+ "loss": 113337.5125,
665
+ "rewards/accuracies": 0.581250011920929,
666
+ "rewards/chosen": -315.4923095703125,
667
+ "rewards/margins": 66.09752655029297,
668
+ "rewards/rejected": -381.5898132324219,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.4710808688824915,
673
+ "grad_norm": 1945629.7722817352,
674
+ "learning_rate": 3.1779403380910425e-07,
675
+ "logits/chosen": -0.5554154515266418,
676
+ "logits/rejected": 0.3164888024330139,
677
+ "logps/chosen": -310.39068603515625,
678
+ "logps/rejected": -347.70709228515625,
679
+ "loss": 112926.525,
680
+ "rewards/accuracies": 0.5687500238418579,
681
+ "rewards/chosen": -310.39068603515625,
682
+ "rewards/margins": 37.316429138183594,
683
+ "rewards/rejected": -347.70709228515625,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.48154933263543576,
688
+ "grad_norm": 1616156.0747634866,
689
+ "learning_rate": 3.0893973387735683e-07,
690
+ "logits/chosen": -0.8544542193412781,
691
+ "logits/rejected": 0.16107910871505737,
692
+ "logps/chosen": -327.91864013671875,
693
+ "logps/rejected": -367.1671447753906,
694
+ "loss": 112795.225,
695
+ "rewards/accuracies": 0.581250011920929,
696
+ "rewards/chosen": -327.91864013671875,
697
+ "rewards/margins": 39.24848175048828,
698
+ "rewards/rejected": -367.1671447753906,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.49201779638838,
703
+ "grad_norm": 1973066.2630310976,
704
+ "learning_rate": 3.000064234440111e-07,
705
+ "logits/chosen": -0.6506497263908386,
706
+ "logits/rejected": 0.023212980479002,
707
+ "logps/chosen": -294.9061279296875,
708
+ "logps/rejected": -359.06591796875,
709
+ "loss": 113001.925,
710
+ "rewards/accuracies": 0.6499999761581421,
711
+ "rewards/chosen": -294.9061279296875,
712
+ "rewards/margins": 64.1597671508789,
713
+ "rewards/rejected": -359.06591796875,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5024862601413242,
718
+ "grad_norm": 2122255.375505896,
719
+ "learning_rate": 2.910060778827554e-07,
720
+ "logits/chosen": -0.884017288684845,
721
+ "logits/rejected": -0.20214924216270447,
722
+ "logps/chosen": -304.61309814453125,
723
+ "logps/rejected": -344.1042175292969,
724
+ "loss": 112705.575,
725
+ "rewards/accuracies": 0.606249988079071,
726
+ "rewards/chosen": -304.61309814453125,
727
+ "rewards/margins": 39.491153717041016,
728
+ "rewards/rejected": -344.1042175292969,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5129547238942685,
733
+ "grad_norm": 1750645.3017169987,
734
+ "learning_rate": 2.8195076242990116e-07,
735
+ "logits/chosen": -0.5472243428230286,
736
+ "logits/rejected": 0.13178296387195587,
737
+ "logps/chosen": -284.5224609375,
738
+ "logps/rejected": -338.53375244140625,
739
+ "loss": 114159.5,
740
+ "rewards/accuracies": 0.5375000238418579,
741
+ "rewards/chosen": -284.5224609375,
742
+ "rewards/margins": 54.01129150390625,
743
+ "rewards/rejected": -338.53375244140625,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.5234231876472127,
748
+ "grad_norm": 2085184.1734165123,
749
+ "learning_rate": 2.7285261601056697e-07,
750
+ "logits/chosen": -0.4131326675415039,
751
+ "logits/rejected": 0.3880499005317688,
752
+ "logps/chosen": -274.2272033691406,
753
+ "logps/rejected": -340.6448669433594,
754
+ "loss": 114531.3375,
755
+ "rewards/accuracies": 0.6312500238418579,
756
+ "rewards/chosen": -274.2272033691406,
757
+ "rewards/margins": 66.4177017211914,
758
+ "rewards/rejected": -340.6448669433594,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.533891651400157,
763
+ "grad_norm": 2304054.790659312,
764
+ "learning_rate": 2.6372383496608186e-07,
765
+ "logits/chosen": -0.17990997433662415,
766
+ "logits/rejected": 0.9603084325790405,
767
+ "logps/chosen": -331.6031188964844,
768
+ "logps/rejected": -412.93817138671875,
769
+ "loss": 111151.35,
770
+ "rewards/accuracies": 0.6000000238418579,
771
+ "rewards/chosen": -331.6031188964844,
772
+ "rewards/margins": 81.3350830078125,
773
+ "rewards/rejected": -412.93817138671875,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5443601151531012,
778
+ "grad_norm": 1940084.13729787,
779
+ "learning_rate": 2.5457665670441937e-07,
780
+ "logits/chosen": -0.2644157409667969,
781
+ "logits/rejected": 0.6259841918945312,
782
+ "logps/chosen": -258.68670654296875,
783
+ "logps/rejected": -366.4393615722656,
784
+ "loss": 112844.35,
785
+ "rewards/accuracies": 0.668749988079071,
786
+ "rewards/chosen": -258.68670654296875,
787
+ "rewards/margins": 107.7526626586914,
788
+ "rewards/rejected": -366.4393615722656,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5548285789060455,
793
+ "grad_norm": 1521044.9308265387,
794
+ "learning_rate": 2.454233432955807e-07,
795
+ "logits/chosen": -0.47308096289634705,
796
+ "logits/rejected": 0.20548152923583984,
797
+ "logps/chosen": -286.80633544921875,
798
+ "logps/rejected": -340.56756591796875,
799
+ "loss": 112564.5375,
800
+ "rewards/accuracies": 0.612500011920929,
801
+ "rewards/chosen": -286.80633544921875,
802
+ "rewards/margins": 53.76123809814453,
803
+ "rewards/rejected": -340.56756591796875,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.5652970426589898,
808
+ "grad_norm": 1873803.7134507762,
809
+ "learning_rate": 2.3627616503391812e-07,
810
+ "logits/chosen": -0.5675733685493469,
811
+ "logits/rejected": 0.14759287238121033,
812
+ "logps/chosen": -301.10040283203125,
813
+ "logps/rejected": -370.1958312988281,
814
+ "loss": 114260.7375,
815
+ "rewards/accuracies": 0.6187499761581421,
816
+ "rewards/chosen": -301.10040283203125,
817
+ "rewards/margins": 69.09541320800781,
818
+ "rewards/rejected": -370.1958312988281,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.575765506411934,
823
+ "grad_norm": 2362564.8339613965,
824
+ "learning_rate": 2.2714738398943308e-07,
825
+ "logits/chosen": -0.6608392000198364,
826
+ "logits/rejected": 0.4885464608669281,
827
+ "logps/chosen": -315.5157775878906,
828
+ "logps/rejected": -383.5878601074219,
829
+ "loss": 111772.275,
830
+ "rewards/accuracies": 0.6312500238418579,
831
+ "rewards/chosen": -315.5157775878906,
832
+ "rewards/margins": 68.07210540771484,
833
+ "rewards/rejected": -383.5878601074219,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.5862339701648783,
838
+ "grad_norm": 1807476.8899846808,
839
+ "learning_rate": 2.1804923757009882e-07,
840
+ "logits/chosen": -0.5532770752906799,
841
+ "logits/rejected": 0.43744096159935,
842
+ "logps/chosen": -315.10870361328125,
843
+ "logps/rejected": -358.2113952636719,
844
+ "loss": 112631.6,
845
+ "rewards/accuracies": 0.6187499761581421,
846
+ "rewards/chosen": -315.10870361328125,
847
+ "rewards/margins": 43.10268020629883,
848
+ "rewards/rejected": -358.2113952636719,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.5967024339178225,
853
+ "grad_norm": 2237959.642261439,
854
+ "learning_rate": 2.089939221172446e-07,
855
+ "logits/chosen": -0.46047574281692505,
856
+ "logits/rejected": 0.012615549378097057,
857
+ "logps/chosen": -293.84136962890625,
858
+ "logps/rejected": -370.7669372558594,
859
+ "loss": 112695.3,
860
+ "rewards/accuracies": 0.574999988079071,
861
+ "rewards/chosen": -293.84136962890625,
862
+ "rewards/margins": 76.92558288574219,
863
+ "rewards/rejected": -370.7669372558594,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6071708976707668,
868
+ "grad_norm": 1554217.5345301214,
869
+ "learning_rate": 1.9999357655598891e-07,
870
+ "logits/chosen": -0.5754300355911255,
871
+ "logits/rejected": 0.33466261625289917,
872
+ "logps/chosen": -303.59539794921875,
873
+ "logps/rejected": -346.04412841796875,
874
+ "loss": 112625.2125,
875
+ "rewards/accuracies": 0.574999988079071,
876
+ "rewards/chosen": -303.59539794921875,
877
+ "rewards/margins": 42.44871520996094,
878
+ "rewards/rejected": -346.04412841796875,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6176393614237111,
883
+ "grad_norm": 2521456.999656128,
884
+ "learning_rate": 1.9106026612264315e-07,
885
+ "logits/chosen": -0.687907338142395,
886
+ "logits/rejected": 0.15663442015647888,
887
+ "logps/chosen": -279.992919921875,
888
+ "logps/rejected": -332.9551696777344,
889
+ "loss": 114791.675,
890
+ "rewards/accuracies": 0.612500011920929,
891
+ "rewards/chosen": -279.992919921875,
892
+ "rewards/margins": 52.962249755859375,
893
+ "rewards/rejected": -332.9551696777344,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6281078251766553,
898
+ "grad_norm": 3193163.1405664305,
899
+ "learning_rate": 1.8220596619089573e-07,
900
+ "logits/chosen": -0.7139306664466858,
901
+ "logits/rejected": -0.06598733365535736,
902
+ "logps/chosen": -264.813232421875,
903
+ "logps/rejected": -318.2864685058594,
904
+ "loss": 112895.5875,
905
+ "rewards/accuracies": 0.643750011920929,
906
+ "rewards/chosen": -264.813232421875,
907
+ "rewards/margins": 53.47322463989258,
908
+ "rewards/rejected": -318.2864685058594,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6385762889295996,
913
+ "grad_norm": 2896442.2441057838,
914
+ "learning_rate": 1.7344254621846017e-07,
915
+ "logits/chosen": -0.5134263634681702,
916
+ "logits/rejected": 0.272099107503891,
917
+ "logps/chosen": -293.1112060546875,
918
+ "logps/rejected": -366.1026306152344,
919
+ "loss": 111599.1625,
920
+ "rewards/accuracies": 0.637499988079071,
921
+ "rewards/chosen": -293.1112060546875,
922
+ "rewards/margins": 72.99146270751953,
923
+ "rewards/rejected": -366.1026306152344,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6490447526825438,
928
+ "grad_norm": 1410328.2640552768,
929
+ "learning_rate": 1.647817538357072e-07,
930
+ "logits/chosen": -0.5094229578971863,
931
+ "logits/rejected": -0.08179249614477158,
932
+ "logps/chosen": -262.71868896484375,
933
+ "logps/rejected": -373.6757507324219,
934
+ "loss": 110514.8625,
935
+ "rewards/accuracies": 0.675000011920929,
936
+ "rewards/chosen": -262.71868896484375,
937
+ "rewards/margins": 110.95704650878906,
938
+ "rewards/rejected": -373.6757507324219,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6595132164354881,
943
+ "grad_norm": 4370337.480639941,
944
+ "learning_rate": 1.562351990976095e-07,
945
+ "logits/chosen": -0.5516433715820312,
946
+ "logits/rejected": 0.3842604160308838,
947
+ "logps/chosen": -299.07208251953125,
948
+ "logps/rejected": -386.3035583496094,
949
+ "loss": 111146.3375,
950
+ "rewards/accuracies": 0.6499999761581421,
951
+ "rewards/chosen": -299.07208251953125,
952
+ "rewards/margins": 87.2314682006836,
953
+ "rewards/rejected": -386.3035583496094,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6699816801884323,
958
+ "grad_norm": 8860713.857687093,
959
+ "learning_rate": 1.478143389201113e-07,
960
+ "logits/chosen": -0.3542352616786957,
961
+ "logits/rejected": 0.15903237462043762,
962
+ "logps/chosen": -277.9214782714844,
963
+ "logps/rejected": -365.1288146972656,
964
+ "loss": 112815.525,
965
+ "rewards/accuracies": 0.6312500238418579,
966
+ "rewards/chosen": -277.9214782714844,
967
+ "rewards/margins": 87.20732879638672,
968
+ "rewards/rejected": -365.1288146972656,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.6804501439413766,
973
+ "grad_norm": 1908239.1278667776,
974
+ "learning_rate": 1.3953046172178413e-07,
975
+ "logits/chosen": -0.5815322399139404,
976
+ "logits/rejected": 0.323032021522522,
977
+ "logps/chosen": -323.28436279296875,
978
+ "logps/rejected": -390.740234375,
979
+ "loss": 112318.4,
980
+ "rewards/accuracies": 0.606249988079071,
981
+ "rewards/chosen": -323.28436279296875,
982
+ "rewards/margins": 67.45586395263672,
983
+ "rewards/rejected": -390.740234375,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.6909186076943209,
988
+ "grad_norm": 2119739.073105214,
989
+ "learning_rate": 1.3139467229135998e-07,
990
+ "logits/chosen": -0.668155312538147,
991
+ "logits/rejected": 0.13567589223384857,
992
+ "logps/chosen": -295.8731384277344,
993
+ "logps/rejected": -347.6330261230469,
994
+ "loss": 111457.7,
995
+ "rewards/accuracies": 0.574999988079071,
996
+ "rewards/chosen": -295.8731384277344,
997
+ "rewards/margins": 51.7598762512207,
998
+ "rewards/rejected": -347.6330261230469,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7013870714472651,
1003
+ "grad_norm": 1927999.1666317754,
1004
+ "learning_rate": 1.2341787690142435e-07,
1005
+ "logits/chosen": -0.8385793566703796,
1006
+ "logits/rejected": -0.16031041741371155,
1007
+ "logps/chosen": -299.18060302734375,
1008
+ "logps/rejected": -360.9104919433594,
1009
+ "loss": 112842.25,
1010
+ "rewards/accuracies": 0.574999988079071,
1011
+ "rewards/chosen": -299.18060302734375,
1012
+ "rewards/margins": 61.72993087768555,
1013
+ "rewards/rejected": -360.9104919433594,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7118555352002094,
1018
+ "grad_norm": 2176227.517015282,
1019
+ "learning_rate": 1.1561076868822755e-07,
1020
+ "logits/chosen": -0.7431761622428894,
1021
+ "logits/rejected": 0.11613886058330536,
1022
+ "logps/chosen": -331.2103271484375,
1023
+ "logps/rejected": -360.3314208984375,
1024
+ "loss": 111618.6375,
1025
+ "rewards/accuracies": 0.5687500238418579,
1026
+ "rewards/chosen": -331.2103271484375,
1027
+ "rewards/margins": 29.121089935302734,
1028
+ "rewards/rejected": -360.3314208984375,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.7223239989531536,
1033
+ "grad_norm": 2699423.898748738,
1034
+ "learning_rate": 1.0798381331721107e-07,
1035
+ "logits/chosen": -0.7944961786270142,
1036
+ "logits/rejected": 0.2726106643676758,
1037
+ "logps/chosen": -324.1297302246094,
1038
+ "logps/rejected": -362.2281188964844,
1039
+ "loss": 111899.3375,
1040
+ "rewards/accuracies": 0.6000000238418579,
1041
+ "rewards/chosen": -324.1297302246094,
1042
+ "rewards/margins": 38.09839630126953,
1043
+ "rewards/rejected": -362.2281188964844,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7327924627060979,
1048
+ "grad_norm": 2320601.542393335,
1049
+ "learning_rate": 1.0054723495346482e-07,
1050
+ "logits/chosen": -0.2713714838027954,
1051
+ "logits/rejected": 0.22024962306022644,
1052
+ "logps/chosen": -288.8630676269531,
1053
+ "logps/rejected": -365.87994384765625,
1054
+ "loss": 113524.075,
1055
+ "rewards/accuracies": 0.606249988079071,
1056
+ "rewards/chosen": -288.8630676269531,
1057
+ "rewards/margins": 77.01687622070312,
1058
+ "rewards/rejected": -365.87994384765625,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7432609264590422,
1063
+ "grad_norm": 1815809.2243324781,
1064
+ "learning_rate": 9.331100255592436e-08,
1065
+ "logits/chosen": -0.2964836657047272,
1066
+ "logits/rejected": 0.5565654039382935,
1067
+ "logps/chosen": -277.563232421875,
1068
+ "logps/rejected": -366.7838134765625,
1069
+ "loss": 111167.625,
1070
+ "rewards/accuracies": 0.675000011920929,
1071
+ "rewards/chosen": -277.563232421875,
1072
+ "rewards/margins": 89.22059631347656,
1073
+ "rewards/rejected": -366.7838134765625,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7537293902119864,
1078
+ "grad_norm": 1971255.6245351008,
1079
+ "learning_rate": 8.628481651367875e-08,
1080
+ "logits/chosen": -0.7251734137535095,
1081
+ "logits/rejected": 0.05562416836619377,
1082
+ "logps/chosen": -304.60357666015625,
1083
+ "logps/rejected": -355.7652587890625,
1084
+ "loss": 109653.975,
1085
+ "rewards/accuracies": 0.5625,
1086
+ "rewards/chosen": -304.60357666015625,
1087
+ "rewards/margins": 51.16161346435547,
1088
+ "rewards/rejected": -355.7652587890625,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.7641978539649307,
1093
+ "grad_norm": 1754900.7076158663,
1094
+ "learning_rate": 7.947809564230445e-08,
1095
+ "logits/chosen": -0.45269888639450073,
1096
+ "logits/rejected": 0.3153532147407532,
1097
+ "logps/chosen": -322.9766845703125,
1098
+ "logps/rejected": -375.75787353515625,
1099
+ "loss": 114208.8,
1100
+ "rewards/accuracies": 0.6499999761581421,
1101
+ "rewards/chosen": -322.9766845703125,
1102
+ "rewards/margins": 52.78118896484375,
1103
+ "rewards/rejected": -375.75787353515625,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7746663177178749,
1108
+ "grad_norm": 2147071.573360362,
1109
+ "learning_rate": 7.289996455765748e-08,
1110
+ "logits/chosen": -0.43487948179244995,
1111
+ "logits/rejected": 0.42789965867996216,
1112
+ "logps/chosen": -311.0076599121094,
1113
+ "logps/rejected": -392.62152099609375,
1114
+ "loss": 112070.675,
1115
+ "rewards/accuracies": 0.59375,
1116
+ "rewards/chosen": -311.0076599121094,
1117
+ "rewards/margins": 81.61390686035156,
1118
+ "rewards/rejected": -392.62152099609375,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.7851347814708192,
1123
+ "grad_norm": 1709073.4926486812,
1124
+ "learning_rate": 6.655924144404906e-08,
1125
+ "logits/chosen": -0.30552688241004944,
1126
+ "logits/rejected": -0.23342788219451904,
1127
+ "logps/chosen": -273.34320068359375,
1128
+ "logps/rejected": -361.71856689453125,
1129
+ "loss": 110961.7625,
1130
+ "rewards/accuracies": 0.637499988079071,
1131
+ "rewards/chosen": -273.34320068359375,
1132
+ "rewards/margins": 88.37535095214844,
1133
+ "rewards/rejected": -361.71856689453125,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.7956032452237635,
1138
+ "grad_norm": 2722896.7250441867,
1139
+ "learning_rate": 6.046442623320145e-08,
1140
+ "logits/chosen": -0.41763028502464294,
1141
+ "logits/rejected": 0.005231809802353382,
1142
+ "logps/chosen": -307.29693603515625,
1143
+ "logps/rejected": -393.7823181152344,
1144
+ "loss": 111852.7,
1145
+ "rewards/accuracies": 0.625,
1146
+ "rewards/chosen": -307.29693603515625,
1147
+ "rewards/margins": 86.4853744506836,
1148
+ "rewards/rejected": -393.7823181152344,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.8060717089767077,
1153
+ "grad_norm": 1745300.231202083,
1154
+ "learning_rate": 5.4623689209832484e-08,
1155
+ "logits/chosen": -0.718239426612854,
1156
+ "logits/rejected": -0.026650678366422653,
1157
+ "logps/chosen": -292.75494384765625,
1158
+ "logps/rejected": -368.7347717285156,
1159
+ "loss": 112271.8625,
1160
+ "rewards/accuracies": 0.6000000238418579,
1161
+ "rewards/chosen": -292.75494384765625,
1162
+ "rewards/margins": 75.97982788085938,
1163
+ "rewards/rejected": -368.7347717285156,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.816540172729652,
1168
+ "grad_norm": 2201936.896729985,
1169
+ "learning_rate": 4.904486005914027e-08,
1170
+ "logits/chosen": -0.9130474328994751,
1171
+ "logits/rejected": 0.17849242687225342,
1172
+ "logps/chosen": -299.4166259765625,
1173
+ "logps/rejected": -363.7040100097656,
1174
+ "loss": 110293.55,
1175
+ "rewards/accuracies": 0.5625,
1176
+ "rewards/chosen": -299.4166259765625,
1177
+ "rewards/margins": 64.2873764038086,
1178
+ "rewards/rejected": -363.7040100097656,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8270086364825961,
1183
+ "grad_norm": 1965017.8644740335,
1184
+ "learning_rate": 4.373541737087263e-08,
1185
+ "logits/chosen": -0.7144075036048889,
1186
+ "logits/rejected": 0.521481454372406,
1187
+ "logps/chosen": -278.52801513671875,
1188
+ "logps/rejected": -330.89202880859375,
1189
+ "loss": 109924.925,
1190
+ "rewards/accuracies": 0.581250011920929,
1191
+ "rewards/chosen": -278.52801513671875,
1192
+ "rewards/margins": 52.3640251159668,
1193
+ "rewards/rejected": -330.89202880859375,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8374771002355405,
1198
+ "grad_norm": 2507424.209111181,
1199
+ "learning_rate": 3.8702478614051345e-08,
1200
+ "logits/chosen": -0.6051787734031677,
1201
+ "logits/rejected": 0.003916704561561346,
1202
+ "logps/chosen": -281.8033447265625,
1203
+ "logps/rejected": -354.2074279785156,
1204
+ "loss": 113172.8375,
1205
+ "rewards/accuracies": 0.612500011920929,
1206
+ "rewards/chosen": -281.8033447265625,
1207
+ "rewards/margins": 72.404052734375,
1208
+ "rewards/rejected": -354.2074279785156,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8479455639884846,
1213
+ "grad_norm": 2422379.6896536425,
1214
+ "learning_rate": 3.3952790595787986e-08,
1215
+ "logits/chosen": -0.6138535737991333,
1216
+ "logits/rejected": -0.022265207022428513,
1217
+ "logps/chosen": -283.72808837890625,
1218
+ "logps/rejected": -363.5780944824219,
1219
+ "loss": 112426.925,
1220
+ "rewards/accuracies": 0.637499988079071,
1221
+ "rewards/chosen": -283.72808837890625,
1222
+ "rewards/margins": 79.85002899169922,
1223
+ "rewards/rejected": -363.5780944824219,
1224
+ "step": 405
1225
+ },
1226
+ {
1227
+ "epoch": 0.8584140277414289,
1228
+ "grad_norm": 2043445.172936004,
1229
+ "learning_rate": 2.9492720416985e-08,
1230
+ "logits/chosen": -0.7124518752098083,
1231
+ "logits/rejected": -0.10028399527072906,
1232
+ "logps/chosen": -277.91021728515625,
1233
+ "logps/rejected": -341.11846923828125,
1234
+ "loss": 112355.5875,
1235
+ "rewards/accuracies": 0.6312500238418579,
1236
+ "rewards/chosen": -277.91021728515625,
1237
+ "rewards/margins": 63.208221435546875,
1238
+ "rewards/rejected": -341.11846923828125,
1239
+ "step": 410
1240
+ },
1241
+ {
1242
+ "epoch": 0.8688824914943732,
1243
+ "grad_norm": 1929711.202147663,
1244
+ "learning_rate": 2.5328246937043525e-08,
1245
+ "logits/chosen": -0.5992367267608643,
1246
+ "logits/rejected": 0.41105660796165466,
1247
+ "logps/chosen": -325.5799560546875,
1248
+ "logps/rejected": -357.8695983886719,
1249
+ "loss": 110899.8875,
1250
+ "rewards/accuracies": 0.5625,
1251
+ "rewards/chosen": -325.5799560546875,
1252
+ "rewards/margins": 32.289649963378906,
1253
+ "rewards/rejected": -357.8695983886719,
1254
+ "step": 415
1255
+ },
1256
+ {
1257
+ "epoch": 0.8793509552473174,
1258
+ "grad_norm": 1596356.9629490953,
1259
+ "learning_rate": 2.1464952759020856e-08,
1260
+ "logits/chosen": -0.666754961013794,
1261
+ "logits/rejected": -0.003174859331920743,
1262
+ "logps/chosen": -269.9102478027344,
1263
+ "logps/rejected": -335.4573974609375,
1264
+ "loss": 111847.95,
1265
+ "rewards/accuracies": 0.6187499761581421,
1266
+ "rewards/chosen": -269.9102478027344,
1267
+ "rewards/margins": 65.54713439941406,
1268
+ "rewards/rejected": -335.4573974609375,
1269
+ "step": 420
1270
+ },
1271
+ {
1272
+ "epoch": 0.8898194190002617,
1273
+ "grad_norm": 1777896.953612317,
1274
+ "learning_rate": 1.7908016745981856e-08,
1275
+ "logits/chosen": -0.5347632765769958,
1276
+ "logits/rejected": 0.15892794728279114,
1277
+ "logps/chosen": -334.6045227050781,
1278
+ "logps/rejected": -374.3296813964844,
1279
+ "loss": 111778.7375,
1280
+ "rewards/accuracies": 0.5625,
1281
+ "rewards/chosen": -334.6045227050781,
1282
+ "rewards/margins": 39.72520065307617,
1283
+ "rewards/rejected": -374.3296813964844,
1284
+ "step": 425
1285
+ },
1286
+ {
1287
+ "epoch": 0.9002878827532059,
1288
+ "grad_norm": 1803597.2077325762,
1289
+ "learning_rate": 1.4662207078575684e-08,
1290
+ "logits/chosen": -0.5875300765037537,
1291
+ "logits/rejected": 0.1222870722413063,
1292
+ "logps/chosen": -282.852783203125,
1293
+ "logps/rejected": -356.6959228515625,
1294
+ "loss": 111337.7875,
1295
+ "rewards/accuracies": 0.643750011920929,
1296
+ "rewards/chosen": -282.852783203125,
1297
+ "rewards/margins": 73.84312438964844,
1298
+ "rewards/rejected": -356.6959228515625,
1299
+ "step": 430
1300
+ },
1301
+ {
1302
+ "epoch": 0.9107563465061502,
1303
+ "grad_norm": 2178153.4810825037,
1304
+ "learning_rate": 1.1731874863145142e-08,
1305
+ "logits/chosen": -0.4485841691493988,
1306
+ "logits/rejected": 0.1706048995256424,
1307
+ "logps/chosen": -246.25521850585938,
1308
+ "logps/rejected": -336.5995178222656,
1309
+ "loss": 112746.675,
1310
+ "rewards/accuracies": 0.668749988079071,
1311
+ "rewards/chosen": -246.25521850585938,
1312
+ "rewards/margins": 90.34431457519531,
1313
+ "rewards/rejected": -336.5995178222656,
1314
+ "step": 435
1315
+ },
1316
+ {
1317
+ "epoch": 0.9212248102590945,
1318
+ "grad_norm": 2249926.728268449,
1319
+ "learning_rate": 9.12094829893642e-09,
1320
+ "logits/chosen": -0.23983442783355713,
1321
+ "logits/rejected": 0.3341619372367859,
1322
+ "logps/chosen": -297.7192077636719,
1323
+ "logps/rejected": -405.0928649902344,
1324
+ "loss": 112266.5125,
1325
+ "rewards/accuracies": 0.65625,
1326
+ "rewards/chosen": -297.7192077636719,
1327
+ "rewards/margins": 107.37367248535156,
1328
+ "rewards/rejected": -405.0928649902344,
1329
+ "step": 440
1330
+ },
1331
+ {
1332
+ "epoch": 0.9316932740120387,
1333
+ "grad_norm": 2093448.7772529407,
1334
+ "learning_rate": 6.832927412229017e-09,
1335
+ "logits/chosen": -0.5585839152336121,
1336
+ "logits/rejected": 0.15140660107135773,
1337
+ "logps/chosen": -316.87335205078125,
1338
+ "logps/rejected": -385.70098876953125,
1339
+ "loss": 112199.175,
1340
+ "rewards/accuracies": 0.625,
1341
+ "rewards/chosen": -316.87335205078125,
1342
+ "rewards/margins": 68.82764434814453,
1343
+ "rewards/rejected": -385.70098876953125,
1344
+ "step": 445
1345
+ },
1346
+ {
1347
+ "epoch": 0.942161737764983,
1348
+ "grad_norm": 2219595.1116894637,
1349
+ "learning_rate": 4.8708793644441086e-09,
1350
+ "logits/chosen": -0.3891911506652832,
1351
+ "logits/rejected": 0.024116378277540207,
1352
+ "logps/chosen": -270.6603088378906,
1353
+ "logps/rejected": -366.87481689453125,
1354
+ "loss": 110792.1375,
1355
+ "rewards/accuracies": 0.6625000238418579,
1356
+ "rewards/chosen": -270.6603088378906,
1357
+ "rewards/margins": 96.21451568603516,
1358
+ "rewards/rejected": -366.87481689453125,
1359
+ "step": 450
1360
+ },
1361
+ {
1362
+ "epoch": 0.9526302015179272,
1363
+ "grad_norm": 2056046.2252654296,
1364
+ "learning_rate": 3.2374343405217884e-09,
1365
+ "logits/chosen": -0.3999771475791931,
1366
+ "logits/rejected": 0.3102295994758606,
1367
+ "logps/chosen": -297.7739562988281,
1368
+ "logps/rejected": -349.3359069824219,
1369
+ "loss": 111786.575,
1370
+ "rewards/accuracies": 0.574999988079071,
1371
+ "rewards/chosen": -297.7739562988281,
1372
+ "rewards/margins": 51.561973571777344,
1373
+ "rewards/rejected": -349.3359069824219,
1374
+ "step": 455
1375
+ },
1376
+ {
1377
+ "epoch": 0.9630986652708715,
1378
+ "grad_norm": 1596322.4991768566,
1379
+ "learning_rate": 1.9347820230782295e-09,
1380
+ "logits/chosen": -0.33234018087387085,
1381
+ "logits/rejected": 0.4286741614341736,
1382
+ "logps/chosen": -302.89599609375,
1383
+ "logps/rejected": -369.64752197265625,
1384
+ "loss": 110058.4875,
1385
+ "rewards/accuracies": 0.59375,
1386
+ "rewards/chosen": -302.89599609375,
1387
+ "rewards/margins": 66.75153350830078,
1388
+ "rewards/rejected": -369.64752197265625,
1389
+ "step": 460
1390
+ },
1391
+ {
1392
+ "epoch": 0.9735671290238157,
1393
+ "grad_norm": 2030583.2053086923,
1394
+ "learning_rate": 9.64668657069706e-10,
1395
+ "logits/chosen": -0.7010616064071655,
1396
+ "logits/rejected": 0.4352653920650482,
1397
+ "logps/chosen": -332.9463195800781,
1398
+ "logps/rejected": -413.53594970703125,
1399
+ "loss": 109834.325,
1400
+ "rewards/accuracies": 0.6000000238418579,
1401
+ "rewards/chosen": -332.9463195800781,
1402
+ "rewards/margins": 80.58956146240234,
1403
+ "rewards/rejected": -413.53594970703125,
1404
+ "step": 465
1405
+ },
1406
+ {
1407
+ "epoch": 0.98403559277676,
1408
+ "grad_norm": 1771708.6547032476,
1409
+ "learning_rate": 3.2839470889836627e-10,
1410
+ "logits/chosen": -0.673961877822876,
1411
+ "logits/rejected": 0.0036758959759026766,
1412
+ "logps/chosen": -312.06292724609375,
1413
+ "logps/rejected": -398.3697814941406,
1414
+ "loss": 112512.225,
1415
+ "rewards/accuracies": 0.612500011920929,
1416
+ "rewards/chosen": -312.06292724609375,
1417
+ "rewards/margins": 86.30685424804688,
1418
+ "rewards/rejected": -398.3697814941406,
1419
+ "step": 470
1420
+ },
1421
+ {
1422
+ "epoch": 0.9945040565297043,
1423
+ "grad_norm": 1840231.2095069257,
1424
+ "learning_rate": 2.6813123097352287e-11,
1425
+ "logits/chosen": -0.7123033404350281,
1426
+ "logits/rejected": 0.20311255753040314,
1427
+ "logps/chosen": -341.65423583984375,
1428
+ "logps/rejected": -375.7768859863281,
1429
+ "loss": 111344.2125,
1430
+ "rewards/accuracies": 0.5375000238418579,
1431
+ "rewards/chosen": -341.65423583984375,
1432
+ "rewards/margins": 34.122650146484375,
1433
+ "rewards/rejected": -375.7768859863281,
1434
+ "step": 475
1435
+ },
1436
+ {
1437
+ "epoch": 0.998691442030882,
1438
+ "step": 477,
1439
+ "total_flos": 0.0,
1440
+ "train_loss": 114854.6911687631,
1441
+ "train_runtime": 7479.76,
1442
+ "train_samples_per_second": 8.173,
1443
+ "train_steps_per_second": 0.064
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 sha256:08209d240fb25d6d3c95b9bfdbccd0a07021fe1ab4913d65aad01d1bfa225462
3
+ size 7224