TTTXXX01 commited on
Commit
1a5e43c
1 Parent(s): 2057274

Model save

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: alignment-handbook/zephyr-7b-sft-full
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Positive_like_DPO_Chat-zephyr-7b-sft-full
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Positive_like_DPO_Chat-zephyr-7b-sft-full
17
+
18
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-07
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 4
43
+ - gradient_accumulation_steps: 8
44
+ - total_train_batch_size: 128
45
+ - total_eval_batch_size: 16
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 1
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.41.2
58
+ - Pytorch 2.3.0+cu121
59
+ - Datasets 2.19.1
60
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.998691442030882,
3
+ "total_flos": 0.0,
4
+ "train_loss": 244.87338864628373,
5
+ "train_runtime": 12795.3282,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 4.778,
8
+ "train_steps_per_second": 0.037
9
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.41.2",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.41.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6d0b46939441c91d0eb967e404759e346cf61c45a684972f08a92926dc610a
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602ad54b55433436a3bdd772a46c9626bff47503675a67c1c0fb058c81be3525
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6b8bb2952a88ef1d915f406f38779d26089fe7ea07c670b5be444bcc4444cf
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": 244.87338864628373,
5
+ "train_runtime": 12795.3282,
6
+ "train_samples": 61135,
7
+ "train_samples_per_second": 4.778,
8
+ "train_steps_per_second": 0.037
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,762 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.002093692750588851,
13
+ "grad_norm": 3535.8126325665735,
14
+ "learning_rate": 1.0416666666666666e-08,
15
+ "logits/chosen": 5002.53564453125,
16
+ "logits/rejected": 4591.72021484375,
17
+ "logps/chosen": -265.6396789550781,
18
+ "logps/rejected": -206.22401428222656,
19
+ "loss": 280.8964,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.02093692750588851,
28
+ "grad_norm": 3583.3887780950436,
29
+ "learning_rate": 1.0416666666666667e-07,
30
+ "logits/chosen": 5976.96337890625,
31
+ "logits/rejected": 5015.21337890625,
32
+ "logps/chosen": -292.321044921875,
33
+ "logps/rejected": -259.08831787109375,
34
+ "loss": 287.6974,
35
+ "rewards/accuracies": 0.4548611044883728,
36
+ "rewards/chosen": 0.00239731022156775,
37
+ "rewards/margins": 4.432235436979681e-05,
38
+ "rewards/rejected": 0.0023529878817498684,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04187385501177702,
43
+ "grad_norm": 1937.0995896878487,
44
+ "learning_rate": 2.0833333333333333e-07,
45
+ "logits/chosen": 5865.89453125,
46
+ "logits/rejected": 4845.67138671875,
47
+ "logps/chosen": -283.9303283691406,
48
+ "logps/rejected": -243.36111450195312,
49
+ "loss": 276.4462,
50
+ "rewards/accuracies": 0.534375011920929,
51
+ "rewards/chosen": 0.06663157045841217,
52
+ "rewards/margins": 0.0029086393769830465,
53
+ "rewards/rejected": 0.06372293084859848,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.06281078251766553,
58
+ "grad_norm": 1357.5939676600453,
59
+ "learning_rate": 3.1249999999999997e-07,
60
+ "logits/chosen": 5566.55859375,
61
+ "logits/rejected": 4849.14208984375,
62
+ "logps/chosen": -256.52099609375,
63
+ "logps/rejected": -223.9065399169922,
64
+ "loss": 259.9777,
65
+ "rewards/accuracies": 0.581250011920929,
66
+ "rewards/chosen": 0.15716445446014404,
67
+ "rewards/margins": 0.008207684382796288,
68
+ "rewards/rejected": 0.1489567756652832,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.08374771002355404,
73
+ "grad_norm": 1133.6293010511845,
74
+ "learning_rate": 4.1666666666666667e-07,
75
+ "logits/chosen": 5576.7578125,
76
+ "logits/rejected": 4843.4580078125,
77
+ "logps/chosen": -252.6702423095703,
78
+ "logps/rejected": -238.50485229492188,
79
+ "loss": 262.5837,
80
+ "rewards/accuracies": 0.546875,
81
+ "rewards/chosen": 0.21286813914775848,
82
+ "rewards/margins": 0.013377232477068901,
83
+ "rewards/rejected": 0.19949090480804443,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.10468463752944256,
88
+ "grad_norm": 1156.1788135816998,
89
+ "learning_rate": 4.999731868769026e-07,
90
+ "logits/chosen": 5815.3984375,
91
+ "logits/rejected": 5046.6923828125,
92
+ "logps/chosen": -254.2016143798828,
93
+ "logps/rejected": -244.6356658935547,
94
+ "loss": 256.2513,
95
+ "rewards/accuracies": 0.550000011920929,
96
+ "rewards/chosen": 0.24416108429431915,
97
+ "rewards/margins": 0.015325096435844898,
98
+ "rewards/rejected": 0.22883598506450653,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.12562156503533106,
103
+ "grad_norm": 1067.5976503019779,
104
+ "learning_rate": 4.990353313429303e-07,
105
+ "logits/chosen": 5575.5048828125,
106
+ "logits/rejected": 4749.95703125,
107
+ "logps/chosen": -249.46359252929688,
108
+ "logps/rejected": -224.8580322265625,
109
+ "loss": 242.7049,
110
+ "rewards/accuracies": 0.5406249761581421,
111
+ "rewards/chosen": 0.2895886301994324,
112
+ "rewards/margins": 0.023379303514957428,
113
+ "rewards/rejected": 0.26620933413505554,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.14655849254121958,
118
+ "grad_norm": 1053.4897470709532,
119
+ "learning_rate": 4.967625656594781e-07,
120
+ "logits/chosen": 5370.1044921875,
121
+ "logits/rejected": 4955.6025390625,
122
+ "logps/chosen": -248.7747039794922,
123
+ "logps/rejected": -239.68154907226562,
124
+ "loss": 242.2774,
125
+ "rewards/accuracies": 0.565625011920929,
126
+ "rewards/chosen": 0.29533231258392334,
127
+ "rewards/margins": 0.02411496639251709,
128
+ "rewards/rejected": 0.27121734619140625,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.16749542004710807,
133
+ "grad_norm": 1023.2390689553637,
134
+ "learning_rate": 4.93167072587771e-07,
135
+ "logits/chosen": 5459.8798828125,
136
+ "logits/rejected": 4685.32275390625,
137
+ "logps/chosen": -244.05105590820312,
138
+ "logps/rejected": -224.86630249023438,
139
+ "loss": 242.3456,
140
+ "rewards/accuracies": 0.6031249761581421,
141
+ "rewards/chosen": 0.32035860419273376,
142
+ "rewards/margins": 0.03829706832766533,
143
+ "rewards/rejected": 0.28206151723861694,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.1884323475529966,
148
+ "grad_norm": 1040.9032310821044,
149
+ "learning_rate": 4.882681251368548e-07,
150
+ "logits/chosen": 5580.447265625,
151
+ "logits/rejected": 4722.6728515625,
152
+ "logps/chosen": -243.3023223876953,
153
+ "logps/rejected": -223.93185424804688,
154
+ "loss": 242.2394,
155
+ "rewards/accuracies": 0.590624988079071,
156
+ "rewards/chosen": 0.3440525531768799,
157
+ "rewards/margins": 0.0336349718272686,
158
+ "rewards/rejected": 0.3104175925254822,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.2093692750588851,
163
+ "grad_norm": 1122.126586948237,
164
+ "learning_rate": 4.820919832540181e-07,
165
+ "logits/chosen": 5649.5400390625,
166
+ "logits/rejected": 5218.107421875,
167
+ "logps/chosen": -244.94400024414062,
168
+ "logps/rejected": -239.73779296875,
169
+ "loss": 242.0253,
170
+ "rewards/accuracies": 0.503125011920929,
171
+ "rewards/chosen": 0.34924736618995667,
172
+ "rewards/margins": 0.0014709115494042635,
173
+ "rewards/rejected": 0.34777647256851196,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.23030620256477363,
178
+ "grad_norm": 997.7885835864053,
179
+ "learning_rate": 4.7467175306295647e-07,
180
+ "logits/chosen": 5795.6767578125,
181
+ "logits/rejected": 4699.9208984375,
182
+ "logps/chosen": -237.4701690673828,
183
+ "logps/rejected": -226.93594360351562,
184
+ "loss": 240.8889,
185
+ "rewards/accuracies": 0.5874999761581421,
186
+ "rewards/chosen": 0.37152451276779175,
187
+ "rewards/margins": 0.05216788500547409,
188
+ "rewards/rejected": 0.31935662031173706,
189
+ "step": 110
190
+ },
191
+ {
192
+ "epoch": 0.2512431300706621,
193
+ "grad_norm": 1067.2738806193756,
194
+ "learning_rate": 4.6604720940421207e-07,
195
+ "logits/chosen": 5398.6474609375,
196
+ "logits/rejected": 5022.0517578125,
197
+ "logps/chosen": -232.2193603515625,
198
+ "logps/rejected": -233.2302703857422,
199
+ "loss": 245.0688,
200
+ "rewards/accuracies": 0.550000011920929,
201
+ "rewards/chosen": 0.3495965003967285,
202
+ "rewards/margins": 0.013141113333404064,
203
+ "rewards/rejected": 0.3364553451538086,
204
+ "step": 120
205
+ },
206
+ {
207
+ "epoch": 0.2721800575765506,
208
+ "grad_norm": 1101.9933538265811,
209
+ "learning_rate": 4.5626458262912735e-07,
210
+ "logits/chosen": 5447.984375,
211
+ "logits/rejected": 4856.47216796875,
212
+ "logps/chosen": -234.07583618164062,
213
+ "logps/rejected": -235.1103973388672,
214
+ "loss": 245.9864,
215
+ "rewards/accuracies": 0.5531250238418579,
216
+ "rewards/chosen": 0.3444148600101471,
217
+ "rewards/margins": 0.005432566162198782,
218
+ "rewards/rejected": 0.3389822840690613,
219
+ "step": 130
220
+ },
221
+ {
222
+ "epoch": 0.29311698508243916,
223
+ "grad_norm": 1062.9847754936125,
224
+ "learning_rate": 4.453763107901675e-07,
225
+ "logits/chosen": 5238.33349609375,
226
+ "logits/rejected": 4664.427734375,
227
+ "logps/chosen": -236.94302368164062,
228
+ "logps/rejected": -218.821044921875,
229
+ "loss": 247.7552,
230
+ "rewards/accuracies": 0.5625,
231
+ "rewards/chosen": 0.3496176600456238,
232
+ "rewards/margins": 0.026499617844820023,
233
+ "rewards/rejected": 0.32311806082725525,
234
+ "step": 140
235
+ },
236
+ {
237
+ "epoch": 0.31405391258832765,
238
+ "grad_norm": 1368.1757226951288,
239
+ "learning_rate": 4.3344075855595097e-07,
240
+ "logits/chosen": 5794.70458984375,
241
+ "logits/rejected": 4785.361328125,
242
+ "logps/chosen": -253.90975952148438,
243
+ "logps/rejected": -218.62548828125,
244
+ "loss": 241.2088,
245
+ "rewards/accuracies": 0.578125,
246
+ "rewards/chosen": 0.35205191373825073,
247
+ "rewards/margins": 0.023399515077471733,
248
+ "rewards/rejected": 0.32865244150161743,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 0.33499084009421615,
253
+ "grad_norm": 1052.0276681831142,
254
+ "learning_rate": 4.2052190435769554e-07,
255
+ "logits/chosen": 5505.08154296875,
256
+ "logits/rejected": 4592.50927734375,
257
+ "logps/chosen": -242.8617706298828,
258
+ "logps/rejected": -221.708251953125,
259
+ "loss": 243.5824,
260
+ "rewards/accuracies": 0.5562499761581421,
261
+ "rewards/chosen": 0.4173237681388855,
262
+ "rewards/margins": 0.07062368839979172,
263
+ "rewards/rejected": 0.34670013189315796,
264
+ "step": 160
265
+ },
266
+ {
267
+ "epoch": 0.3559277676001047,
268
+ "grad_norm": 1072.8144440956282,
269
+ "learning_rate": 4.0668899744407567e-07,
270
+ "logits/chosen": 5766.25244140625,
271
+ "logits/rejected": 4925.43017578125,
272
+ "logps/chosen": -249.1059112548828,
273
+ "logps/rejected": -209.27963256835938,
274
+ "loss": 248.3713,
275
+ "rewards/accuracies": 0.550000011920929,
276
+ "rewards/chosen": 0.3320981562137604,
277
+ "rewards/margins": 0.01844380795955658,
278
+ "rewards/rejected": 0.3136543333530426,
279
+ "step": 170
280
+ },
281
+ {
282
+ "epoch": 0.3768646951059932,
283
+ "grad_norm": 983.0618691372457,
284
+ "learning_rate": 3.920161866827889e-07,
285
+ "logits/chosen": 5427.0126953125,
286
+ "logits/rejected": 4671.05224609375,
287
+ "logps/chosen": -251.17276000976562,
288
+ "logps/rejected": -214.9893035888672,
289
+ "loss": 245.643,
290
+ "rewards/accuracies": 0.565625011920929,
291
+ "rewards/chosen": 0.3612250089645386,
292
+ "rewards/margins": 0.011310195550322533,
293
+ "rewards/rejected": 0.3499148190021515,
294
+ "step": 180
295
+ },
296
+ {
297
+ "epoch": 0.39780162261188173,
298
+ "grad_norm": 1005.4792953444737,
299
+ "learning_rate": 3.765821230985757e-07,
300
+ "logits/chosen": 5555.00634765625,
301
+ "logits/rejected": 4690.0107421875,
302
+ "logps/chosen": -232.8914337158203,
303
+ "logps/rejected": -213.5168914794922,
304
+ "loss": 244.4388,
305
+ "rewards/accuracies": 0.5375000238418579,
306
+ "rewards/chosen": 0.3686008155345917,
307
+ "rewards/margins": 0.024937449023127556,
308
+ "rewards/rejected": 0.34366339445114136,
309
+ "step": 190
310
+ },
311
+ {
312
+ "epoch": 0.4187385501177702,
313
+ "grad_norm": 1095.9872681623817,
314
+ "learning_rate": 3.604695382782159e-07,
315
+ "logits/chosen": 5196.1396484375,
316
+ "logits/rejected": 4525.6201171875,
317
+ "logps/chosen": -218.52597045898438,
318
+ "logps/rejected": -209.1753692626953,
319
+ "loss": 242.2741,
320
+ "rewards/accuracies": 0.559374988079071,
321
+ "rewards/chosen": 0.3582485318183899,
322
+ "rewards/margins": 0.02139531448483467,
323
+ "rewards/rejected": 0.33685317635536194,
324
+ "step": 200
325
+ },
326
+ {
327
+ "epoch": 0.4396754776236587,
328
+ "grad_norm": 1032.5136886828875,
329
+ "learning_rate": 3.4376480090239047e-07,
330
+ "logits/chosen": 5817.4052734375,
331
+ "logits/rejected": 4964.2431640625,
332
+ "logps/chosen": -250.0350341796875,
333
+ "logps/rejected": -227.2427978515625,
334
+ "loss": 242.9751,
335
+ "rewards/accuracies": 0.5406249761581421,
336
+ "rewards/chosen": 0.3673235774040222,
337
+ "rewards/margins": 0.022716034203767776,
338
+ "rewards/rejected": 0.34460753202438354,
339
+ "step": 210
340
+ },
341
+ {
342
+ "epoch": 0.46061240512954726,
343
+ "grad_norm": 1069.3112273505162,
344
+ "learning_rate": 3.265574537815398e-07,
345
+ "logits/chosen": 5231.8330078125,
346
+ "logits/rejected": 4868.0009765625,
347
+ "logps/chosen": -235.4297332763672,
348
+ "logps/rejected": -224.67996215820312,
349
+ "loss": 247.8473,
350
+ "rewards/accuracies": 0.5562499761581421,
351
+ "rewards/chosen": 0.35685989260673523,
352
+ "rewards/margins": 0.00022467300004791468,
353
+ "rewards/rejected": 0.3566352427005768,
354
+ "step": 220
355
+ },
356
+ {
357
+ "epoch": 0.48154933263543576,
358
+ "grad_norm": 1038.3755229403357,
359
+ "learning_rate": 3.0893973387735683e-07,
360
+ "logits/chosen": 5424.3896484375,
361
+ "logits/rejected": 4603.22265625,
362
+ "logps/chosen": -229.6114959716797,
363
+ "logps/rejected": -212.58535766601562,
364
+ "loss": 235.744,
365
+ "rewards/accuracies": 0.612500011920929,
366
+ "rewards/chosen": 0.3865725100040436,
367
+ "rewards/margins": 0.05810902267694473,
368
+ "rewards/rejected": 0.32846349477767944,
369
+ "step": 230
370
+ },
371
+ {
372
+ "epoch": 0.5024862601413242,
373
+ "grad_norm": 1058.0373868868155,
374
+ "learning_rate": 2.910060778827554e-07,
375
+ "logits/chosen": 5579.22265625,
376
+ "logits/rejected": 4746.73291015625,
377
+ "logps/chosen": -228.1630401611328,
378
+ "logps/rejected": -214.03872680664062,
379
+ "loss": 246.103,
380
+ "rewards/accuracies": 0.5687500238418579,
381
+ "rewards/chosen": 0.3741385042667389,
382
+ "rewards/margins": 0.01671653240919113,
383
+ "rewards/rejected": 0.35742202401161194,
384
+ "step": 240
385
+ },
386
+ {
387
+ "epoch": 0.5234231876472127,
388
+ "grad_norm": 1066.8993672604806,
389
+ "learning_rate": 2.7285261601056697e-07,
390
+ "logits/chosen": 5711.28759765625,
391
+ "logits/rejected": 4824.6904296875,
392
+ "logps/chosen": -245.55361938476562,
393
+ "logps/rejected": -227.17333984375,
394
+ "loss": 243.4184,
395
+ "rewards/accuracies": 0.59375,
396
+ "rewards/chosen": 0.4039505124092102,
397
+ "rewards/margins": 0.054931532591581345,
398
+ "rewards/rejected": 0.34901896119117737,
399
+ "step": 250
400
+ },
401
+ {
402
+ "epoch": 0.5443601151531012,
403
+ "grad_norm": 983.2388962195462,
404
+ "learning_rate": 2.5457665670441937e-07,
405
+ "logits/chosen": 5527.0869140625,
406
+ "logits/rejected": 5007.7177734375,
407
+ "logps/chosen": -246.20358276367188,
408
+ "logps/rejected": -224.95919799804688,
409
+ "loss": 244.2827,
410
+ "rewards/accuracies": 0.546875,
411
+ "rewards/chosen": 0.3986549377441406,
412
+ "rewards/margins": 0.037424616515636444,
413
+ "rewards/rejected": 0.36123034358024597,
414
+ "step": 260
415
+ },
416
+ {
417
+ "epoch": 0.5652970426589898,
418
+ "grad_norm": 1105.5507497790131,
419
+ "learning_rate": 2.3627616503391812e-07,
420
+ "logits/chosen": 5603.63916015625,
421
+ "logits/rejected": 5142.90576171875,
422
+ "logps/chosen": -234.740478515625,
423
+ "logps/rejected": -224.26904296875,
424
+ "loss": 234.9617,
425
+ "rewards/accuracies": 0.581250011920929,
426
+ "rewards/chosen": 0.39873379468917847,
427
+ "rewards/margins": 0.03745921701192856,
428
+ "rewards/rejected": 0.3612746000289917,
429
+ "step": 270
430
+ },
431
+ {
432
+ "epoch": 0.5862339701648783,
433
+ "grad_norm": 1034.2532678101588,
434
+ "learning_rate": 2.1804923757009882e-07,
435
+ "logits/chosen": 5626.45556640625,
436
+ "logits/rejected": 4683.701171875,
437
+ "logps/chosen": -242.08908081054688,
438
+ "logps/rejected": -211.0960235595703,
439
+ "loss": 233.7415,
440
+ "rewards/accuracies": 0.596875011920929,
441
+ "rewards/chosen": 0.3863658607006073,
442
+ "rewards/margins": 0.02948523685336113,
443
+ "rewards/rejected": 0.35688066482543945,
444
+ "step": 280
445
+ },
446
+ {
447
+ "epoch": 0.6071708976707668,
448
+ "grad_norm": 1148.0848744279972,
449
+ "learning_rate": 1.9999357655598891e-07,
450
+ "logits/chosen": 5876.2919921875,
451
+ "logits/rejected": 5516.24072265625,
452
+ "logps/chosen": -250.70028686523438,
453
+ "logps/rejected": -249.01510620117188,
454
+ "loss": 245.2798,
455
+ "rewards/accuracies": 0.550000011920929,
456
+ "rewards/chosen": 0.40733808279037476,
457
+ "rewards/margins": -0.0817265659570694,
458
+ "rewards/rejected": 0.48906460404396057,
459
+ "step": 290
460
+ },
461
+ {
462
+ "epoch": 0.6281078251766553,
463
+ "grad_norm": 1067.1492136203478,
464
+ "learning_rate": 1.8220596619089573e-07,
465
+ "logits/chosen": 5382.34765625,
466
+ "logits/rejected": 5070.5087890625,
467
+ "logps/chosen": -234.3385467529297,
468
+ "logps/rejected": -230.91720581054688,
469
+ "loss": 239.1968,
470
+ "rewards/accuracies": 0.543749988079071,
471
+ "rewards/chosen": 0.37011438608169556,
472
+ "rewards/margins": -0.029902536422014236,
473
+ "rewards/rejected": 0.4000169336795807,
474
+ "step": 300
475
+ },
476
+ {
477
+ "epoch": 0.6490447526825438,
478
+ "grad_norm": 1038.567182284818,
479
+ "learning_rate": 1.647817538357072e-07,
480
+ "logits/chosen": 6013.2529296875,
481
+ "logits/rejected": 5287.40478515625,
482
+ "logps/chosen": -247.5303192138672,
483
+ "logps/rejected": -233.228759765625,
484
+ "loss": 237.5939,
485
+ "rewards/accuracies": 0.581250011920929,
486
+ "rewards/chosen": 0.43299251794815063,
487
+ "rewards/margins": 0.06971301883459091,
488
+ "rewards/rejected": 0.3632794916629791,
489
+ "step": 310
490
+ },
491
+ {
492
+ "epoch": 0.6699816801884323,
493
+ "grad_norm": 1204.0142191428097,
494
+ "learning_rate": 1.478143389201113e-07,
495
+ "logits/chosen": 5575.4404296875,
496
+ "logits/rejected": 4841.73974609375,
497
+ "logps/chosen": -233.0708465576172,
498
+ "logps/rejected": -221.49600219726562,
499
+ "loss": 242.2518,
500
+ "rewards/accuracies": 0.5531250238418579,
501
+ "rewards/chosen": 0.38792601227760315,
502
+ "rewards/margins": 0.004761689808219671,
503
+ "rewards/rejected": 0.38316434621810913,
504
+ "step": 320
505
+ },
506
+ {
507
+ "epoch": 0.6909186076943209,
508
+ "grad_norm": 1019.620900443292,
509
+ "learning_rate": 1.3139467229135998e-07,
510
+ "logits/chosen": 5387.96044921875,
511
+ "logits/rejected": 5011.3662109375,
512
+ "logps/chosen": -238.8975067138672,
513
+ "logps/rejected": -226.3376007080078,
514
+ "loss": 238.7415,
515
+ "rewards/accuracies": 0.5375000238418579,
516
+ "rewards/chosen": 0.3788672685623169,
517
+ "rewards/margins": -0.0010509025305509567,
518
+ "rewards/rejected": 0.3799181580543518,
519
+ "step": 330
520
+ },
521
+ {
522
+ "epoch": 0.7118555352002094,
523
+ "grad_norm": 997.6449734870048,
524
+ "learning_rate": 1.1561076868822755e-07,
525
+ "logits/chosen": 5218.39013671875,
526
+ "logits/rejected": 4540.35986328125,
527
+ "logps/chosen": -217.21044921875,
528
+ "logps/rejected": -205.6111297607422,
529
+ "loss": 231.9898,
530
+ "rewards/accuracies": 0.59375,
531
+ "rewards/chosen": 0.403564989566803,
532
+ "rewards/margins": 0.04764997214078903,
533
+ "rewards/rejected": 0.35591498017311096,
534
+ "step": 340
535
+ },
536
+ {
537
+ "epoch": 0.7327924627060979,
538
+ "grad_norm": 1066.0615606169838,
539
+ "learning_rate": 1.0054723495346482e-07,
540
+ "logits/chosen": 5892.0224609375,
541
+ "logits/rejected": 4797.64306640625,
542
+ "logps/chosen": -258.8974914550781,
543
+ "logps/rejected": -231.6051025390625,
544
+ "loss": 251.9084,
545
+ "rewards/accuracies": 0.565625011920929,
546
+ "rewards/chosen": 0.42017000913619995,
547
+ "rewards/margins": 0.05283670499920845,
548
+ "rewards/rejected": 0.367333322763443,
549
+ "step": 350
550
+ },
551
+ {
552
+ "epoch": 0.7537293902119864,
553
+ "grad_norm": 1000.4777940737159,
554
+ "learning_rate": 8.628481651367875e-08,
555
+ "logits/chosen": 5596.86962890625,
556
+ "logits/rejected": 4888.3076171875,
557
+ "logps/chosen": -236.48135375976562,
558
+ "logps/rejected": -220.30322265625,
559
+ "loss": 233.4907,
560
+ "rewards/accuracies": 0.5625,
561
+ "rewards/chosen": 0.4124221205711365,
562
+ "rewards/margins": 0.03293180465698242,
563
+ "rewards/rejected": 0.37949031591415405,
564
+ "step": 360
565
+ },
566
+ {
567
+ "epoch": 0.7746663177178749,
568
+ "grad_norm": 937.2926675342543,
569
+ "learning_rate": 7.289996455765748e-08,
570
+ "logits/chosen": 5473.3173828125,
571
+ "logits/rejected": 4680.34521484375,
572
+ "logps/chosen": -251.95211791992188,
573
+ "logps/rejected": -224.4751739501953,
574
+ "loss": 239.6144,
575
+ "rewards/accuracies": 0.609375,
576
+ "rewards/chosen": 0.3684094548225403,
577
+ "rewards/margins": 0.04351681098341942,
578
+ "rewards/rejected": 0.3248926103115082,
579
+ "step": 370
580
+ },
581
+ {
582
+ "epoch": 0.7956032452237635,
583
+ "grad_norm": 1050.3155040091867,
584
+ "learning_rate": 6.046442623320145e-08,
585
+ "logits/chosen": 5725.0947265625,
586
+ "logits/rejected": 5000.07470703125,
587
+ "logps/chosen": -246.28152465820312,
588
+ "logps/rejected": -213.35775756835938,
589
+ "loss": 252.1425,
590
+ "rewards/accuracies": 0.5562499761581421,
591
+ "rewards/chosen": 0.38419944047927856,
592
+ "rewards/margins": 0.00920055340975523,
593
+ "rewards/rejected": 0.37499889731407166,
594
+ "step": 380
595
+ },
596
+ {
597
+ "epoch": 0.816540172729652,
598
+ "grad_norm": 1053.9561839695411,
599
+ "learning_rate": 4.904486005914027e-08,
600
+ "logits/chosen": 5992.890625,
601
+ "logits/rejected": 5294.5634765625,
602
+ "logps/chosen": -247.9290313720703,
603
+ "logps/rejected": -235.806640625,
604
+ "loss": 238.8614,
605
+ "rewards/accuracies": 0.574999988079071,
606
+ "rewards/chosen": 0.438203901052475,
607
+ "rewards/margins": 0.048503682017326355,
608
+ "rewards/rejected": 0.3897002339363098,
609
+ "step": 390
610
+ },
611
+ {
612
+ "epoch": 0.8374771002355405,
613
+ "grad_norm": 938.4991044304853,
614
+ "learning_rate": 3.8702478614051345e-08,
615
+ "logits/chosen": 5561.79296875,
616
+ "logits/rejected": 4942.47314453125,
617
+ "logps/chosen": -247.83755493164062,
618
+ "logps/rejected": -216.7385711669922,
619
+ "loss": 244.8828,
620
+ "rewards/accuracies": 0.5562499761581421,
621
+ "rewards/chosen": 0.4306658208370209,
622
+ "rewards/margins": 0.03947380185127258,
623
+ "rewards/rejected": 0.3911920487880707,
624
+ "step": 400
625
+ },
626
+ {
627
+ "epoch": 0.8584140277414289,
628
+ "grad_norm": 991.4623358360578,
629
+ "learning_rate": 2.9492720416985e-08,
630
+ "logits/chosen": 5575.3115234375,
631
+ "logits/rejected": 4932.56201171875,
632
+ "logps/chosen": -235.03713989257812,
633
+ "logps/rejected": -220.0222625732422,
634
+ "loss": 239.7671,
635
+ "rewards/accuracies": 0.590624988079071,
636
+ "rewards/chosen": 0.4683019518852234,
637
+ "rewards/margins": -0.14257735013961792,
638
+ "rewards/rejected": 0.6108792424201965,
639
+ "step": 410
640
+ },
641
+ {
642
+ "epoch": 0.8793509552473174,
643
+ "grad_norm": 1039.9341468951118,
644
+ "learning_rate": 2.1464952759020856e-08,
645
+ "logits/chosen": 5915.91748046875,
646
+ "logits/rejected": 5172.326171875,
647
+ "logps/chosen": -250.53573608398438,
648
+ "logps/rejected": -234.00204467773438,
649
+ "loss": 240.5354,
650
+ "rewards/accuracies": 0.5406249761581421,
651
+ "rewards/chosen": 0.4144343435764313,
652
+ "rewards/margins": 0.029571443796157837,
653
+ "rewards/rejected": 0.38486289978027344,
654
+ "step": 420
655
+ },
656
+ {
657
+ "epoch": 0.9002878827532059,
658
+ "grad_norm": 1393.4874470921877,
659
+ "learning_rate": 1.4662207078575684e-08,
660
+ "logits/chosen": 5823.2763671875,
661
+ "logits/rejected": 4703.76025390625,
662
+ "logps/chosen": -245.7346954345703,
663
+ "logps/rejected": -221.4534149169922,
664
+ "loss": 239.5021,
665
+ "rewards/accuracies": 0.59375,
666
+ "rewards/chosen": 0.41867977380752563,
667
+ "rewards/margins": 0.05862581729888916,
668
+ "rewards/rejected": 0.3600539565086365,
669
+ "step": 430
670
+ },
671
+ {
672
+ "epoch": 0.9212248102590945,
673
+ "grad_norm": 974.1988194474727,
674
+ "learning_rate": 9.12094829893642e-09,
675
+ "logits/chosen": 5649.8154296875,
676
+ "logits/rejected": 5389.01953125,
677
+ "logps/chosen": -241.44961547851562,
678
+ "logps/rejected": -239.0779266357422,
679
+ "loss": 232.5532,
680
+ "rewards/accuracies": 0.4906249940395355,
681
+ "rewards/chosen": 0.37093910574913025,
682
+ "rewards/margins": 0.0012592204147949815,
683
+ "rewards/rejected": 0.36967989802360535,
684
+ "step": 440
685
+ },
686
+ {
687
+ "epoch": 0.942161737764983,
688
+ "grad_norm": 1054.0987809731553,
689
+ "learning_rate": 4.8708793644441086e-09,
690
+ "logits/chosen": 5798.8427734375,
691
+ "logits/rejected": 4999.23828125,
692
+ "logps/chosen": -249.7338104248047,
693
+ "logps/rejected": -220.97769165039062,
694
+ "loss": 238.5285,
695
+ "rewards/accuracies": 0.5375000238418579,
696
+ "rewards/chosen": 0.4060141146183014,
697
+ "rewards/margins": 0.0012865230673924088,
698
+ "rewards/rejected": 0.40472760796546936,
699
+ "step": 450
700
+ },
701
+ {
702
+ "epoch": 0.9630986652708715,
703
+ "grad_norm": 1120.0717473345896,
704
+ "learning_rate": 1.9347820230782295e-09,
705
+ "logits/chosen": 5987.23388671875,
706
+ "logits/rejected": 5070.90625,
707
+ "logps/chosen": -269.4898376464844,
708
+ "logps/rejected": -243.72256469726562,
709
+ "loss": 256.2592,
710
+ "rewards/accuracies": 0.559374988079071,
711
+ "rewards/chosen": 0.435092031955719,
712
+ "rewards/margins": 0.015190321020781994,
713
+ "rewards/rejected": 0.41990166902542114,
714
+ "step": 460
715
+ },
716
+ {
717
+ "epoch": 0.98403559277676,
718
+ "grad_norm": 1126.7552362991885,
719
+ "learning_rate": 3.2839470889836627e-10,
720
+ "logits/chosen": 5581.7841796875,
721
+ "logits/rejected": 4960.31689453125,
722
+ "logps/chosen": -238.2722930908203,
723
+ "logps/rejected": -217.5271453857422,
724
+ "loss": 245.3545,
725
+ "rewards/accuracies": 0.581250011920929,
726
+ "rewards/chosen": 0.42566928267478943,
727
+ "rewards/margins": 0.022912535816431046,
728
+ "rewards/rejected": 0.40275678038597107,
729
+ "step": 470
730
+ },
731
+ {
732
+ "epoch": 0.998691442030882,
733
+ "step": 477,
734
+ "total_flos": 0.0,
735
+ "train_loss": 244.87338864628373,
736
+ "train_runtime": 12795.3282,
737
+ "train_samples_per_second": 4.778,
738
+ "train_steps_per_second": 0.037
739
+ }
740
+ ],
741
+ "logging_steps": 10,
742
+ "max_steps": 477,
743
+ "num_input_tokens_seen": 0,
744
+ "num_train_epochs": 1,
745
+ "save_steps": 1000,
746
+ "stateful_callbacks": {
747
+ "TrainerControl": {
748
+ "args": {
749
+ "should_epoch_stop": false,
750
+ "should_evaluate": false,
751
+ "should_log": false,
752
+ "should_save": false,
753
+ "should_training_stop": false
754
+ },
755
+ "attributes": {}
756
+ }
757
+ },
758
+ "total_flos": 0.0,
759
+ "train_batch_size": 4,
760
+ "trial_name": null,
761
+ "trial_params": null
762
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b357f0f37a9f0ab171d4093877641370186158ab284b271fd0a157ff29caa633
3
+ size 7352