Teng Xiao commited on
Commit
b3b4393
1 Parent(s): 4200bce

commit from TX

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: alignment-handbook/zephyr-7b-sft-full
4
+ tags:
5
+ - alignment_handbook-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - HuggingFaceH4/ultrafeedback_binarized
9
+ model-index:
10
+ - name: zephyr-7b-MI-1-selm2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # zephyr-7b-MI-1-selm2
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 4.44.0
59
+ - Pytorch 2.1.2+cu121
60
+ - Datasets 2.20.0
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": 1.8663299063716545,
5
+ "train_runtime": 8277.1533,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 7.386,
8
+ "train_steps_per_second": 0.058
9
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.44.0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
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": "4.44.0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4e34dc28eb5ebf06c3d0c2066b84995a6b65424ba936c74c9c4c46c9d97efc
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:ec6c46acf8bfc7400a4df5def62837862d22e91f5da5c443704c66477b724954
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:a323331aa96e02b9aaf69100c95bef201af4580a66de200ad9b6e6cbf25f66c4
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "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 %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 2048,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.998691442030882,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.8663299063716545,
5
+ "train_runtime": 8277.1533,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 7.386,
8
+ "train_steps_per_second": 0.058
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 12.869433218842474,
14
+ "learning_rate": 5.208333333333333e-08,
15
+ "logits/chosen": -2.7303454875946045,
16
+ "logits/rejected": -2.6748926639556885,
17
+ "logps/chosen": -1.0383304357528687,
18
+ "logps/rejected": -1.093923807144165,
19
+ "loss": 2.0262,
20
+ "rewards/accuracies": 0.518750011920929,
21
+ "rewards/chosen": -1.0383304357528687,
22
+ "rewards/margins": 0.05559344217181206,
23
+ "rewards/rejected": -1.093923807144165,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.02093692750588851,
28
+ "grad_norm": 12.963970831519292,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": -2.8506417274475098,
31
+ "logits/rejected": -2.7654807567596436,
32
+ "logps/chosen": -1.025138020515442,
33
+ "logps/rejected": -1.1677943468093872,
34
+ "loss": 2.0292,
35
+ "rewards/accuracies": 0.581250011920929,
36
+ "rewards/chosen": -1.025138020515442,
37
+ "rewards/margins": 0.1426563411951065,
38
+ "rewards/rejected": -1.1677943468093872,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.031405391258832765,
43
+ "grad_norm": 15.099715830730236,
44
+ "learning_rate": 1.5624999999999999e-07,
45
+ "logits/chosen": -2.77595853805542,
46
+ "logits/rejected": -2.7310924530029297,
47
+ "logps/chosen": -1.0620777606964111,
48
+ "logps/rejected": -1.1130949258804321,
49
+ "loss": 2.0243,
50
+ "rewards/accuracies": 0.5375000238418579,
51
+ "rewards/chosen": -1.0620777606964111,
52
+ "rewards/margins": 0.051017045974731445,
53
+ "rewards/rejected": -1.1130949258804321,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.04187385501177702,
58
+ "grad_norm": 14.125874639614404,
59
+ "learning_rate": 2.0833333333333333e-07,
60
+ "logits/chosen": -2.798926830291748,
61
+ "logits/rejected": -2.6963000297546387,
62
+ "logps/chosen": -1.026979684829712,
63
+ "logps/rejected": -1.1289321184158325,
64
+ "loss": 2.0224,
65
+ "rewards/accuracies": 0.5562499761581421,
66
+ "rewards/chosen": -1.026979684829712,
67
+ "rewards/margins": 0.1019524484872818,
68
+ "rewards/rejected": -1.1289321184158325,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.05234231876472128,
73
+ "grad_norm": 12.739023934080043,
74
+ "learning_rate": 2.604166666666667e-07,
75
+ "logits/chosen": -2.797764301300049,
76
+ "logits/rejected": -2.6895253658294678,
77
+ "logps/chosen": -0.9821299314498901,
78
+ "logps/rejected": -1.1730941534042358,
79
+ "loss": 1.9952,
80
+ "rewards/accuracies": 0.5687500238418579,
81
+ "rewards/chosen": -0.9821299314498901,
82
+ "rewards/margins": 0.19096432626247406,
83
+ "rewards/rejected": -1.1730941534042358,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06281078251766553,
88
+ "grad_norm": 18.287014857226495,
89
+ "learning_rate": 3.1249999999999997e-07,
90
+ "logits/chosen": -2.7723119258880615,
91
+ "logits/rejected": -2.7337851524353027,
92
+ "logps/chosen": -1.0000275373458862,
93
+ "logps/rejected": -1.0346484184265137,
94
+ "loss": 1.9952,
95
+ "rewards/accuracies": 0.5625,
96
+ "rewards/chosen": -1.0000275373458862,
97
+ "rewards/margins": 0.034620799124240875,
98
+ "rewards/rejected": -1.0346484184265137,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07327924627060979,
103
+ "grad_norm": 17.8360996219737,
104
+ "learning_rate": 3.645833333333333e-07,
105
+ "logits/chosen": -2.7883362770080566,
106
+ "logits/rejected": -2.715696334838867,
107
+ "logps/chosen": -1.0128945112228394,
108
+ "logps/rejected": -1.225642442703247,
109
+ "loss": 1.9748,
110
+ "rewards/accuracies": 0.59375,
111
+ "rewards/chosen": -1.0128945112228394,
112
+ "rewards/margins": 0.2127479612827301,
113
+ "rewards/rejected": -1.225642442703247,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08374771002355404,
118
+ "grad_norm": 18.333373463486794,
119
+ "learning_rate": 4.1666666666666667e-07,
120
+ "logits/chosen": -2.7703633308410645,
121
+ "logits/rejected": -2.6918962001800537,
122
+ "logps/chosen": -1.0058094263076782,
123
+ "logps/rejected": -1.131239891052246,
124
+ "loss": 1.9619,
125
+ "rewards/accuracies": 0.59375,
126
+ "rewards/chosen": -1.0058094263076782,
127
+ "rewards/margins": 0.12543055415153503,
128
+ "rewards/rejected": -1.131239891052246,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.0942161737764983,
133
+ "grad_norm": 15.971248778309374,
134
+ "learning_rate": 4.6874999999999996e-07,
135
+ "logits/chosen": -2.732913017272949,
136
+ "logits/rejected": -2.7122368812561035,
137
+ "logps/chosen": -0.9598785638809204,
138
+ "logps/rejected": -1.1564022302627563,
139
+ "loss": 1.9542,
140
+ "rewards/accuracies": 0.6187499761581421,
141
+ "rewards/chosen": -0.9598785638809204,
142
+ "rewards/margins": 0.196523517370224,
143
+ "rewards/rejected": -1.1564022302627563,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.10468463752944256,
148
+ "grad_norm": 23.366392169452176,
149
+ "learning_rate": 4.999731868769026e-07,
150
+ "logits/chosen": -2.672335624694824,
151
+ "logits/rejected": -2.6771888732910156,
152
+ "logps/chosen": -1.0208399295806885,
153
+ "logps/rejected": -1.2945979833602905,
154
+ "loss": 1.9581,
155
+ "rewards/accuracies": 0.612500011920929,
156
+ "rewards/chosen": -1.0208399295806885,
157
+ "rewards/margins": 0.2737579941749573,
158
+ "rewards/rejected": -1.2945979833602905,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11515310128238682,
163
+ "grad_norm": 19.929116348471684,
164
+ "learning_rate": 4.996716052911017e-07,
165
+ "logits/chosen": -2.7723307609558105,
166
+ "logits/rejected": -2.747865676879883,
167
+ "logps/chosen": -1.0856590270996094,
168
+ "logps/rejected": -1.219327449798584,
169
+ "loss": 1.9648,
170
+ "rewards/accuracies": 0.574999988079071,
171
+ "rewards/chosen": -1.0856590270996094,
172
+ "rewards/margins": 0.13366840779781342,
173
+ "rewards/rejected": -1.219327449798584,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.12562156503533106,
178
+ "grad_norm": 23.73282923950602,
179
+ "learning_rate": 4.990353313429303e-07,
180
+ "logits/chosen": -2.7040231227874756,
181
+ "logits/rejected": -2.6466102600097656,
182
+ "logps/chosen": -1.0688912868499756,
183
+ "logps/rejected": -1.260387659072876,
184
+ "loss": 1.9501,
185
+ "rewards/accuracies": 0.5562499761581421,
186
+ "rewards/chosen": -1.0688912868499756,
187
+ "rewards/margins": 0.19149653613567352,
188
+ "rewards/rejected": -1.260387659072876,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.1360900287882753,
193
+ "grad_norm": 18.942833820850367,
194
+ "learning_rate": 4.980652179769217e-07,
195
+ "logits/chosen": -2.716078519821167,
196
+ "logits/rejected": -2.7220449447631836,
197
+ "logps/chosen": -1.027010440826416,
198
+ "logps/rejected": -1.2260963916778564,
199
+ "loss": 1.9536,
200
+ "rewards/accuracies": 0.612500011920929,
201
+ "rewards/chosen": -1.027010440826416,
202
+ "rewards/margins": 0.199085995554924,
203
+ "rewards/rejected": -1.2260963916778564,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.14655849254121958,
208
+ "grad_norm": 22.28146945050057,
209
+ "learning_rate": 4.967625656594781e-07,
210
+ "logits/chosen": -2.7145752906799316,
211
+ "logits/rejected": -2.6811351776123047,
212
+ "logps/chosen": -1.074029564857483,
213
+ "logps/rejected": -1.3044393062591553,
214
+ "loss": 1.9325,
215
+ "rewards/accuracies": 0.574999988079071,
216
+ "rewards/chosen": -1.074029564857483,
217
+ "rewards/margins": 0.2304096519947052,
218
+ "rewards/rejected": -1.3044393062591553,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.15702695629416383,
223
+ "grad_norm": 30.956539188115524,
224
+ "learning_rate": 4.951291206355559e-07,
225
+ "logits/chosen": -2.640056610107422,
226
+ "logits/rejected": -2.5216145515441895,
227
+ "logps/chosen": -1.0524249076843262,
228
+ "logps/rejected": -1.358999490737915,
229
+ "loss": 1.9439,
230
+ "rewards/accuracies": 0.6187499761581421,
231
+ "rewards/chosen": -1.0524249076843262,
232
+ "rewards/margins": 0.3065745234489441,
233
+ "rewards/rejected": -1.358999490737915,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.16749542004710807,
238
+ "grad_norm": 19.173789722918567,
239
+ "learning_rate": 4.93167072587771e-07,
240
+ "logits/chosen": -2.5955734252929688,
241
+ "logits/rejected": -2.5555953979492188,
242
+ "logps/chosen": -1.0017749071121216,
243
+ "logps/rejected": -1.4020613431930542,
244
+ "loss": 1.9082,
245
+ "rewards/accuracies": 0.6875,
246
+ "rewards/chosen": -1.0017749071121216,
247
+ "rewards/margins": 0.4002866744995117,
248
+ "rewards/rejected": -1.4020613431930542,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.17796388380005235,
253
+ "grad_norm": 26.77907962647508,
254
+ "learning_rate": 4.908790517010636e-07,
255
+ "logits/chosen": -2.730196475982666,
256
+ "logits/rejected": -2.6316986083984375,
257
+ "logps/chosen": -1.0233409404754639,
258
+ "logps/rejected": -1.4025558233261108,
259
+ "loss": 1.9293,
260
+ "rewards/accuracies": 0.6499999761581421,
261
+ "rewards/chosen": -1.0233409404754639,
262
+ "rewards/margins": 0.3792147934436798,
263
+ "rewards/rejected": -1.4025558233261108,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.1884323475529966,
268
+ "grad_norm": 20.94451147733862,
269
+ "learning_rate": 4.882681251368548e-07,
270
+ "logits/chosen": -2.7333931922912598,
271
+ "logits/rejected": -2.594924211502075,
272
+ "logps/chosen": -1.0183618068695068,
273
+ "logps/rejected": -1.4752748012542725,
274
+ "loss": 1.903,
275
+ "rewards/accuracies": 0.637499988079071,
276
+ "rewards/chosen": -1.0183618068695068,
277
+ "rewards/margins": 0.4569129943847656,
278
+ "rewards/rejected": -1.4752748012542725,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.19890081130594087,
283
+ "grad_norm": 27.23027264774861,
284
+ "learning_rate": 4.853377929214243e-07,
285
+ "logits/chosen": -2.6479899883270264,
286
+ "logits/rejected": -2.612231492996216,
287
+ "logps/chosen": -0.9796420335769653,
288
+ "logps/rejected": -1.2683651447296143,
289
+ "loss": 1.9133,
290
+ "rewards/accuracies": 0.612500011920929,
291
+ "rewards/chosen": -0.9796420335769653,
292
+ "rewards/margins": 0.28872328996658325,
293
+ "rewards/rejected": -1.2683651447296143,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.2093692750588851,
298
+ "grad_norm": 20.647765632695478,
299
+ "learning_rate": 4.820919832540181e-07,
300
+ "logits/chosen": -2.7929205894470215,
301
+ "logits/rejected": -2.730536460876465,
302
+ "logps/chosen": -1.0671679973602295,
303
+ "logps/rejected": -1.3122754096984863,
304
+ "loss": 1.9562,
305
+ "rewards/accuracies": 0.5249999761581421,
306
+ "rewards/chosen": -1.0671679973602295,
307
+ "rewards/margins": 0.24510732293128967,
308
+ "rewards/rejected": -1.3122754096984863,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.21983773881182936,
313
+ "grad_norm": 19.882099174165575,
314
+ "learning_rate": 4.785350472409791e-07,
315
+ "logits/chosen": -2.7290585041046143,
316
+ "logits/rejected": -2.661957263946533,
317
+ "logps/chosen": -1.1218279600143433,
318
+ "logps/rejected": -1.4676848649978638,
319
+ "loss": 1.8476,
320
+ "rewards/accuracies": 0.6499999761581421,
321
+ "rewards/chosen": -1.1218279600143433,
322
+ "rewards/margins": 0.3458569347858429,
323
+ "rewards/rejected": -1.4676848649978638,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23030620256477363,
328
+ "grad_norm": 29.356563953547646,
329
+ "learning_rate": 4.7467175306295647e-07,
330
+ "logits/chosen": -2.677428722381592,
331
+ "logits/rejected": -2.587128162384033,
332
+ "logps/chosen": -1.0471330881118774,
333
+ "logps/rejected": -1.3834892511367798,
334
+ "loss": 1.8785,
335
+ "rewards/accuracies": 0.6000000238418579,
336
+ "rewards/chosen": -1.0471330881118774,
337
+ "rewards/margins": 0.33635613322257996,
338
+ "rewards/rejected": -1.3834892511367798,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.24077466631771788,
343
+ "grad_norm": 22.70599557212694,
344
+ "learning_rate": 4.70507279583015e-07,
345
+ "logits/chosen": -2.699206590652466,
346
+ "logits/rejected": -2.6752054691314697,
347
+ "logps/chosen": -1.037027359008789,
348
+ "logps/rejected": -1.2504864931106567,
349
+ "loss": 1.8781,
350
+ "rewards/accuracies": 0.625,
351
+ "rewards/chosen": -1.037027359008789,
352
+ "rewards/margins": 0.21345916390419006,
353
+ "rewards/rejected": -1.2504864931106567,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2512431300706621,
358
+ "grad_norm": 22.718720973130083,
359
+ "learning_rate": 4.6604720940421207e-07,
360
+ "logits/chosen": -2.7028520107269287,
361
+ "logits/rejected": -2.581420660018921,
362
+ "logps/chosen": -0.958320140838623,
363
+ "logps/rejected": -1.4017829895019531,
364
+ "loss": 1.8894,
365
+ "rewards/accuracies": 0.6312500238418579,
366
+ "rewards/chosen": -0.958320140838623,
367
+ "rewards/margins": 0.44346290826797485,
368
+ "rewards/rejected": -1.4017829895019531,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.26171159382360637,
373
+ "grad_norm": 27.839637111582167,
374
+ "learning_rate": 4.612975213859487e-07,
375
+ "logits/chosen": -2.5790719985961914,
376
+ "logits/rejected": -2.534557342529297,
377
+ "logps/chosen": -1.0435621738433838,
378
+ "logps/rejected": -1.4774357080459595,
379
+ "loss": 1.9045,
380
+ "rewards/accuracies": 0.668749988079071,
381
+ "rewards/chosen": -1.0435621738433838,
382
+ "rewards/margins": 0.43387335538864136,
383
+ "rewards/rejected": -1.4774357080459595,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.2721800575765506,
388
+ "grad_norm": 24.64049193676725,
389
+ "learning_rate": 4.5626458262912735e-07,
390
+ "logits/chosen": -2.6262755393981934,
391
+ "logits/rejected": -2.5886640548706055,
392
+ "logps/chosen": -1.1033378839492798,
393
+ "logps/rejected": -1.5101052522659302,
394
+ "loss": 1.8774,
395
+ "rewards/accuracies": 0.668749988079071,
396
+ "rewards/chosen": -1.1033378839492798,
397
+ "rewards/margins": 0.40676751732826233,
398
+ "rewards/rejected": -1.5101052522659302,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.2826485213294949,
403
+ "grad_norm": 24.054739646210816,
404
+ "learning_rate": 4.5095513994085974e-07,
405
+ "logits/chosen": -2.5852103233337402,
406
+ "logits/rejected": -2.5114357471466064,
407
+ "logps/chosen": -1.036170244216919,
408
+ "logps/rejected": -1.5170302391052246,
409
+ "loss": 1.8964,
410
+ "rewards/accuracies": 0.6625000238418579,
411
+ "rewards/chosen": -1.036170244216919,
412
+ "rewards/margins": 0.4808600842952728,
413
+ "rewards/rejected": -1.5170302391052246,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.29311698508243916,
418
+ "grad_norm": 32.17420726348548,
419
+ "learning_rate": 4.453763107901675e-07,
420
+ "logits/chosen": -2.5846521854400635,
421
+ "logits/rejected": -2.540843963623047,
422
+ "logps/chosen": -1.1467993259429932,
423
+ "logps/rejected": -1.3851490020751953,
424
+ "loss": 1.958,
425
+ "rewards/accuracies": 0.5375000238418579,
426
+ "rewards/chosen": -1.1467993259429932,
427
+ "rewards/margins": 0.23834970593452454,
428
+ "rewards/rejected": -1.3851490020751953,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.3035854488353834,
433
+ "grad_norm": 31.293592588837402,
434
+ "learning_rate": 4.395355737667985e-07,
435
+ "logits/chosen": -2.5842862129211426,
436
+ "logits/rejected": -2.481231451034546,
437
+ "logps/chosen": -1.019995927810669,
438
+ "logps/rejected": -1.450305700302124,
439
+ "loss": 1.8621,
440
+ "rewards/accuracies": 0.625,
441
+ "rewards/chosen": -1.019995927810669,
442
+ "rewards/margins": 0.43030983209609985,
443
+ "rewards/rejected": -1.450305700302124,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.31405391258832765,
448
+ "grad_norm": 31.395757438350795,
449
+ "learning_rate": 4.3344075855595097e-07,
450
+ "logits/chosen": -2.6442532539367676,
451
+ "logits/rejected": -2.5464065074920654,
452
+ "logps/chosen": -1.066561222076416,
453
+ "logps/rejected": -1.4769625663757324,
454
+ "loss": 1.8856,
455
+ "rewards/accuracies": 0.581250011920929,
456
+ "rewards/chosen": -1.066561222076416,
457
+ "rewards/margins": 0.4104014039039612,
458
+ "rewards/rejected": -1.4769625663757324,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.3245223763412719,
463
+ "grad_norm": 54.99577539115471,
464
+ "learning_rate": 4.271000354423425e-07,
465
+ "logits/chosen": -2.584909200668335,
466
+ "logits/rejected": -2.5346925258636475,
467
+ "logps/chosen": -1.1342883110046387,
468
+ "logps/rejected": -1.709241509437561,
469
+ "loss": 1.8796,
470
+ "rewards/accuracies": 0.7124999761581421,
471
+ "rewards/chosen": -1.1342883110046387,
472
+ "rewards/margins": 0.5749532580375671,
473
+ "rewards/rejected": -1.709241509437561,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.33499084009421615,
478
+ "grad_norm": 62.43588869532461,
479
+ "learning_rate": 4.2052190435769554e-07,
480
+ "logits/chosen": -2.5957446098327637,
481
+ "logits/rejected": -2.523685932159424,
482
+ "logps/chosen": -1.048396348953247,
483
+ "logps/rejected": -1.6725311279296875,
484
+ "loss": 1.8954,
485
+ "rewards/accuracies": 0.6812499761581421,
486
+ "rewards/chosen": -1.048396348953247,
487
+ "rewards/margins": 0.6241349577903748,
488
+ "rewards/rejected": -1.6725311279296875,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.34545930384716045,
493
+ "grad_norm": 33.35503026194792,
494
+ "learning_rate": 4.137151834863213e-07,
495
+ "logits/chosen": -2.730977773666382,
496
+ "logits/rejected": -2.645996570587158,
497
+ "logps/chosen": -1.0159308910369873,
498
+ "logps/rejected": -1.359212040901184,
499
+ "loss": 1.8352,
500
+ "rewards/accuracies": 0.612500011920929,
501
+ "rewards/chosen": -1.0159308910369873,
502
+ "rewards/margins": 0.343281090259552,
503
+ "rewards/rejected": -1.359212040901184,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3559277676001047,
508
+ "grad_norm": 32.04170211845891,
509
+ "learning_rate": 4.0668899744407567e-07,
510
+ "logits/chosen": -2.7265422344207764,
511
+ "logits/rejected": -2.597689151763916,
512
+ "logps/chosen": -0.9698517918586731,
513
+ "logps/rejected": -1.3197566270828247,
514
+ "loss": 1.8688,
515
+ "rewards/accuracies": 0.643750011920929,
516
+ "rewards/chosen": -0.9698517918586731,
517
+ "rewards/margins": 0.349904865026474,
518
+ "rewards/rejected": -1.3197566270828247,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.36639623135304894,
523
+ "grad_norm": 27.34421984947454,
524
+ "learning_rate": 3.994527650465352e-07,
525
+ "logits/chosen": -2.652785062789917,
526
+ "logits/rejected": -2.5916075706481934,
527
+ "logps/chosen": -0.9570480585098267,
528
+ "logps/rejected": -1.3661720752716064,
529
+ "loss": 1.8595,
530
+ "rewards/accuracies": 0.6875,
531
+ "rewards/chosen": -0.9570480585098267,
532
+ "rewards/margins": 0.409123957157135,
533
+ "rewards/rejected": -1.3661720752716064,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.3768646951059932,
538
+ "grad_norm": 35.429346147889426,
539
+ "learning_rate": 3.920161866827889e-07,
540
+ "logits/chosen": -2.6718568801879883,
541
+ "logits/rejected": -2.613348960876465,
542
+ "logps/chosen": -1.037642240524292,
543
+ "logps/rejected": -1.553224802017212,
544
+ "loss": 1.8512,
545
+ "rewards/accuracies": 0.6499999761581421,
546
+ "rewards/chosen": -1.037642240524292,
547
+ "rewards/margins": 0.5155824422836304,
548
+ "rewards/rejected": -1.553224802017212,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.38733315885893743,
553
+ "grad_norm": 21.700575234978658,
554
+ "learning_rate": 3.8438923131177237e-07,
555
+ "logits/chosen": -2.6914803981781006,
556
+ "logits/rejected": -2.6440558433532715,
557
+ "logps/chosen": -0.9652795791625977,
558
+ "logps/rejected": -1.3787884712219238,
559
+ "loss": 1.8051,
560
+ "rewards/accuracies": 0.6625000238418579,
561
+ "rewards/chosen": -0.9652795791625977,
562
+ "rewards/margins": 0.41350871324539185,
563
+ "rewards/rejected": -1.3787884712219238,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.39780162261188173,
568
+ "grad_norm": 32.670099112476585,
569
+ "learning_rate": 3.765821230985757e-07,
570
+ "logits/chosen": -2.6735928058624268,
571
+ "logits/rejected": -2.640225648880005,
572
+ "logps/chosen": -1.0144473314285278,
573
+ "logps/rejected": -1.4563645124435425,
574
+ "loss": 1.8273,
575
+ "rewards/accuracies": 0.6625000238418579,
576
+ "rewards/chosen": -1.0144473314285278,
577
+ "rewards/margins": 0.4419172406196594,
578
+ "rewards/rejected": -1.4563645124435425,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.408270086364826,
583
+ "grad_norm": 25.238718639520766,
584
+ "learning_rate": 3.6860532770864005e-07,
585
+ "logits/chosen": -2.705747365951538,
586
+ "logits/rejected": -2.6104602813720703,
587
+ "logps/chosen": -1.0011558532714844,
588
+ "logps/rejected": -1.5988446474075317,
589
+ "loss": 1.8926,
590
+ "rewards/accuracies": 0.71875,
591
+ "rewards/chosen": -1.0011558532714844,
592
+ "rewards/margins": 0.5976886749267578,
593
+ "rewards/rejected": -1.5988446474075317,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.4187385501177702,
598
+ "grad_norm": 23.97929885445044,
599
+ "learning_rate": 3.604695382782159e-07,
600
+ "logits/chosen": -2.644472122192383,
601
+ "logits/rejected": -2.5559470653533936,
602
+ "logps/chosen": -1.0497673749923706,
603
+ "logps/rejected": -1.3750804662704468,
604
+ "loss": 1.853,
605
+ "rewards/accuracies": 0.6187499761581421,
606
+ "rewards/chosen": -1.0497673749923706,
607
+ "rewards/margins": 0.32531291246414185,
608
+ "rewards/rejected": -1.3750804662704468,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.42920701387071447,
613
+ "grad_norm": 24.184854862916072,
614
+ "learning_rate": 3.5218566107988867e-07,
615
+ "logits/chosen": -2.730355739593506,
616
+ "logits/rejected": -2.683979034423828,
617
+ "logps/chosen": -0.9922051429748535,
618
+ "logps/rejected": -1.5398856401443481,
619
+ "loss": 1.8724,
620
+ "rewards/accuracies": 0.6312500238418579,
621
+ "rewards/chosen": -0.9922051429748535,
622
+ "rewards/margins": 0.5476802587509155,
623
+ "rewards/rejected": -1.5398856401443481,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.4396754776236587,
628
+ "grad_norm": 26.69782735208681,
629
+ "learning_rate": 3.4376480090239047e-07,
630
+ "logits/chosen": -2.5600266456604004,
631
+ "logits/rejected": -2.5641884803771973,
632
+ "logps/chosen": -1.0444707870483398,
633
+ "logps/rejected": -1.4003455638885498,
634
+ "loss": 1.8764,
635
+ "rewards/accuracies": 0.637499988079071,
636
+ "rewards/chosen": -1.0444707870483398,
637
+ "rewards/margins": 0.35587459802627563,
638
+ "rewards/rejected": -1.4003455638885498,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.45014394137660296,
643
+ "grad_norm": 39.9600540211152,
644
+ "learning_rate": 3.3521824616429284e-07,
645
+ "logits/chosen": -2.594709873199463,
646
+ "logits/rejected": -2.5683107376098633,
647
+ "logps/chosen": -1.126425862312317,
648
+ "logps/rejected": -1.614018440246582,
649
+ "loss": 1.8882,
650
+ "rewards/accuracies": 0.6812499761581421,
651
+ "rewards/chosen": -1.126425862312317,
652
+ "rewards/margins": 0.4875926077365875,
653
+ "rewards/rejected": -1.614018440246582,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.46061240512954726,
658
+ "grad_norm": 35.61682268118621,
659
+ "learning_rate": 3.265574537815398e-07,
660
+ "logits/chosen": -2.5961153507232666,
661
+ "logits/rejected": -2.541783094406128,
662
+ "logps/chosen": -1.102477788925171,
663
+ "logps/rejected": -1.5613858699798584,
664
+ "loss": 1.8517,
665
+ "rewards/accuracies": 0.6499999761581421,
666
+ "rewards/chosen": -1.102477788925171,
667
+ "rewards/margins": 0.45890823006629944,
668
+ "rewards/rejected": -1.5613858699798584,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.4710808688824915,
673
+ "grad_norm": 28.356766220400576,
674
+ "learning_rate": 3.1779403380910425e-07,
675
+ "logits/chosen": -2.6027655601501465,
676
+ "logits/rejected": -2.4865376949310303,
677
+ "logps/chosen": -1.0470962524414062,
678
+ "logps/rejected": -1.5330448150634766,
679
+ "loss": 1.8686,
680
+ "rewards/accuracies": 0.71875,
681
+ "rewards/chosen": -1.0470962524414062,
682
+ "rewards/margins": 0.4859485626220703,
683
+ "rewards/rejected": -1.5330448150634766,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.48154933263543576,
688
+ "grad_norm": 46.96042544932364,
689
+ "learning_rate": 3.0893973387735683e-07,
690
+ "logits/chosen": -2.6151013374328613,
691
+ "logits/rejected": -2.59317684173584,
692
+ "logps/chosen": -1.0420851707458496,
693
+ "logps/rejected": -1.637976050376892,
694
+ "loss": 1.8322,
695
+ "rewards/accuracies": 0.706250011920929,
696
+ "rewards/chosen": -1.0420851707458496,
697
+ "rewards/margins": 0.5958911180496216,
698
+ "rewards/rejected": -1.637976050376892,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.49201779638838,
703
+ "grad_norm": 26.100391626514853,
704
+ "learning_rate": 3.000064234440111e-07,
705
+ "logits/chosen": -2.5428245067596436,
706
+ "logits/rejected": -2.4851417541503906,
707
+ "logps/chosen": -1.0481144189834595,
708
+ "logps/rejected": -1.4148355722427368,
709
+ "loss": 1.8385,
710
+ "rewards/accuracies": 0.65625,
711
+ "rewards/chosen": -1.0481144189834595,
712
+ "rewards/margins": 0.3667212724685669,
713
+ "rewards/rejected": -1.4148355722427368,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5024862601413242,
718
+ "grad_norm": 24.14989026973158,
719
+ "learning_rate": 2.910060778827554e-07,
720
+ "logits/chosen": -2.537334680557251,
721
+ "logits/rejected": -2.472512722015381,
722
+ "logps/chosen": -1.0776469707489014,
723
+ "logps/rejected": -1.6333630084991455,
724
+ "loss": 1.8508,
725
+ "rewards/accuracies": 0.6937500238418579,
726
+ "rewards/chosen": -1.0776469707489014,
727
+ "rewards/margins": 0.5557159185409546,
728
+ "rewards/rejected": -1.6333630084991455,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5129547238942685,
733
+ "grad_norm": 32.38845341862983,
734
+ "learning_rate": 2.8195076242990116e-07,
735
+ "logits/chosen": -2.6101131439208984,
736
+ "logits/rejected": -2.5712387561798096,
737
+ "logps/chosen": -0.9908210635185242,
738
+ "logps/rejected": -1.6324228048324585,
739
+ "loss": 1.8075,
740
+ "rewards/accuracies": 0.675000011920929,
741
+ "rewards/chosen": -0.9908210635185242,
742
+ "rewards/margins": 0.6416017413139343,
743
+ "rewards/rejected": -1.6324228048324585,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.5234231876472127,
748
+ "grad_norm": 24.243213200791057,
749
+ "learning_rate": 2.7285261601056697e-07,
750
+ "logits/chosen": -2.559380292892456,
751
+ "logits/rejected": -2.4537248611450195,
752
+ "logps/chosen": -1.0512077808380127,
753
+ "logps/rejected": -1.6259485483169556,
754
+ "loss": 1.8615,
755
+ "rewards/accuracies": 0.6812499761581421,
756
+ "rewards/chosen": -1.0512077808380127,
757
+ "rewards/margins": 0.5747405290603638,
758
+ "rewards/rejected": -1.6259485483169556,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.533891651400157,
763
+ "grad_norm": 24.228357677990427,
764
+ "learning_rate": 2.6372383496608186e-07,
765
+ "logits/chosen": -2.654383420944214,
766
+ "logits/rejected": -2.566788911819458,
767
+ "logps/chosen": -1.0131515264511108,
768
+ "logps/rejected": -1.4951848983764648,
769
+ "loss": 1.8526,
770
+ "rewards/accuracies": 0.574999988079071,
771
+ "rewards/chosen": -1.0131515264511108,
772
+ "rewards/margins": 0.4820333421230316,
773
+ "rewards/rejected": -1.4951848983764648,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5443601151531012,
778
+ "grad_norm": 26.47263727780241,
779
+ "learning_rate": 2.5457665670441937e-07,
780
+ "logits/chosen": -2.597144603729248,
781
+ "logits/rejected": -2.572925090789795,
782
+ "logps/chosen": -0.9740694761276245,
783
+ "logps/rejected": -1.3979696035385132,
784
+ "loss": 1.8422,
785
+ "rewards/accuracies": 0.6625000238418579,
786
+ "rewards/chosen": -0.9740694761276245,
787
+ "rewards/margins": 0.4239000678062439,
788
+ "rewards/rejected": -1.3979696035385132,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5548285789060455,
793
+ "grad_norm": 22.019445712488015,
794
+ "learning_rate": 2.454233432955807e-07,
795
+ "logits/chosen": -2.612497329711914,
796
+ "logits/rejected": -2.5739381313323975,
797
+ "logps/chosen": -1.0217043161392212,
798
+ "logps/rejected": -1.4334819316864014,
799
+ "loss": 1.8467,
800
+ "rewards/accuracies": 0.6937500238418579,
801
+ "rewards/chosen": -1.0217043161392212,
802
+ "rewards/margins": 0.4117775857448578,
803
+ "rewards/rejected": -1.4334819316864014,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.5652970426589898,
808
+ "grad_norm": 31.0373082982515,
809
+ "learning_rate": 2.3627616503391812e-07,
810
+ "logits/chosen": -2.673020839691162,
811
+ "logits/rejected": -2.6832852363586426,
812
+ "logps/chosen": -1.1109861135482788,
813
+ "logps/rejected": -1.4625297784805298,
814
+ "loss": 1.8524,
815
+ "rewards/accuracies": 0.6312500238418579,
816
+ "rewards/chosen": -1.1109861135482788,
817
+ "rewards/margins": 0.3515436351299286,
818
+ "rewards/rejected": -1.4625297784805298,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.575765506411934,
823
+ "grad_norm": 29.601053617457204,
824
+ "learning_rate": 2.2714738398943308e-07,
825
+ "logits/chosen": -2.6691536903381348,
826
+ "logits/rejected": -2.587501049041748,
827
+ "logps/chosen": -1.0023844242095947,
828
+ "logps/rejected": -1.6990854740142822,
829
+ "loss": 1.7818,
830
+ "rewards/accuracies": 0.6812499761581421,
831
+ "rewards/chosen": -1.0023844242095947,
832
+ "rewards/margins": 0.6967008113861084,
833
+ "rewards/rejected": -1.6990854740142822,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.5862339701648783,
838
+ "grad_norm": 23.304378897117243,
839
+ "learning_rate": 2.1804923757009882e-07,
840
+ "logits/chosen": -2.7478485107421875,
841
+ "logits/rejected": -2.6739115715026855,
842
+ "logps/chosen": -0.967931866645813,
843
+ "logps/rejected": -1.6212472915649414,
844
+ "loss": 1.8289,
845
+ "rewards/accuracies": 0.6312500238418579,
846
+ "rewards/chosen": -0.967931866645813,
847
+ "rewards/margins": 0.6533153653144836,
848
+ "rewards/rejected": -1.6212472915649414,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.5967024339178225,
853
+ "grad_norm": 30.765932632186015,
854
+ "learning_rate": 2.089939221172446e-07,
855
+ "logits/chosen": -2.683306932449341,
856
+ "logits/rejected": -2.599849224090576,
857
+ "logps/chosen": -1.079810380935669,
858
+ "logps/rejected": -1.5674939155578613,
859
+ "loss": 1.8595,
860
+ "rewards/accuracies": 0.6499999761581421,
861
+ "rewards/chosen": -1.079810380935669,
862
+ "rewards/margins": 0.4876834750175476,
863
+ "rewards/rejected": -1.5674939155578613,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6071708976707668,
868
+ "grad_norm": 29.814903147144946,
869
+ "learning_rate": 1.9999357655598891e-07,
870
+ "logits/chosen": -2.6533594131469727,
871
+ "logits/rejected": -2.5845093727111816,
872
+ "logps/chosen": -1.0454188585281372,
873
+ "logps/rejected": -1.3878004550933838,
874
+ "loss": 1.824,
875
+ "rewards/accuracies": 0.6499999761581421,
876
+ "rewards/chosen": -1.0454188585281372,
877
+ "rewards/margins": 0.3423817753791809,
878
+ "rewards/rejected": -1.3878004550933838,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6176393614237111,
883
+ "grad_norm": 27.45666647767728,
884
+ "learning_rate": 1.9106026612264315e-07,
885
+ "logits/chosen": -2.6601853370666504,
886
+ "logits/rejected": -2.6058852672576904,
887
+ "logps/chosen": -1.038104772567749,
888
+ "logps/rejected": -1.3897347450256348,
889
+ "loss": 1.8319,
890
+ "rewards/accuracies": 0.643750011920929,
891
+ "rewards/chosen": -1.038104772567749,
892
+ "rewards/margins": 0.3516300320625305,
893
+ "rewards/rejected": -1.3897347450256348,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6281078251766553,
898
+ "grad_norm": 30.25718786399205,
899
+ "learning_rate": 1.8220596619089573e-07,
900
+ "logits/chosen": -2.5553667545318604,
901
+ "logits/rejected": -2.451190233230591,
902
+ "logps/chosen": -1.108663558959961,
903
+ "logps/rejected": -1.5200892686843872,
904
+ "loss": 1.8653,
905
+ "rewards/accuracies": 0.6499999761581421,
906
+ "rewards/chosen": -1.108663558959961,
907
+ "rewards/margins": 0.4114256501197815,
908
+ "rewards/rejected": -1.5200892686843872,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6385762889295996,
913
+ "grad_norm": 30.020985917091327,
914
+ "learning_rate": 1.7344254621846017e-07,
915
+ "logits/chosen": -2.640211343765259,
916
+ "logits/rejected": -2.6043474674224854,
917
+ "logps/chosen": -1.0029397010803223,
918
+ "logps/rejected": -1.265366792678833,
919
+ "loss": 1.8019,
920
+ "rewards/accuracies": 0.606249988079071,
921
+ "rewards/chosen": -1.0029397010803223,
922
+ "rewards/margins": 0.2624271512031555,
923
+ "rewards/rejected": -1.265366792678833,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6490447526825438,
928
+ "grad_norm": 35.00385114807507,
929
+ "learning_rate": 1.647817538357072e-07,
930
+ "logits/chosen": -2.629307270050049,
931
+ "logits/rejected": -2.4974796772003174,
932
+ "logps/chosen": -1.0108293294906616,
933
+ "logps/rejected": -1.5987032651901245,
934
+ "loss": 1.825,
935
+ "rewards/accuracies": 0.6625000238418579,
936
+ "rewards/chosen": -1.0108293294906616,
937
+ "rewards/margins": 0.5878738164901733,
938
+ "rewards/rejected": -1.5987032651901245,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6595132164354881,
943
+ "grad_norm": 33.95334568069759,
944
+ "learning_rate": 1.562351990976095e-07,
945
+ "logits/chosen": -2.6276791095733643,
946
+ "logits/rejected": -2.503952980041504,
947
+ "logps/chosen": -1.0764460563659668,
948
+ "logps/rejected": -1.5906479358673096,
949
+ "loss": 1.8359,
950
+ "rewards/accuracies": 0.6499999761581421,
951
+ "rewards/chosen": -1.0764460563659668,
952
+ "rewards/margins": 0.514201819896698,
953
+ "rewards/rejected": -1.5906479358673096,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6699816801884323,
958
+ "grad_norm": 29.685480077784828,
959
+ "learning_rate": 1.478143389201113e-07,
960
+ "logits/chosen": -2.592771291732788,
961
+ "logits/rejected": -2.5038256645202637,
962
+ "logps/chosen": -1.034784197807312,
963
+ "logps/rejected": -1.6445497274398804,
964
+ "loss": 1.7974,
965
+ "rewards/accuracies": 0.6312500238418579,
966
+ "rewards/chosen": -1.034784197807312,
967
+ "rewards/margins": 0.6097655892372131,
968
+ "rewards/rejected": -1.6445497274398804,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.6804501439413766,
973
+ "grad_norm": 45.93159466769048,
974
+ "learning_rate": 1.3953046172178413e-07,
975
+ "logits/chosen": -2.5624806880950928,
976
+ "logits/rejected": -2.4602789878845215,
977
+ "logps/chosen": -1.1025031805038452,
978
+ "logps/rejected": -1.7038898468017578,
979
+ "loss": 1.8729,
980
+ "rewards/accuracies": 0.6875,
981
+ "rewards/chosen": -1.1025031805038452,
982
+ "rewards/margins": 0.6013867855072021,
983
+ "rewards/rejected": -1.7038898468017578,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.6909186076943209,
988
+ "grad_norm": 31.678205608236812,
989
+ "learning_rate": 1.3139467229135998e-07,
990
+ "logits/chosen": -2.599463939666748,
991
+ "logits/rejected": -2.5258090496063232,
992
+ "logps/chosen": -0.9680983424186707,
993
+ "logps/rejected": -1.6296237707138062,
994
+ "loss": 1.8012,
995
+ "rewards/accuracies": 0.706250011920929,
996
+ "rewards/chosen": -0.9680983424186707,
997
+ "rewards/margins": 0.6615251302719116,
998
+ "rewards/rejected": -1.6296237707138062,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7013870714472651,
1003
+ "grad_norm": 37.038121368656675,
1004
+ "learning_rate": 1.2341787690142435e-07,
1005
+ "logits/chosen": -2.5534796714782715,
1006
+ "logits/rejected": -2.517007827758789,
1007
+ "logps/chosen": -1.1220486164093018,
1008
+ "logps/rejected": -1.6694402694702148,
1009
+ "loss": 1.8584,
1010
+ "rewards/accuracies": 0.737500011920929,
1011
+ "rewards/chosen": -1.1220486164093018,
1012
+ "rewards/margins": 0.5473915338516235,
1013
+ "rewards/rejected": -1.6694402694702148,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7118555352002094,
1018
+ "grad_norm": 32.99732563960218,
1019
+ "learning_rate": 1.1561076868822755e-07,
1020
+ "logits/chosen": -2.58585524559021,
1021
+ "logits/rejected": -2.4757778644561768,
1022
+ "logps/chosen": -1.0188167095184326,
1023
+ "logps/rejected": -1.71088445186615,
1024
+ "loss": 1.8167,
1025
+ "rewards/accuracies": 0.6875,
1026
+ "rewards/chosen": -1.0188167095184326,
1027
+ "rewards/margins": 0.6920677423477173,
1028
+ "rewards/rejected": -1.71088445186615,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.7223239989531536,
1033
+ "grad_norm": 31.150959005223893,
1034
+ "learning_rate": 1.0798381331721107e-07,
1035
+ "logits/chosen": -2.595191478729248,
1036
+ "logits/rejected": -2.491788387298584,
1037
+ "logps/chosen": -1.0228018760681152,
1038
+ "logps/rejected": -1.5643987655639648,
1039
+ "loss": 1.8471,
1040
+ "rewards/accuracies": 0.731249988079071,
1041
+ "rewards/chosen": -1.0228018760681152,
1042
+ "rewards/margins": 0.5415968298912048,
1043
+ "rewards/rejected": -1.5643987655639648,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7327924627060979,
1048
+ "grad_norm": 32.974367073048874,
1049
+ "learning_rate": 1.0054723495346482e-07,
1050
+ "logits/chosen": -2.4937729835510254,
1051
+ "logits/rejected": -2.3299617767333984,
1052
+ "logps/chosen": -1.100921630859375,
1053
+ "logps/rejected": -1.6467349529266357,
1054
+ "loss": 1.8361,
1055
+ "rewards/accuracies": 0.6312500238418579,
1056
+ "rewards/chosen": -1.100921630859375,
1057
+ "rewards/margins": 0.5458132028579712,
1058
+ "rewards/rejected": -1.6467349529266357,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7432609264590422,
1063
+ "grad_norm": 28.926067639567258,
1064
+ "learning_rate": 9.331100255592436e-08,
1065
+ "logits/chosen": -2.4389522075653076,
1066
+ "logits/rejected": -2.374527931213379,
1067
+ "logps/chosen": -1.0656179189682007,
1068
+ "logps/rejected": -1.67294442653656,
1069
+ "loss": 1.8606,
1070
+ "rewards/accuracies": 0.675000011920929,
1071
+ "rewards/chosen": -1.0656179189682007,
1072
+ "rewards/margins": 0.6073265075683594,
1073
+ "rewards/rejected": -1.67294442653656,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7537293902119864,
1078
+ "grad_norm": 41.902021950847704,
1079
+ "learning_rate": 8.628481651367875e-08,
1080
+ "logits/chosen": -2.497872829437256,
1081
+ "logits/rejected": -2.4256420135498047,
1082
+ "logps/chosen": -1.0714236497879028,
1083
+ "logps/rejected": -1.6986573934555054,
1084
+ "loss": 1.8331,
1085
+ "rewards/accuracies": 0.7124999761581421,
1086
+ "rewards/chosen": -1.0714236497879028,
1087
+ "rewards/margins": 0.6272337436676025,
1088
+ "rewards/rejected": -1.6986573934555054,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.7641978539649307,
1093
+ "grad_norm": 31.435500480488756,
1094
+ "learning_rate": 7.947809564230445e-08,
1095
+ "logits/chosen": -2.532473087310791,
1096
+ "logits/rejected": -2.366628646850586,
1097
+ "logps/chosen": -1.0359852313995361,
1098
+ "logps/rejected": -1.7668260335922241,
1099
+ "loss": 1.7899,
1100
+ "rewards/accuracies": 0.6812499761581421,
1101
+ "rewards/chosen": -1.0359852313995361,
1102
+ "rewards/margins": 0.730840802192688,
1103
+ "rewards/rejected": -1.7668260335922241,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7746663177178749,
1108
+ "grad_norm": 39.54146493100524,
1109
+ "learning_rate": 7.289996455765748e-08,
1110
+ "logits/chosen": -2.484086513519287,
1111
+ "logits/rejected": -2.349870204925537,
1112
+ "logps/chosen": -1.0333083868026733,
1113
+ "logps/rejected": -1.6121408939361572,
1114
+ "loss": 1.7669,
1115
+ "rewards/accuracies": 0.7124999761581421,
1116
+ "rewards/chosen": -1.0333083868026733,
1117
+ "rewards/margins": 0.5788324475288391,
1118
+ "rewards/rejected": -1.6121408939361572,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.7851347814708192,
1123
+ "grad_norm": 44.26258075929706,
1124
+ "learning_rate": 6.655924144404906e-08,
1125
+ "logits/chosen": -2.413093328475952,
1126
+ "logits/rejected": -2.3522191047668457,
1127
+ "logps/chosen": -0.994648277759552,
1128
+ "logps/rejected": -1.8310960531234741,
1129
+ "loss": 1.8098,
1130
+ "rewards/accuracies": 0.706250011920929,
1131
+ "rewards/chosen": -0.994648277759552,
1132
+ "rewards/margins": 0.8364478945732117,
1133
+ "rewards/rejected": -1.8310960531234741,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.7956032452237635,
1138
+ "grad_norm": 42.81392142197046,
1139
+ "learning_rate": 6.046442623320145e-08,
1140
+ "logits/chosen": -2.5220797061920166,
1141
+ "logits/rejected": -2.5181660652160645,
1142
+ "logps/chosen": -1.0257781744003296,
1143
+ "logps/rejected": -1.565146803855896,
1144
+ "loss": 1.848,
1145
+ "rewards/accuracies": 0.668749988079071,
1146
+ "rewards/chosen": -1.0257781744003296,
1147
+ "rewards/margins": 0.5393685102462769,
1148
+ "rewards/rejected": -1.565146803855896,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.8060717089767077,
1153
+ "grad_norm": 29.963279293888323,
1154
+ "learning_rate": 5.4623689209832484e-08,
1155
+ "logits/chosen": -2.4084603786468506,
1156
+ "logits/rejected": -2.3918216228485107,
1157
+ "logps/chosen": -1.0294010639190674,
1158
+ "logps/rejected": -1.5665457248687744,
1159
+ "loss": 1.8117,
1160
+ "rewards/accuracies": 0.6499999761581421,
1161
+ "rewards/chosen": -1.0294010639190674,
1162
+ "rewards/margins": 0.537144660949707,
1163
+ "rewards/rejected": -1.5665457248687744,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.816540172729652,
1168
+ "grad_norm": 33.04796978561497,
1169
+ "learning_rate": 4.904486005914027e-08,
1170
+ "logits/chosen": -2.4773898124694824,
1171
+ "logits/rejected": -2.334437608718872,
1172
+ "logps/chosen": -1.0476093292236328,
1173
+ "logps/rejected": -1.5581729412078857,
1174
+ "loss": 1.8541,
1175
+ "rewards/accuracies": 0.612500011920929,
1176
+ "rewards/chosen": -1.0476093292236328,
1177
+ "rewards/margins": 0.5105637311935425,
1178
+ "rewards/rejected": -1.5581729412078857,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8270086364825961,
1183
+ "grad_norm": 36.23962004411558,
1184
+ "learning_rate": 4.373541737087263e-08,
1185
+ "logits/chosen": -2.4543843269348145,
1186
+ "logits/rejected": -2.3622539043426514,
1187
+ "logps/chosen": -1.0004545450210571,
1188
+ "logps/rejected": -1.7118451595306396,
1189
+ "loss": 1.822,
1190
+ "rewards/accuracies": 0.6875,
1191
+ "rewards/chosen": -1.0004545450210571,
1192
+ "rewards/margins": 0.7113906145095825,
1193
+ "rewards/rejected": -1.7118451595306396,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8374771002355405,
1198
+ "grad_norm": 35.25243486313715,
1199
+ "learning_rate": 3.8702478614051345e-08,
1200
+ "logits/chosen": -2.4065768718719482,
1201
+ "logits/rejected": -2.2744433879852295,
1202
+ "logps/chosen": -1.054172396659851,
1203
+ "logps/rejected": -1.5296390056610107,
1204
+ "loss": 1.8213,
1205
+ "rewards/accuracies": 0.643750011920929,
1206
+ "rewards/chosen": -1.054172396659851,
1207
+ "rewards/margins": 0.4754667282104492,
1208
+ "rewards/rejected": -1.5296390056610107,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8479455639884846,
1213
+ "grad_norm": 37.565064056547584,
1214
+ "learning_rate": 3.3952790595787986e-08,
1215
+ "logits/chosen": -2.449446439743042,
1216
+ "logits/rejected": -2.3016552925109863,
1217
+ "logps/chosen": -1.0504591464996338,
1218
+ "logps/rejected": -1.7570114135742188,
1219
+ "loss": 1.8237,
1220
+ "rewards/accuracies": 0.675000011920929,
1221
+ "rewards/chosen": -1.0504591464996338,
1222
+ "rewards/margins": 0.7065523266792297,
1223
+ "rewards/rejected": -1.7570114135742188,
1224
+ "step": 405
1225
+ },
1226
+ {
1227
+ "epoch": 0.8584140277414289,
1228
+ "grad_norm": 32.90354747950104,
1229
+ "learning_rate": 2.9492720416985e-08,
1230
+ "logits/chosen": -2.3721275329589844,
1231
+ "logits/rejected": -2.268225908279419,
1232
+ "logps/chosen": -1.1106208562850952,
1233
+ "logps/rejected": -1.9150855541229248,
1234
+ "loss": 1.8043,
1235
+ "rewards/accuracies": 0.668749988079071,
1236
+ "rewards/chosen": -1.1106208562850952,
1237
+ "rewards/margins": 0.8044648170471191,
1238
+ "rewards/rejected": -1.9150855541229248,
1239
+ "step": 410
1240
+ },
1241
+ {
1242
+ "epoch": 0.8688824914943732,
1243
+ "grad_norm": 56.846827175134244,
1244
+ "learning_rate": 2.5328246937043525e-08,
1245
+ "logits/chosen": -2.4376819133758545,
1246
+ "logits/rejected": -2.3333914279937744,
1247
+ "logps/chosen": -1.1099225282669067,
1248
+ "logps/rejected": -1.6782783269882202,
1249
+ "loss": 1.8252,
1250
+ "rewards/accuracies": 0.612500011920929,
1251
+ "rewards/chosen": -1.1099225282669067,
1252
+ "rewards/margins": 0.568355917930603,
1253
+ "rewards/rejected": -1.6782783269882202,
1254
+ "step": 415
1255
+ },
1256
+ {
1257
+ "epoch": 0.8793509552473174,
1258
+ "grad_norm": 43.77757640842041,
1259
+ "learning_rate": 2.1464952759020856e-08,
1260
+ "logits/chosen": -2.4453635215759277,
1261
+ "logits/rejected": -2.2761971950531006,
1262
+ "logps/chosen": -1.050205111503601,
1263
+ "logps/rejected": -1.8707281351089478,
1264
+ "loss": 1.7931,
1265
+ "rewards/accuracies": 0.699999988079071,
1266
+ "rewards/chosen": -1.050205111503601,
1267
+ "rewards/margins": 0.8205229640007019,
1268
+ "rewards/rejected": -1.8707281351089478,
1269
+ "step": 420
1270
+ },
1271
+ {
1272
+ "epoch": 0.8898194190002617,
1273
+ "grad_norm": 37.41494353520166,
1274
+ "learning_rate": 1.7908016745981856e-08,
1275
+ "logits/chosen": -2.448782444000244,
1276
+ "logits/rejected": -2.2901499271392822,
1277
+ "logps/chosen": -1.043718695640564,
1278
+ "logps/rejected": -1.739383339881897,
1279
+ "loss": 1.8267,
1280
+ "rewards/accuracies": 0.6875,
1281
+ "rewards/chosen": -1.043718695640564,
1282
+ "rewards/margins": 0.695664644241333,
1283
+ "rewards/rejected": -1.739383339881897,
1284
+ "step": 425
1285
+ },
1286
+ {
1287
+ "epoch": 0.9002878827532059,
1288
+ "grad_norm": 30.693244043593708,
1289
+ "learning_rate": 1.4662207078575684e-08,
1290
+ "logits/chosen": -2.4449446201324463,
1291
+ "logits/rejected": -2.294093608856201,
1292
+ "logps/chosen": -1.0893933773040771,
1293
+ "logps/rejected": -1.642295241355896,
1294
+ "loss": 1.7605,
1295
+ "rewards/accuracies": 0.6937500238418579,
1296
+ "rewards/chosen": -1.0893933773040771,
1297
+ "rewards/margins": 0.5529020428657532,
1298
+ "rewards/rejected": -1.642295241355896,
1299
+ "step": 430
1300
+ },
1301
+ {
1302
+ "epoch": 0.9107563465061502,
1303
+ "grad_norm": 33.12531830225382,
1304
+ "learning_rate": 1.1731874863145142e-08,
1305
+ "logits/chosen": -2.3656153678894043,
1306
+ "logits/rejected": -2.352541208267212,
1307
+ "logps/chosen": -0.9648414850234985,
1308
+ "logps/rejected": -1.5097295045852661,
1309
+ "loss": 1.7984,
1310
+ "rewards/accuracies": 0.65625,
1311
+ "rewards/chosen": -0.9648414850234985,
1312
+ "rewards/margins": 0.5448881983757019,
1313
+ "rewards/rejected": -1.5097295045852661,
1314
+ "step": 435
1315
+ },
1316
+ {
1317
+ "epoch": 0.9212248102590945,
1318
+ "grad_norm": 40.86500194765816,
1319
+ "learning_rate": 9.12094829893642e-09,
1320
+ "logits/chosen": -2.48162579536438,
1321
+ "logits/rejected": -2.3563125133514404,
1322
+ "logps/chosen": -1.0542184114456177,
1323
+ "logps/rejected": -1.5571963787078857,
1324
+ "loss": 1.8252,
1325
+ "rewards/accuracies": 0.6499999761581421,
1326
+ "rewards/chosen": -1.0542184114456177,
1327
+ "rewards/margins": 0.5029779672622681,
1328
+ "rewards/rejected": -1.5571963787078857,
1329
+ "step": 440
1330
+ },
1331
+ {
1332
+ "epoch": 0.9316932740120387,
1333
+ "grad_norm": 30.792748106701044,
1334
+ "learning_rate": 6.832927412229017e-09,
1335
+ "logits/chosen": -2.399744987487793,
1336
+ "logits/rejected": -2.232243061065674,
1337
+ "logps/chosen": -1.0769870281219482,
1338
+ "logps/rejected": -1.728468656539917,
1339
+ "loss": 1.7915,
1340
+ "rewards/accuracies": 0.675000011920929,
1341
+ "rewards/chosen": -1.0769870281219482,
1342
+ "rewards/margins": 0.6514816284179688,
1343
+ "rewards/rejected": -1.728468656539917,
1344
+ "step": 445
1345
+ },
1346
+ {
1347
+ "epoch": 0.942161737764983,
1348
+ "grad_norm": 29.999766652539517,
1349
+ "learning_rate": 4.8708793644441086e-09,
1350
+ "logits/chosen": -2.459473133087158,
1351
+ "logits/rejected": -2.2956230640411377,
1352
+ "logps/chosen": -1.0055310726165771,
1353
+ "logps/rejected": -1.5959385633468628,
1354
+ "loss": 1.8126,
1355
+ "rewards/accuracies": 0.668749988079071,
1356
+ "rewards/chosen": -1.0055310726165771,
1357
+ "rewards/margins": 0.5904075503349304,
1358
+ "rewards/rejected": -1.5959385633468628,
1359
+ "step": 450
1360
+ },
1361
+ {
1362
+ "epoch": 0.9526302015179272,
1363
+ "grad_norm": 36.992525127734154,
1364
+ "learning_rate": 3.2374343405217884e-09,
1365
+ "logits/chosen": -2.42592191696167,
1366
+ "logits/rejected": -2.3259921073913574,
1367
+ "logps/chosen": -1.0747435092926025,
1368
+ "logps/rejected": -1.6361202001571655,
1369
+ "loss": 1.8922,
1370
+ "rewards/accuracies": 0.6812499761581421,
1371
+ "rewards/chosen": -1.0747435092926025,
1372
+ "rewards/margins": 0.5613764524459839,
1373
+ "rewards/rejected": -1.6361202001571655,
1374
+ "step": 455
1375
+ },
1376
+ {
1377
+ "epoch": 0.9630986652708715,
1378
+ "grad_norm": 43.04775872660601,
1379
+ "learning_rate": 1.9347820230782295e-09,
1380
+ "logits/chosen": -2.488020896911621,
1381
+ "logits/rejected": -2.239854097366333,
1382
+ "logps/chosen": -0.9606490135192871,
1383
+ "logps/rejected": -1.82891845703125,
1384
+ "loss": 1.8115,
1385
+ "rewards/accuracies": 0.7749999761581421,
1386
+ "rewards/chosen": -0.9606490135192871,
1387
+ "rewards/margins": 0.8682695627212524,
1388
+ "rewards/rejected": -1.82891845703125,
1389
+ "step": 460
1390
+ },
1391
+ {
1392
+ "epoch": 0.9735671290238157,
1393
+ "grad_norm": 25.076712480507634,
1394
+ "learning_rate": 9.64668657069706e-10,
1395
+ "logits/chosen": -2.4506993293762207,
1396
+ "logits/rejected": -2.252009868621826,
1397
+ "logps/chosen": -1.0200697183609009,
1398
+ "logps/rejected": -1.8124902248382568,
1399
+ "loss": 1.8012,
1400
+ "rewards/accuracies": 0.7250000238418579,
1401
+ "rewards/chosen": -1.0200697183609009,
1402
+ "rewards/margins": 0.7924206852912903,
1403
+ "rewards/rejected": -1.8124902248382568,
1404
+ "step": 465
1405
+ },
1406
+ {
1407
+ "epoch": 0.98403559277676,
1408
+ "grad_norm": 26.74704043050654,
1409
+ "learning_rate": 3.2839470889836627e-10,
1410
+ "logits/chosen": -2.3772401809692383,
1411
+ "logits/rejected": -2.2120604515075684,
1412
+ "logps/chosen": -0.9293681979179382,
1413
+ "logps/rejected": -1.7934061288833618,
1414
+ "loss": 1.7671,
1415
+ "rewards/accuracies": 0.6875,
1416
+ "rewards/chosen": -0.9293681979179382,
1417
+ "rewards/margins": 0.8640381097793579,
1418
+ "rewards/rejected": -1.7934061288833618,
1419
+ "step": 470
1420
+ },
1421
+ {
1422
+ "epoch": 0.9945040565297043,
1423
+ "grad_norm": 50.411989213964986,
1424
+ "learning_rate": 2.6813123097352287e-11,
1425
+ "logits/chosen": -2.4256701469421387,
1426
+ "logits/rejected": -2.3270206451416016,
1427
+ "logps/chosen": -0.9691774249076843,
1428
+ "logps/rejected": -1.615407943725586,
1429
+ "loss": 1.797,
1430
+ "rewards/accuracies": 0.637499988079071,
1431
+ "rewards/chosen": -0.9691774249076843,
1432
+ "rewards/margins": 0.6462305784225464,
1433
+ "rewards/rejected": -1.615407943725586,
1434
+ "step": 475
1435
+ },
1436
+ {
1437
+ "epoch": 0.998691442030882,
1438
+ "step": 477,
1439
+ "total_flos": 0.0,
1440
+ "train_loss": 1.8663299063716545,
1441
+ "train_runtime": 8277.1533,
1442
+ "train_samples_per_second": 7.386,
1443
+ "train_steps_per_second": 0.058
1444
+ }
1445
+ ],
1446
+ "logging_steps": 5,
1447
+ "max_steps": 477,
1448
+ "num_input_tokens_seen": 0,
1449
+ "num_train_epochs": 1,
1450
+ "save_steps": 10000,
1451
+ "stateful_callbacks": {
1452
+ "TrainerControl": {
1453
+ "args": {
1454
+ "should_epoch_stop": false,
1455
+ "should_evaluate": false,
1456
+ "should_log": false,
1457
+ "should_save": true,
1458
+ "should_training_stop": true
1459
+ },
1460
+ "attributes": {}
1461
+ }
1462
+ },
1463
+ "total_flos": 0.0,
1464
+ "train_batch_size": 2,
1465
+ "trial_name": null,
1466
+ "trial_params": null
1467
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369ba55aaf5013e98b2324de98544a6b70f8f3bd54b0c180935afb66acea981c
3
+ size 7416