tengxiao1 commited on
Commit
83552a2
1 Parent(s): 093830b
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - princeton-nlp/mistral-instruct-ultrafeedback
9
+ model-index:
10
+ - name: Mistral-7B-Base-MI-1e-6
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
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tengxiao01/huggingface/runs/plgo1il8)
18
+ # Mistral-7B-Base-MI-1e-6
19
+
20
+ 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 princeton-nlp/mistral-instruct-ultrafeedback dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.8911
23
+ - Rewards/chosen: -0.9791
24
+ - Rewards/rejected: -1.1183
25
+ - Rewards/accuracies: 0.6263
26
+ - Rewards/margins: 0.1393
27
+ - Logps/rejected: -1.1183
28
+ - Logps/chosen: -0.9791
29
+ - Logits/rejected: -2.7752
30
+ - Logits/chosen: -2.7881
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 1e-06
50
+ - train_batch_size: 2
51
+ - eval_batch_size: 4
52
+ - seed: 42
53
+ - distributed_type: multi-GPU
54
+ - num_devices: 4
55
+ - gradient_accumulation_steps: 16
56
+ - total_train_batch_size: 128
57
+ - total_eval_batch_size: 16
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 1
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
66
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
67
+ | 1.8319 | 0.8573 | 400 | 1.8911 | -0.9791 | -1.1183 | 0.6263 | 0.1393 | -1.1183 | -0.9791 | -2.7752 | -2.7881 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.42.0
73
+ - Pytorch 2.1.2+cu121
74
+ - Datasets 2.14.6
75
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9987943737441393,
3
+ "eval_logits/chosen": -2.7708370685577393,
4
+ "eval_logits/rejected": -2.7552716732025146,
5
+ "eval_logps/chosen": -1.012373447418213,
6
+ "eval_logps/rejected": -1.167529821395874,
7
+ "eval_loss": 1.8871065378189087,
8
+ "eval_rewards/accuracies": 0.6422872543334961,
9
+ "eval_rewards/chosen": -1.012373447418213,
10
+ "eval_rewards/margins": 0.1551561951637268,
11
+ "eval_rewards/rejected": -1.167529821395874,
12
+ "eval_runtime": 436.9003,
13
+ "eval_samples": 2994,
14
+ "eval_samples_per_second": 6.853,
15
+ "eval_steps_per_second": 0.43,
16
+ "total_flos": 0.0,
17
+ "train_loss": 1.899593046294773,
18
+ "train_runtime": 19390.7723,
19
+ "train_samples": 59720,
20
+ "train_samples_per_second": 3.08,
21
+ "train_steps_per_second": 0.024
22
+ }
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": "4.42.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9987943737441393,
3
+ "eval_logits/chosen": -2.7708370685577393,
4
+ "eval_logits/rejected": -2.7552716732025146,
5
+ "eval_logps/chosen": -1.012373447418213,
6
+ "eval_logps/rejected": -1.167529821395874,
7
+ "eval_loss": 1.8871065378189087,
8
+ "eval_rewards/accuracies": 0.6422872543334961,
9
+ "eval_rewards/chosen": -1.012373447418213,
10
+ "eval_rewards/margins": 0.1551561951637268,
11
+ "eval_rewards/rejected": -1.167529821395874,
12
+ "eval_runtime": 436.9003,
13
+ "eval_samples": 2994,
14
+ "eval_samples_per_second": 6.853,
15
+ "eval_steps_per_second": 0.43
16
+ }
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": "4.42.0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d23ad9d8332caffc386a11ccc4e163f41e962aa7c7c4f1e5fb09c654028887c
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225b298e378e3363889bae132e9556d7a300c2e6a0b93d5376320f55664b6692
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377e869d6b3694663ca2b5fa762ce140d465fa3d5747cfe4461e36bb37807374
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": 0.9987943737441393,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.899593046294773,
5
+ "train_runtime": 19390.7723,
6
+ "train_samples": 59720,
7
+ "train_samples_per_second": 3.08,
8
+ "train_steps_per_second": 0.024
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9987943737441393,
5
+ "eval_steps": 400,
6
+ "global_step": 466,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010716677829872739,
13
+ "grad_norm": 8.743332175030668,
14
+ "learning_rate": 1.0638297872340425e-07,
15
+ "logits/chosen": -2.890564441680908,
16
+ "logits/rejected": -2.88779878616333,
17
+ "logps/chosen": -0.9741678237915039,
18
+ "logps/rejected": -0.9829432368278503,
19
+ "loss": 1.9541,
20
+ "rewards/accuracies": 0.48750001192092896,
21
+ "rewards/chosen": -0.9741678237915039,
22
+ "rewards/margins": 0.008775472640991211,
23
+ "rewards/rejected": -0.9829432368278503,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.021433355659745478,
28
+ "grad_norm": 10.116815688406033,
29
+ "learning_rate": 2.127659574468085e-07,
30
+ "logits/chosen": -2.906921863555908,
31
+ "logits/rejected": -2.892861843109131,
32
+ "logps/chosen": -0.9780665636062622,
33
+ "logps/rejected": -1.0012353658676147,
34
+ "loss": 1.9659,
35
+ "rewards/accuracies": 0.518750011920929,
36
+ "rewards/chosen": -0.9780665636062622,
37
+ "rewards/margins": 0.02316875383257866,
38
+ "rewards/rejected": -1.0012353658676147,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.032150033489618215,
43
+ "grad_norm": 7.106110538153892,
44
+ "learning_rate": 3.1914893617021275e-07,
45
+ "logits/chosen": -2.8951611518859863,
46
+ "logits/rejected": -2.917839288711548,
47
+ "logps/chosen": -0.9592474102973938,
48
+ "logps/rejected": -0.9844042658805847,
49
+ "loss": 1.9681,
50
+ "rewards/accuracies": 0.512499988079071,
51
+ "rewards/chosen": -0.9592474102973938,
52
+ "rewards/margins": 0.025157025083899498,
53
+ "rewards/rejected": -0.9844042658805847,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.042866711319490956,
58
+ "grad_norm": 7.768435236696218,
59
+ "learning_rate": 4.25531914893617e-07,
60
+ "logits/chosen": -2.9024550914764404,
61
+ "logits/rejected": -2.9008612632751465,
62
+ "logps/chosen": -0.9704982042312622,
63
+ "logps/rejected": -0.9749953150749207,
64
+ "loss": 1.9515,
65
+ "rewards/accuracies": 0.5375000238418579,
66
+ "rewards/chosen": -0.9704982042312622,
67
+ "rewards/margins": 0.004497217480093241,
68
+ "rewards/rejected": -0.9749953150749207,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.0535833891493637,
73
+ "grad_norm": 6.749888376224144,
74
+ "learning_rate": 5.319148936170212e-07,
75
+ "logits/chosen": -2.8302013874053955,
76
+ "logits/rejected": -2.8350861072540283,
77
+ "logps/chosen": -0.9493886828422546,
78
+ "logps/rejected": -0.9983908534049988,
79
+ "loss": 1.9589,
80
+ "rewards/accuracies": 0.5562499761581421,
81
+ "rewards/chosen": -0.9493886828422546,
82
+ "rewards/margins": 0.04900217801332474,
83
+ "rewards/rejected": -0.9983908534049988,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06430006697923643,
88
+ "grad_norm": 8.485574549470025,
89
+ "learning_rate": 6.382978723404255e-07,
90
+ "logits/chosen": -2.8937394618988037,
91
+ "logits/rejected": -2.9207406044006348,
92
+ "logps/chosen": -0.9754034876823425,
93
+ "logps/rejected": -0.9767441749572754,
94
+ "loss": 1.9649,
95
+ "rewards/accuracies": 0.4749999940395355,
96
+ "rewards/chosen": -0.9754034876823425,
97
+ "rewards/margins": 0.0013406850630417466,
98
+ "rewards/rejected": -0.9767441749572754,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07501674480910918,
103
+ "grad_norm": 7.870295088882763,
104
+ "learning_rate": 7.446808510638297e-07,
105
+ "logits/chosen": -2.9515388011932373,
106
+ "logits/rejected": -2.9212729930877686,
107
+ "logps/chosen": -0.943376362323761,
108
+ "logps/rejected": -0.9886476397514343,
109
+ "loss": 1.9685,
110
+ "rewards/accuracies": 0.581250011920929,
111
+ "rewards/chosen": -0.943376362323761,
112
+ "rewards/margins": 0.04527140408754349,
113
+ "rewards/rejected": -0.9886476397514343,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08573342263898191,
118
+ "grad_norm": 8.140974741892732,
119
+ "learning_rate": 8.51063829787234e-07,
120
+ "logits/chosen": -2.886676788330078,
121
+ "logits/rejected": -2.884409189224243,
122
+ "logps/chosen": -0.9962645769119263,
123
+ "logps/rejected": -0.9912681579589844,
124
+ "loss": 1.9721,
125
+ "rewards/accuracies": 0.4749999940395355,
126
+ "rewards/chosen": -0.9962645769119263,
127
+ "rewards/margins": -0.004996386356651783,
128
+ "rewards/rejected": -0.9912681579589844,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.09645010046885466,
133
+ "grad_norm": 7.451026538163931,
134
+ "learning_rate": 9.574468085106384e-07,
135
+ "logits/chosen": -2.845064878463745,
136
+ "logits/rejected": -2.834542751312256,
137
+ "logps/chosen": -0.9799020886421204,
138
+ "logps/rejected": -1.0003235340118408,
139
+ "loss": 1.9741,
140
+ "rewards/accuracies": 0.518750011920929,
141
+ "rewards/chosen": -0.9799020886421204,
142
+ "rewards/margins": 0.020421411842107773,
143
+ "rewards/rejected": -1.0003235340118408,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.1071667782987274,
148
+ "grad_norm": 7.309795501443683,
149
+ "learning_rate": 9.998735159083292e-07,
150
+ "logits/chosen": -2.8403611183166504,
151
+ "logits/rejected": -2.8530068397521973,
152
+ "logps/chosen": -0.9515609741210938,
153
+ "logps/rejected": -0.9347367286682129,
154
+ "loss": 1.9306,
155
+ "rewards/accuracies": 0.4937500059604645,
156
+ "rewards/chosen": -0.9515609741210938,
157
+ "rewards/margins": -0.01682429201900959,
158
+ "rewards/rejected": -0.9347367286682129,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11788345612860013,
163
+ "grad_norm": 8.763620887929697,
164
+ "learning_rate": 9.99100789302024e-07,
165
+ "logits/chosen": -2.861494541168213,
166
+ "logits/rejected": -2.8731250762939453,
167
+ "logps/chosen": -0.9942106008529663,
168
+ "logps/rejected": -1.0270545482635498,
169
+ "loss": 1.9564,
170
+ "rewards/accuracies": 0.53125,
171
+ "rewards/chosen": -0.9942106008529663,
172
+ "rewards/margins": 0.032844070345163345,
173
+ "rewards/rejected": -1.0270545482635498,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.12860013395847286,
178
+ "grad_norm": 10.67048824818839,
179
+ "learning_rate": 9.976266896046142e-07,
180
+ "logits/chosen": -2.745513439178467,
181
+ "logits/rejected": -2.7677714824676514,
182
+ "logps/chosen": -0.9298070669174194,
183
+ "logps/rejected": -0.9584784507751465,
184
+ "loss": 1.9575,
185
+ "rewards/accuracies": 0.518750011920929,
186
+ "rewards/chosen": -0.9298070669174194,
187
+ "rewards/margins": 0.028671354055404663,
188
+ "rewards/rejected": -0.9584784507751465,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.13931681178834562,
193
+ "grad_norm": 8.587332020158266,
194
+ "learning_rate": 9.954532883292758e-07,
195
+ "logits/chosen": -2.8174448013305664,
196
+ "logits/rejected": -2.827878713607788,
197
+ "logps/chosen": -0.9096312522888184,
198
+ "logps/rejected": -0.9340154528617859,
199
+ "loss": 1.9445,
200
+ "rewards/accuracies": 0.5562499761581421,
201
+ "rewards/chosen": -0.9096312522888184,
202
+ "rewards/margins": 0.02438436448574066,
203
+ "rewards/rejected": -0.9340154528617859,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.15003348961821836,
208
+ "grad_norm": 8.28588297183277,
209
+ "learning_rate": 9.925836396991307e-07,
210
+ "logits/chosen": -2.7543578147888184,
211
+ "logits/rejected": -2.7767698764801025,
212
+ "logps/chosen": -0.9463087320327759,
213
+ "logps/rejected": -1.000276803970337,
214
+ "loss": 1.9328,
215
+ "rewards/accuracies": 0.543749988079071,
216
+ "rewards/chosen": -0.9463087320327759,
217
+ "rewards/margins": 0.05396796017885208,
218
+ "rewards/rejected": -1.000276803970337,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.1607501674480911,
223
+ "grad_norm": 9.088492984557346,
224
+ "learning_rate": 9.89021776355227e-07,
225
+ "logits/chosen": -2.7640278339385986,
226
+ "logits/rejected": -2.7647509574890137,
227
+ "logps/chosen": -0.9192463755607605,
228
+ "logps/rejected": -0.9625679850578308,
229
+ "loss": 1.95,
230
+ "rewards/accuracies": 0.5625,
231
+ "rewards/chosen": -0.9192463755607605,
232
+ "rewards/margins": 0.043321557343006134,
233
+ "rewards/rejected": -0.9625679850578308,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.17146684527796383,
238
+ "grad_norm": 9.431427301698536,
239
+ "learning_rate": 9.847727036895757e-07,
240
+ "logits/chosen": -2.8038690090179443,
241
+ "logits/rejected": -2.82570481300354,
242
+ "logps/chosen": -0.9232662320137024,
243
+ "logps/rejected": -1.0234979391098022,
244
+ "loss": 1.9471,
245
+ "rewards/accuracies": 0.5874999761581421,
246
+ "rewards/chosen": -0.9232662320137024,
247
+ "rewards/margins": 0.10023164749145508,
248
+ "rewards/rejected": -1.0234979391098022,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.18218352310783656,
253
+ "grad_norm": 10.888524371529982,
254
+ "learning_rate": 9.79842392811207e-07,
255
+ "logits/chosen": -2.8308658599853516,
256
+ "logits/rejected": -2.840531349182129,
257
+ "logps/chosen": -0.9489914774894714,
258
+ "logps/rejected": -1.0153648853302002,
259
+ "loss": 1.9556,
260
+ "rewards/accuracies": 0.59375,
261
+ "rewards/chosen": -0.9489914774894714,
262
+ "rewards/margins": 0.06637347489595413,
263
+ "rewards/rejected": -1.0153648853302002,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.19290020093770932,
268
+ "grad_norm": 11.29650020138619,
269
+ "learning_rate": 9.742377721551285e-07,
270
+ "logits/chosen": -2.837176561355591,
271
+ "logits/rejected": -2.8398804664611816,
272
+ "logps/chosen": -0.9703192710876465,
273
+ "logps/rejected": -1.0296133756637573,
274
+ "loss": 1.9557,
275
+ "rewards/accuracies": 0.550000011920929,
276
+ "rewards/chosen": -0.9703192710876465,
277
+ "rewards/margins": 0.05929403379559517,
278
+ "rewards/rejected": -1.0296133756637573,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.20361687876758205,
283
+ "grad_norm": 10.210746185136436,
284
+ "learning_rate": 9.679667177459793e-07,
285
+ "logits/chosen": -2.8701424598693848,
286
+ "logits/rejected": -2.8827216625213623,
287
+ "logps/chosen": -0.9922488927841187,
288
+ "logps/rejected": -1.0364185571670532,
289
+ "loss": 1.935,
290
+ "rewards/accuracies": 0.5375000238418579,
291
+ "rewards/chosen": -0.9922488927841187,
292
+ "rewards/margins": 0.04416964575648308,
293
+ "rewards/rejected": -1.0364185571670532,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.2143335565974548,
298
+ "grad_norm": 12.483295768661268,
299
+ "learning_rate": 9.61038042130062e-07,
300
+ "logits/chosen": -2.8926491737365723,
301
+ "logits/rejected": -2.901106357574463,
302
+ "logps/chosen": -1.0361850261688232,
303
+ "logps/rejected": -1.0975309610366821,
304
+ "loss": 1.9596,
305
+ "rewards/accuracies": 0.59375,
306
+ "rewards/chosen": -1.0361850261688232,
307
+ "rewards/margins": 0.06134594604372978,
308
+ "rewards/rejected": -1.0975309610366821,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.22505023442732752,
313
+ "grad_norm": 10.251687371352437,
314
+ "learning_rate": 9.534614819913056e-07,
315
+ "logits/chosen": -2.8896324634552,
316
+ "logits/rejected": -2.8919472694396973,
317
+ "logps/chosen": -0.951892077922821,
318
+ "logps/rejected": -1.0144917964935303,
319
+ "loss": 1.9124,
320
+ "rewards/accuracies": 0.5625,
321
+ "rewards/chosen": -0.951892077922821,
322
+ "rewards/margins": 0.06259982287883759,
323
+ "rewards/rejected": -1.0144917964935303,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23576691225720026,
328
+ "grad_norm": 12.050194786037592,
329
+ "learning_rate": 9.45247684468561e-07,
330
+ "logits/chosen": -2.884787082672119,
331
+ "logits/rejected": -2.8778603076934814,
332
+ "logps/chosen": -0.9767457842826843,
333
+ "logps/rejected": -1.0685449838638306,
334
+ "loss": 1.9478,
335
+ "rewards/accuracies": 0.6499999761581421,
336
+ "rewards/chosen": -0.9767457842826843,
337
+ "rewards/margins": 0.09179918467998505,
338
+ "rewards/rejected": -1.0685449838638306,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.24648359008707302,
343
+ "grad_norm": 16.70841820517718,
344
+ "learning_rate": 9.364081921934605e-07,
345
+ "logits/chosen": -2.938917636871338,
346
+ "logits/rejected": -2.9450087547302246,
347
+ "logps/chosen": -0.9636579751968384,
348
+ "logps/rejected": -0.9759002923965454,
349
+ "loss": 1.9752,
350
+ "rewards/accuracies": 0.5249999761581421,
351
+ "rewards/chosen": -0.9636579751968384,
352
+ "rewards/margins": 0.01224228460341692,
353
+ "rewards/rejected": -0.9759002923965454,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2572002679169457,
358
+ "grad_norm": 11.293944567951943,
359
+ "learning_rate": 9.269554270698635e-07,
360
+ "logits/chosen": -2.945613384246826,
361
+ "logits/rejected": -2.9629931449890137,
362
+ "logps/chosen": -0.9591239094734192,
363
+ "logps/rejected": -0.9764735102653503,
364
+ "loss": 1.9573,
365
+ "rewards/accuracies": 0.518750011920929,
366
+ "rewards/chosen": -0.9591239094734192,
367
+ "rewards/margins": 0.01734955981373787,
368
+ "rewards/rejected": -0.9764735102653503,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.2679169457468185,
373
+ "grad_norm": 11.980171410561908,
374
+ "learning_rate": 9.169026728176843e-07,
375
+ "logits/chosen": -2.933450222015381,
376
+ "logits/rejected": -2.9331278800964355,
377
+ "logps/chosen": -0.9632900357246399,
378
+ "logps/rejected": -1.0157678127288818,
379
+ "loss": 1.9492,
380
+ "rewards/accuracies": 0.5687500238418579,
381
+ "rewards/chosen": -0.9632900357246399,
382
+ "rewards/margins": 0.05247765779495239,
383
+ "rewards/rejected": -1.0157678127288818,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.27863362357669125,
388
+ "grad_norm": 13.043968582425784,
389
+ "learning_rate": 9.062640563056338e-07,
390
+ "logits/chosen": -2.991359233856201,
391
+ "logits/rejected": -2.988865613937378,
392
+ "logps/chosen": -0.9493595361709595,
393
+ "logps/rejected": -1.034130334854126,
394
+ "loss": 1.922,
395
+ "rewards/accuracies": 0.59375,
396
+ "rewards/chosen": -0.9493595361709595,
397
+ "rewards/margins": 0.08477075397968292,
398
+ "rewards/rejected": -1.034130334854126,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.289350301406564,
403
+ "grad_norm": 12.532276437925889,
404
+ "learning_rate": 8.950545276991059e-07,
405
+ "logits/chosen": -3.0021941661834717,
406
+ "logits/rejected": -3.0065648555755615,
407
+ "logps/chosen": -0.9963411092758179,
408
+ "logps/rejected": -1.0470635890960693,
409
+ "loss": 1.9424,
410
+ "rewards/accuracies": 0.5874999761581421,
411
+ "rewards/chosen": -0.9963411092758179,
412
+ "rewards/margins": 0.05072233825922012,
413
+ "rewards/rejected": -1.0470635890960693,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.3000669792364367,
418
+ "grad_norm": 12.705557690233402,
419
+ "learning_rate": 8.832898394511059e-07,
420
+ "logits/chosen": -2.9534518718719482,
421
+ "logits/rejected": -2.955967903137207,
422
+ "logps/chosen": -0.9860572814941406,
423
+ "logps/rejected": -1.0404431819915771,
424
+ "loss": 1.9178,
425
+ "rewards/accuracies": 0.574999988079071,
426
+ "rewards/chosen": -0.9860572814941406,
427
+ "rewards/margins": 0.054385989904403687,
428
+ "rewards/rejected": -1.0404431819915771,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.31078365706630945,
433
+ "grad_norm": 13.072919082266676,
434
+ "learning_rate": 8.709865241657479e-07,
435
+ "logits/chosen": -3.0093483924865723,
436
+ "logits/rejected": -2.979004383087158,
437
+ "logps/chosen": -0.9930181503295898,
438
+ "logps/rejected": -1.0835025310516357,
439
+ "loss": 1.9157,
440
+ "rewards/accuracies": 0.574999988079071,
441
+ "rewards/chosen": -0.9930181503295898,
442
+ "rewards/margins": 0.09048454463481903,
443
+ "rewards/rejected": -1.0835025310516357,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.3215003348961822,
448
+ "grad_norm": 12.426824715988731,
449
+ "learning_rate": 8.581618713654237e-07,
450
+ "logits/chosen": -3.013441324234009,
451
+ "logits/rejected": -3.020658016204834,
452
+ "logps/chosen": -0.9797670245170593,
453
+ "logps/rejected": -1.0478479862213135,
454
+ "loss": 1.9384,
455
+ "rewards/accuracies": 0.6000000238418579,
456
+ "rewards/chosen": -0.9797670245170593,
457
+ "rewards/margins": 0.06808092445135117,
458
+ "rewards/rejected": -1.0478479862213135,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.3322170127260549,
463
+ "grad_norm": 12.994046950866517,
464
+ "learning_rate": 8.448339031942969e-07,
465
+ "logits/chosen": -3.1380882263183594,
466
+ "logits/rejected": -3.119088649749756,
467
+ "logps/chosen": -1.0096795558929443,
468
+ "logps/rejected": -1.0793818235397339,
469
+ "loss": 1.9501,
470
+ "rewards/accuracies": 0.6187499761581421,
471
+ "rewards/chosen": -1.0096795558929443,
472
+ "rewards/margins": 0.0697021633386612,
473
+ "rewards/rejected": -1.0793818235397339,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.34293369055592765,
478
+ "grad_norm": 14.285933742292032,
479
+ "learning_rate": 8.310213490922615e-07,
480
+ "logits/chosen": -3.086894989013672,
481
+ "logits/rejected": -3.0781033039093018,
482
+ "logps/chosen": -1.01212477684021,
483
+ "logps/rejected": -1.1041617393493652,
484
+ "loss": 1.924,
485
+ "rewards/accuracies": 0.574999988079071,
486
+ "rewards/chosen": -1.01212477684021,
487
+ "rewards/margins": 0.09203706681728363,
488
+ "rewards/rejected": -1.1041617393493652,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.3536503683858004,
493
+ "grad_norm": 12.902647964980785,
494
+ "learning_rate": 8.167436194749575e-07,
495
+ "logits/chosen": -3.154498815536499,
496
+ "logits/rejected": -3.1380507946014404,
497
+ "logps/chosen": -0.9696465730667114,
498
+ "logps/rejected": -1.0397228002548218,
499
+ "loss": 1.9234,
500
+ "rewards/accuracies": 0.6312500238418579,
501
+ "rewards/chosen": -0.9696465730667114,
502
+ "rewards/margins": 0.07007621228694916,
503
+ "rewards/rejected": -1.0397228002548218,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3643670462156731,
508
+ "grad_norm": 10.461713458782954,
509
+ "learning_rate": 8.020207784568291e-07,
510
+ "logits/chosen": -3.0909907817840576,
511
+ "logits/rejected": -3.0954232215881348,
512
+ "logps/chosen": -0.9789296388626099,
513
+ "logps/rejected": -1.0583703517913818,
514
+ "loss": 1.8994,
515
+ "rewards/accuracies": 0.5625,
516
+ "rewards/chosen": -0.9789296388626099,
517
+ "rewards/margins": 0.07944078743457794,
518
+ "rewards/rejected": -1.0583703517913818,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.3750837240455459,
523
+ "grad_norm": 14.39267394950559,
524
+ "learning_rate": 7.868735156555566e-07,
525
+ "logits/chosen": -3.113248348236084,
526
+ "logits/rejected": -3.116093158721924,
527
+ "logps/chosen": -0.9837858080863953,
528
+ "logps/rejected": -1.0499708652496338,
529
+ "loss": 1.9274,
530
+ "rewards/accuracies": 0.637499988079071,
531
+ "rewards/chosen": -0.9837858080863953,
532
+ "rewards/margins": 0.06618491560220718,
533
+ "rewards/rejected": -1.0499708652496338,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.38580040187541864,
538
+ "grad_norm": 15.99990919657707,
539
+ "learning_rate": 7.713231171174868e-07,
540
+ "logits/chosen": -3.117457866668701,
541
+ "logits/rejected": -3.1266255378723145,
542
+ "logps/chosen": -1.0582538843154907,
543
+ "logps/rejected": -1.133825659751892,
544
+ "loss": 1.9527,
545
+ "rewards/accuracies": 0.53125,
546
+ "rewards/chosen": -1.0582538843154907,
547
+ "rewards/margins": 0.0755719467997551,
548
+ "rewards/rejected": -1.133825659751892,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.3965170797052914,
553
+ "grad_norm": 14.766672490703176,
554
+ "learning_rate": 7.553914354049162e-07,
555
+ "logits/chosen": -3.0913758277893066,
556
+ "logits/rejected": -3.103057384490967,
557
+ "logps/chosen": -1.023158073425293,
558
+ "logps/rejected": -1.06888747215271,
559
+ "loss": 1.9093,
560
+ "rewards/accuracies": 0.612500011920929,
561
+ "rewards/chosen": -1.023158073425293,
562
+ "rewards/margins": 0.04572921246290207,
563
+ "rewards/rejected": -1.06888747215271,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.4072337575351641,
568
+ "grad_norm": 15.970782695590072,
569
+ "learning_rate": 7.39100858887266e-07,
570
+ "logits/chosen": -3.0117366313934326,
571
+ "logits/rejected": -3.0253918170928955,
572
+ "logps/chosen": -0.9792415499687195,
573
+ "logps/rejected": -1.192731499671936,
574
+ "loss": 1.9159,
575
+ "rewards/accuracies": 0.6875,
576
+ "rewards/chosen": -0.9792415499687195,
577
+ "rewards/margins": 0.2134898155927658,
578
+ "rewards/rejected": -1.192731499671936,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.41795043536503684,
583
+ "grad_norm": 14.772743027007902,
584
+ "learning_rate": 7.224742802793004e-07,
585
+ "logits/chosen": -3.117619514465332,
586
+ "logits/rejected": -3.105710506439209,
587
+ "logps/chosen": -0.9820570945739746,
588
+ "logps/rejected": -1.0550075769424438,
589
+ "loss": 1.9206,
590
+ "rewards/accuracies": 0.5687500238418579,
591
+ "rewards/chosen": -0.9820570945739746,
592
+ "rewards/margins": 0.07295046001672745,
593
+ "rewards/rejected": -1.0550075769424438,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.4286671131949096,
598
+ "grad_norm": 13.569195793364742,
599
+ "learning_rate": 7.055350644706022e-07,
600
+ "logits/chosen": -3.0321404933929443,
601
+ "logits/rejected": -3.049098491668701,
602
+ "logps/chosen": -0.9425796270370483,
603
+ "logps/rejected": -1.015730857849121,
604
+ "loss": 1.8967,
605
+ "rewards/accuracies": 0.550000011920929,
606
+ "rewards/chosen": -0.9425796270370483,
607
+ "rewards/margins": 0.07315118610858917,
608
+ "rewards/rejected": -1.015730857849121,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.4393837910247823,
613
+ "grad_norm": 17.357578155356272,
614
+ "learning_rate": 6.883070156915139e-07,
615
+ "logits/chosen": -3.1063551902770996,
616
+ "logits/rejected": -3.087735652923584,
617
+ "logps/chosen": -0.9921137094497681,
618
+ "logps/rejected": -1.0688540935516357,
619
+ "loss": 1.9072,
620
+ "rewards/accuracies": 0.643750011920929,
621
+ "rewards/chosen": -0.9921137094497681,
622
+ "rewards/margins": 0.07674027979373932,
623
+ "rewards/rejected": -1.0688540935516357,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.45010046885465504,
628
+ "grad_norm": 18.638096035157822,
629
+ "learning_rate": 6.708143440616845e-07,
630
+ "logits/chosen": -3.037801504135132,
631
+ "logits/rejected": -3.043381452560425,
632
+ "logps/chosen": -0.9749434590339661,
633
+ "logps/rejected": -1.093065619468689,
634
+ "loss": 1.8807,
635
+ "rewards/accuracies": 0.6499999761581421,
636
+ "rewards/chosen": -0.9749434590339661,
637
+ "rewards/margins": 0.11812222003936768,
638
+ "rewards/rejected": -1.093065619468689,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.4608171466845278,
643
+ "grad_norm": 14.384225079310538,
644
+ "learning_rate": 6.530816315682306e-07,
645
+ "logits/chosen": -3.039210319519043,
646
+ "logits/rejected": -3.036463499069214,
647
+ "logps/chosen": -0.9878280758857727,
648
+ "logps/rejected": -1.0471224784851074,
649
+ "loss": 1.8936,
650
+ "rewards/accuracies": 0.581250011920929,
651
+ "rewards/chosen": -0.9878280758857727,
652
+ "rewards/margins": 0.0592944398522377,
653
+ "rewards/rejected": -1.0471224784851074,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.4715338245144005,
658
+ "grad_norm": 15.635777348265833,
659
+ "learning_rate": 6.351337975213237e-07,
660
+ "logits/chosen": -2.952924966812134,
661
+ "logits/rejected": -2.9542202949523926,
662
+ "logps/chosen": -0.950057327747345,
663
+ "logps/rejected": -1.0494937896728516,
664
+ "loss": 1.9176,
665
+ "rewards/accuracies": 0.550000011920929,
666
+ "rewards/chosen": -0.950057327747345,
667
+ "rewards/margins": 0.0994364321231842,
668
+ "rewards/rejected": -1.0494937896728516,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.4822505023442733,
673
+ "grad_norm": 15.744387463358793,
674
+ "learning_rate": 6.169960635357437e-07,
675
+ "logits/chosen": -2.9482624530792236,
676
+ "logits/rejected": -2.989917278289795,
677
+ "logps/chosen": -0.9638145565986633,
678
+ "logps/rejected": -1.1090409755706787,
679
+ "loss": 1.9033,
680
+ "rewards/accuracies": 0.65625,
681
+ "rewards/chosen": -0.9638145565986633,
682
+ "rewards/margins": 0.14522647857666016,
683
+ "rewards/rejected": -1.1090409755706787,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.49296718017414604,
688
+ "grad_norm": 20.61441976992923,
689
+ "learning_rate": 5.98693918087613e-07,
690
+ "logits/chosen": -2.8699066638946533,
691
+ "logits/rejected": -2.870300531387329,
692
+ "logps/chosen": -0.9924839735031128,
693
+ "logps/rejected": -1.0983588695526123,
694
+ "loss": 1.8841,
695
+ "rewards/accuracies": 0.6875,
696
+ "rewards/chosen": -0.9924839735031128,
697
+ "rewards/margins": 0.10587481409311295,
698
+ "rewards/rejected": -1.0983588695526123,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.5036838580040187,
703
+ "grad_norm": 16.252130697815385,
704
+ "learning_rate": 5.802530806961194e-07,
705
+ "logits/chosen": -2.817322254180908,
706
+ "logits/rejected": -2.829948663711548,
707
+ "logps/chosen": -0.980228066444397,
708
+ "logps/rejected": -1.1411757469177246,
709
+ "loss": 1.8909,
710
+ "rewards/accuracies": 0.606249988079071,
711
+ "rewards/chosen": -0.980228066444397,
712
+ "rewards/margins": 0.16094763576984406,
713
+ "rewards/rejected": -1.1411757469177246,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5144005358338914,
718
+ "grad_norm": 18.85039464903285,
719
+ "learning_rate": 5.616994657805565e-07,
720
+ "logits/chosen": -2.8348546028137207,
721
+ "logits/rejected": -2.8363900184631348,
722
+ "logps/chosen": -1.0022538900375366,
723
+ "logps/rejected": -1.091737985610962,
724
+ "loss": 1.9144,
725
+ "rewards/accuracies": 0.643750011920929,
726
+ "rewards/chosen": -1.0022538900375366,
727
+ "rewards/margins": 0.08948404341936111,
728
+ "rewards/rejected": -1.091737985610962,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5251172136637642,
733
+ "grad_norm": 18.11195320561811,
734
+ "learning_rate": 5.430591462434792e-07,
735
+ "logits/chosen": -2.8302159309387207,
736
+ "logits/rejected": -2.8293166160583496,
737
+ "logps/chosen": -0.9994494318962097,
738
+ "logps/rejected": -1.0923607349395752,
739
+ "loss": 1.8816,
740
+ "rewards/accuracies": 0.6312500238418579,
741
+ "rewards/chosen": -0.9994494318962097,
742
+ "rewards/margins": 0.09291131794452667,
743
+ "rewards/rejected": -1.0923607349395752,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.535833891493637,
748
+ "grad_norm": 17.05860095183427,
749
+ "learning_rate": 5.24358316831145e-07,
750
+ "logits/chosen": -2.8530397415161133,
751
+ "logits/rejected": -2.8722071647644043,
752
+ "logps/chosen": -1.039880394935608,
753
+ "logps/rejected": -1.1407957077026367,
754
+ "loss": 1.8947,
755
+ "rewards/accuracies": 0.675000011920929,
756
+ "rewards/chosen": -1.039880394935608,
757
+ "rewards/margins": 0.10091539472341537,
758
+ "rewards/rejected": -1.1407957077026367,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.5465505693235098,
763
+ "grad_norm": 18.749033093794495,
764
+ "learning_rate": 5.05623257322734e-07,
765
+ "logits/chosen": -2.93331241607666,
766
+ "logits/rejected": -2.944380283355713,
767
+ "logps/chosen": -0.9659943580627441,
768
+ "logps/rejected": -1.0837066173553467,
769
+ "loss": 1.8979,
770
+ "rewards/accuracies": 0.612500011920929,
771
+ "rewards/chosen": -0.9659943580627441,
772
+ "rewards/margins": 0.11771215498447418,
773
+ "rewards/rejected": -1.0837066173553467,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5572672471533825,
778
+ "grad_norm": 16.94811716813612,
779
+ "learning_rate": 4.868802956000706e-07,
780
+ "logits/chosen": -2.931999683380127,
781
+ "logits/rejected": -2.9354639053344727,
782
+ "logps/chosen": -0.9535225033760071,
783
+ "logps/rejected": -1.0598043203353882,
784
+ "loss": 1.8988,
785
+ "rewards/accuracies": 0.543749988079071,
786
+ "rewards/chosen": -0.9535225033760071,
787
+ "rewards/margins": 0.10628175735473633,
788
+ "rewards/rejected": -1.0598043203353882,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5679839249832552,
793
+ "grad_norm": 16.773823816327198,
794
+ "learning_rate": 4.681557706497518e-07,
795
+ "logits/chosen": -2.9415526390075684,
796
+ "logits/rejected": -2.928161144256592,
797
+ "logps/chosen": -0.9740009307861328,
798
+ "logps/rejected": -1.1567602157592773,
799
+ "loss": 1.8795,
800
+ "rewards/accuracies": 0.6312500238418579,
801
+ "rewards/chosen": -0.9740009307861328,
802
+ "rewards/margins": 0.1827593445777893,
803
+ "rewards/rejected": -1.1567602157592773,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.578700602813128,
808
+ "grad_norm": 18.918032339525077,
809
+ "learning_rate": 4.494759955496678e-07,
810
+ "logits/chosen": -2.977628231048584,
811
+ "logits/rejected": -2.993778705596924,
812
+ "logps/chosen": -0.9572176933288574,
813
+ "logps/rejected": -1.0660667419433594,
814
+ "loss": 1.8826,
815
+ "rewards/accuracies": 0.6625000238418579,
816
+ "rewards/chosen": -0.9572176933288574,
817
+ "rewards/margins": 0.1088489443063736,
818
+ "rewards/rejected": -1.0660667419433594,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.5894172806430007,
823
+ "grad_norm": 18.052342935862615,
824
+ "learning_rate": 4.3086722049193145e-07,
825
+ "logits/chosen": -3.0297939777374268,
826
+ "logits/rejected": -3.0311572551727295,
827
+ "logps/chosen": -0.9626353979110718,
828
+ "logps/rejected": -1.1277216672897339,
829
+ "loss": 1.8892,
830
+ "rewards/accuracies": 0.6812499761581421,
831
+ "rewards/chosen": -0.9626353979110718,
832
+ "rewards/margins": 0.16508622467517853,
833
+ "rewards/rejected": -1.1277216672897339,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.6001339584728734,
838
+ "grad_norm": 17.526484616917582,
839
+ "learning_rate": 4.1235559589418164e-07,
840
+ "logits/chosen": -2.9183692932128906,
841
+ "logits/rejected": -2.9183740615844727,
842
+ "logps/chosen": -1.0271321535110474,
843
+ "logps/rejected": -1.1547820568084717,
844
+ "loss": 1.8912,
845
+ "rewards/accuracies": 0.6312500238418579,
846
+ "rewards/chosen": -1.0271321535110474,
847
+ "rewards/margins": 0.1276499330997467,
848
+ "rewards/rejected": -1.1547820568084717,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.6108506363027462,
853
+ "grad_norm": 18.526748745941557,
854
+ "learning_rate": 3.9396713565109375e-07,
855
+ "logits/chosen": -2.999577045440674,
856
+ "logits/rejected": -2.9965460300445557,
857
+ "logps/chosen": -0.9945805668830872,
858
+ "logps/rejected": -1.077164888381958,
859
+ "loss": 1.9015,
860
+ "rewards/accuracies": 0.606249988079071,
861
+ "rewards/chosen": -0.9945805668830872,
862
+ "rewards/margins": 0.08258435875177383,
863
+ "rewards/rejected": -1.077164888381958,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6215673141326189,
868
+ "grad_norm": 20.379894797382978,
869
+ "learning_rate": 3.757276805777454e-07,
870
+ "logits/chosen": -3.0354697704315186,
871
+ "logits/rejected": -3.0337672233581543,
872
+ "logps/chosen": -0.9179645776748657,
873
+ "logps/rejected": -1.0484569072723389,
874
+ "loss": 1.8803,
875
+ "rewards/accuracies": 0.550000011920929,
876
+ "rewards/chosen": -0.9179645776748657,
877
+ "rewards/margins": 0.13049228489398956,
878
+ "rewards/rejected": -1.0484569072723389,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6322839919624916,
883
+ "grad_norm": 20.690228448794066,
884
+ "learning_rate": 3.5766286209620446e-07,
885
+ "logits/chosen": -3.001173973083496,
886
+ "logits/rejected": -2.9999818801879883,
887
+ "logps/chosen": -0.9978302717208862,
888
+ "logps/rejected": -1.218730092048645,
889
+ "loss": 1.8787,
890
+ "rewards/accuracies": 0.643750011920929,
891
+ "rewards/chosen": -0.9978302717208862,
892
+ "rewards/margins": 0.22089961171150208,
893
+ "rewards/rejected": -1.218730092048645,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6430006697923644,
898
+ "grad_norm": 21.088864907959156,
899
+ "learning_rate": 3.3979806621637095e-07,
900
+ "logits/chosen": -3.0734269618988037,
901
+ "logits/rejected": -3.0850183963775635,
902
+ "logps/chosen": -1.0158809423446655,
903
+ "logps/rejected": -1.203379511833191,
904
+ "loss": 1.8412,
905
+ "rewards/accuracies": 0.675000011920929,
906
+ "rewards/chosen": -1.0158809423446655,
907
+ "rewards/margins": 0.1874985247850418,
908
+ "rewards/rejected": -1.203379511833191,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6537173476222371,
913
+ "grad_norm": 20.56239032846782,
914
+ "learning_rate": 3.221583978616932e-07,
915
+ "logits/chosen": -3.0289087295532227,
916
+ "logits/rejected": -3.0159077644348145,
917
+ "logps/chosen": -1.0385640859603882,
918
+ "logps/rejected": -1.1604039669036865,
919
+ "loss": 1.8697,
920
+ "rewards/accuracies": 0.6499999761581421,
921
+ "rewards/chosen": -1.0385640859603882,
922
+ "rewards/margins": 0.12183995544910431,
923
+ "rewards/rejected": -1.1604039669036865,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6644340254521098,
928
+ "grad_norm": 23.460225989452297,
929
+ "learning_rate": 3.047686455898836e-07,
930
+ "logits/chosen": -3.080087423324585,
931
+ "logits/rejected": -3.0696513652801514,
932
+ "logps/chosen": -1.0038082599639893,
933
+ "logps/rejected": -1.1881027221679688,
934
+ "loss": 1.8639,
935
+ "rewards/accuracies": 0.65625,
936
+ "rewards/chosen": -1.0038082599639893,
937
+ "rewards/margins": 0.18429455161094666,
938
+ "rewards/rejected": -1.1881027221679688,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6751507032819826,
943
+ "grad_norm": 20.943994771592788,
944
+ "learning_rate": 2.8765324675821734e-07,
945
+ "logits/chosen": -2.944671630859375,
946
+ "logits/rejected": -2.9371066093444824,
947
+ "logps/chosen": -1.0098899602890015,
948
+ "logps/rejected": -1.1762586832046509,
949
+ "loss": 1.8745,
950
+ "rewards/accuracies": 0.625,
951
+ "rewards/chosen": -1.0098899602890015,
952
+ "rewards/margins": 0.16636863350868225,
953
+ "rewards/rejected": -1.1762586832046509,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6858673811118553,
958
+ "grad_norm": 23.376564204026522,
959
+ "learning_rate": 2.708362531823621e-07,
960
+ "logits/chosen": -2.9114675521850586,
961
+ "logits/rejected": -2.8761847019195557,
962
+ "logps/chosen": -1.0019965171813965,
963
+ "logps/rejected": -1.203962802886963,
964
+ "loss": 1.8847,
965
+ "rewards/accuracies": 0.675000011920929,
966
+ "rewards/chosen": -1.0019965171813965,
967
+ "rewards/margins": 0.20196643471717834,
968
+ "rewards/rejected": -1.203962802886963,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.696584058941728,
973
+ "grad_norm": 21.72889429456692,
974
+ "learning_rate": 2.5434129733700093e-07,
975
+ "logits/chosen": -2.859740734100342,
976
+ "logits/rejected": -2.850984573364258,
977
+ "logps/chosen": -0.9476163983345032,
978
+ "logps/rejected": -1.190605640411377,
979
+ "loss": 1.8338,
980
+ "rewards/accuracies": 0.6812499761581421,
981
+ "rewards/chosen": -0.9476163983345032,
982
+ "rewards/margins": 0.24298930168151855,
983
+ "rewards/rejected": -1.190605640411377,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.7073007367716008,
988
+ "grad_norm": 23.976896941165123,
989
+ "learning_rate": 2.3819155914574235e-07,
990
+ "logits/chosen": -2.881459951400757,
991
+ "logits/rejected": -2.860196113586426,
992
+ "logps/chosen": -0.9749948382377625,
993
+ "logps/rejected": -1.1787073612213135,
994
+ "loss": 1.8473,
995
+ "rewards/accuracies": 0.6625000238418579,
996
+ "rewards/chosen": -0.9749948382377625,
997
+ "rewards/margins": 0.20371253788471222,
998
+ "rewards/rejected": -1.1787073612213135,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7180174146014735,
1003
+ "grad_norm": 28.808399946877696,
1004
+ "learning_rate": 2.2240973340698882e-07,
1005
+ "logits/chosen": -2.9146461486816406,
1006
+ "logits/rejected": -2.9025330543518066,
1007
+ "logps/chosen": -0.9778841137886047,
1008
+ "logps/rejected": -1.1417423486709595,
1009
+ "loss": 1.8579,
1010
+ "rewards/accuracies": 0.7124999761581421,
1011
+ "rewards/chosen": -0.9778841137886047,
1012
+ "rewards/margins": 0.16385838389396667,
1013
+ "rewards/rejected": -1.1417423486709595,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7287340924313462,
1018
+ "grad_norm": 25.882278976736618,
1019
+ "learning_rate": 2.0701799790153896e-07,
1020
+ "logits/chosen": -2.8679490089416504,
1021
+ "logits/rejected": -2.8503952026367188,
1022
+ "logps/chosen": -0.9974260330200195,
1023
+ "logps/rejected": -1.2173974514007568,
1024
+ "loss": 1.858,
1025
+ "rewards/accuracies": 0.668749988079071,
1026
+ "rewards/chosen": -0.9974260330200195,
1027
+ "rewards/margins": 0.21997132897377014,
1028
+ "rewards/rejected": -1.2173974514007568,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.739450770261219,
1033
+ "grad_norm": 25.899929236131076,
1034
+ "learning_rate": 1.9203798222674138e-07,
1035
+ "logits/chosen": -2.881312608718872,
1036
+ "logits/rejected": -2.886810779571533,
1037
+ "logps/chosen": -0.9790380597114563,
1038
+ "logps/rejected": -1.2078144550323486,
1039
+ "loss": 1.8434,
1040
+ "rewards/accuracies": 0.625,
1041
+ "rewards/chosen": -0.9790380597114563,
1042
+ "rewards/margins": 0.2287764996290207,
1043
+ "rewards/rejected": -1.2078144550323486,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7501674480910918,
1048
+ "grad_norm": 22.394258706384488,
1049
+ "learning_rate": 1.774907374009953e-07,
1050
+ "logits/chosen": -2.854478120803833,
1051
+ "logits/rejected": -2.8414759635925293,
1052
+ "logps/chosen": -0.9902400970458984,
1053
+ "logps/rejected": -1.1531636714935303,
1054
+ "loss": 1.8534,
1055
+ "rewards/accuracies": 0.6000000238418579,
1056
+ "rewards/chosen": -0.9902400970458984,
1057
+ "rewards/margins": 0.16292349994182587,
1058
+ "rewards/rejected": -1.1531636714935303,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7608841259209645,
1063
+ "grad_norm": 32.75022427627133,
1064
+ "learning_rate": 1.6339670628131326e-07,
1065
+ "logits/chosen": -2.8383326530456543,
1066
+ "logits/rejected": -2.819650888442993,
1067
+ "logps/chosen": -1.0634033679962158,
1068
+ "logps/rejected": -1.194883942604065,
1069
+ "loss": 1.876,
1070
+ "rewards/accuracies": 0.59375,
1071
+ "rewards/chosen": -1.0634033679962158,
1072
+ "rewards/margins": 0.13148045539855957,
1073
+ "rewards/rejected": -1.194883942604065,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7716008037508373,
1078
+ "grad_norm": 23.817047943255176,
1079
+ "learning_rate": 1.4977569483551632e-07,
1080
+ "logits/chosen": -2.8515446186065674,
1081
+ "logits/rejected": -2.8371310234069824,
1082
+ "logps/chosen": -0.9948540925979614,
1083
+ "logps/rejected": -1.1568361520767212,
1084
+ "loss": 1.8636,
1085
+ "rewards/accuracies": 0.6312500238418579,
1086
+ "rewards/chosen": -0.9948540925979614,
1087
+ "rewards/margins": 0.16198216378688812,
1088
+ "rewards/rejected": -1.1568361520767212,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.78231748158071,
1093
+ "grad_norm": 29.671187736811945,
1094
+ "learning_rate": 1.366468443094343e-07,
1095
+ "logits/chosen": -2.875363826751709,
1096
+ "logits/rejected": -2.8553128242492676,
1097
+ "logps/chosen": -1.039432168006897,
1098
+ "logps/rejected": -1.2274564504623413,
1099
+ "loss": 1.859,
1100
+ "rewards/accuracies": 0.6625000238418579,
1101
+ "rewards/chosen": -1.039432168006897,
1102
+ "rewards/margins": 0.18802431225776672,
1103
+ "rewards/rejected": -1.2274564504623413,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7930341594105828,
1108
+ "grad_norm": 33.954689650694874,
1109
+ "learning_rate": 1.240286043282197e-07,
1110
+ "logits/chosen": -2.8917102813720703,
1111
+ "logits/rejected": -2.8770086765289307,
1112
+ "logps/chosen": -1.0392128229141235,
1113
+ "logps/rejected": -1.1902668476104736,
1114
+ "loss": 1.8531,
1115
+ "rewards/accuracies": 0.6625000238418579,
1116
+ "rewards/chosen": -1.0392128229141235,
1117
+ "rewards/margins": 0.15105411410331726,
1118
+ "rewards/rejected": -1.1902668476104736,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.8037508372404555,
1123
+ "grad_norm": 29.25246301873259,
1124
+ "learning_rate": 1.1193870696958058e-07,
1125
+ "logits/chosen": -2.866624116897583,
1126
+ "logits/rejected": -2.865328073501587,
1127
+ "logps/chosen": -1.0088036060333252,
1128
+ "logps/rejected": -1.1752225160598755,
1129
+ "loss": 1.871,
1130
+ "rewards/accuracies": 0.625,
1131
+ "rewards/chosen": -1.0088036060333252,
1132
+ "rewards/margins": 0.16641899943351746,
1133
+ "rewards/rejected": -1.1752225160598755,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.8144675150703282,
1138
+ "grad_norm": 23.976856879448345,
1139
+ "learning_rate": 1.003941418453616e-07,
1140
+ "logits/chosen": -2.9358296394348145,
1141
+ "logits/rejected": -2.9078102111816406,
1142
+ "logps/chosen": -0.9131346940994263,
1143
+ "logps/rejected": -1.0847430229187012,
1144
+ "loss": 1.8614,
1145
+ "rewards/accuracies": 0.6625000238418579,
1146
+ "rewards/chosen": -0.9131346940994263,
1147
+ "rewards/margins": 0.1716083586215973,
1148
+ "rewards/rejected": -1.0847430229187012,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.825184192900201,
1153
+ "grad_norm": 32.2123584818521,
1154
+ "learning_rate": 8.941113222649327e-08,
1155
+ "logits/chosen": -2.8775150775909424,
1156
+ "logits/rejected": -2.842041254043579,
1157
+ "logps/chosen": -1.0087697505950928,
1158
+ "logps/rejected": -1.1664918661117554,
1159
+ "loss": 1.8549,
1160
+ "rewards/accuracies": 0.6937500238418579,
1161
+ "rewards/chosen": -1.0087697505950928,
1162
+ "rewards/margins": 0.15772202610969543,
1163
+ "rewards/rejected": -1.1664918661117554,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.8359008707300737,
1168
+ "grad_norm": 31.35752151311303,
1169
+ "learning_rate": 7.900511224486083e-08,
1170
+ "logits/chosen": -2.8315508365631104,
1171
+ "logits/rejected": -2.801546812057495,
1172
+ "logps/chosen": -1.1222208738327026,
1173
+ "logps/rejected": -1.3023992776870728,
1174
+ "loss": 1.8914,
1175
+ "rewards/accuracies": 0.643750011920929,
1176
+ "rewards/chosen": -1.1222208738327026,
1177
+ "rewards/margins": 0.18017837405204773,
1178
+ "rewards/rejected": -1.3023992776870728,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8466175485599464,
1183
+ "grad_norm": 31.331425662268856,
1184
+ "learning_rate": 6.919070520412768e-08,
1185
+ "logits/chosen": -2.8807644844055176,
1186
+ "logits/rejected": -2.877798080444336,
1187
+ "logps/chosen": -1.002872347831726,
1188
+ "logps/rejected": -1.2327783107757568,
1189
+ "loss": 1.8638,
1190
+ "rewards/accuracies": 0.731249988079071,
1191
+ "rewards/chosen": -1.002872347831726,
1192
+ "rewards/margins": 0.22990599274635315,
1193
+ "rewards/rejected": -1.2327783107757568,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8573342263898192,
1198
+ "grad_norm": 27.689197557194653,
1199
+ "learning_rate": 5.998170302999528e-08,
1200
+ "logits/chosen": -2.866481304168701,
1201
+ "logits/rejected": -2.851442575454712,
1202
+ "logps/chosen": -0.9658647775650024,
1203
+ "logps/rejected": -1.2617170810699463,
1204
+ "loss": 1.8319,
1205
+ "rewards/accuracies": 0.706250011920929,
1206
+ "rewards/chosen": -0.9658647775650024,
1207
+ "rewards/margins": 0.2958524823188782,
1208
+ "rewards/rejected": -1.2617170810699463,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8573342263898192,
1213
+ "eval_logits/chosen": -2.7880678176879883,
1214
+ "eval_logits/rejected": -2.7752296924591064,
1215
+ "eval_logps/chosen": -0.9790560007095337,
1216
+ "eval_logps/rejected": -1.1183466911315918,
1217
+ "eval_loss": 1.8910752534866333,
1218
+ "eval_rewards/accuracies": 0.626329779624939,
1219
+ "eval_rewards/chosen": -0.9790560007095337,
1220
+ "eval_rewards/margins": 0.1392906755208969,
1221
+ "eval_rewards/rejected": -1.1183466911315918,
1222
+ "eval_runtime": 436.0547,
1223
+ "eval_samples_per_second": 6.866,
1224
+ "eval_steps_per_second": 0.431,
1225
+ "step": 400
1226
+ },
1227
+ {
1228
+ "epoch": 0.8680509042196919,
1229
+ "grad_norm": 32.62329228952369,
1230
+ "learning_rate": 5.1391046888775493e-08,
1231
+ "logits/chosen": -2.8493621349334717,
1232
+ "logits/rejected": -2.8683342933654785,
1233
+ "logps/chosen": -0.949614405632019,
1234
+ "logps/rejected": -1.1213003396987915,
1235
+ "loss": 1.8697,
1236
+ "rewards/accuracies": 0.6937500238418579,
1237
+ "rewards/chosen": -0.949614405632019,
1238
+ "rewards/margins": 0.1716858595609665,
1239
+ "rewards/rejected": -1.1213003396987915,
1240
+ "step": 405
1241
+ },
1242
+ {
1243
+ "epoch": 0.8787675820495646,
1244
+ "grad_norm": 25.8354383097588,
1245
+ "learning_rate": 4.343080900151375e-08,
1246
+ "logits/chosen": -2.881870985031128,
1247
+ "logits/rejected": -2.899685859680176,
1248
+ "logps/chosen": -0.9602924585342407,
1249
+ "logps/rejected": -1.1478478908538818,
1250
+ "loss": 1.8356,
1251
+ "rewards/accuracies": 0.65625,
1252
+ "rewards/chosen": -0.9602924585342407,
1253
+ "rewards/margins": 0.1875552237033844,
1254
+ "rewards/rejected": -1.1478478908538818,
1255
+ "step": 410
1256
+ },
1257
+ {
1258
+ "epoch": 0.8894842598794374,
1259
+ "grad_norm": 25.748109045396355,
1260
+ "learning_rate": 3.611217567921709e-08,
1261
+ "logits/chosen": -2.8336663246154785,
1262
+ "logits/rejected": -2.813194513320923,
1263
+ "logps/chosen": -1.000084400177002,
1264
+ "logps/rejected": -1.1840862035751343,
1265
+ "loss": 1.8298,
1266
+ "rewards/accuracies": 0.6875,
1267
+ "rewards/chosen": -1.000084400177002,
1268
+ "rewards/margins": 0.18400196731090546,
1269
+ "rewards/rejected": -1.1840862035751343,
1270
+ "step": 415
1271
+ },
1272
+ {
1273
+ "epoch": 0.9002009377093101,
1274
+ "grad_norm": 32.06643463040125,
1275
+ "learning_rate": 2.944543160302787e-08,
1276
+ "logits/chosen": -2.857529878616333,
1277
+ "logits/rejected": -2.8420491218566895,
1278
+ "logps/chosen": -0.9639240503311157,
1279
+ "logps/rejected": -1.1220653057098389,
1280
+ "loss": 1.8748,
1281
+ "rewards/accuracies": 0.581250011920929,
1282
+ "rewards/chosen": -0.9639240503311157,
1283
+ "rewards/margins": 0.15814124047756195,
1284
+ "rewards/rejected": -1.1220653057098389,
1285
+ "step": 420
1286
+ },
1287
+ {
1288
+ "epoch": 0.9109176155391828,
1289
+ "grad_norm": 35.70189678978648,
1290
+ "learning_rate": 2.343994537143479e-08,
1291
+ "logits/chosen": -2.8647522926330566,
1292
+ "logits/rejected": -2.8519949913024902,
1293
+ "logps/chosen": -0.9895116686820984,
1294
+ "logps/rejected": -1.3003708124160767,
1295
+ "loss": 1.8221,
1296
+ "rewards/accuracies": 0.7250000238418579,
1297
+ "rewards/chosen": -0.9895116686820984,
1298
+ "rewards/margins": 0.31085896492004395,
1299
+ "rewards/rejected": -1.3003708124160767,
1300
+ "step": 425
1301
+ },
1302
+ {
1303
+ "epoch": 0.9216342933690556,
1304
+ "grad_norm": 34.791804330091374,
1305
+ "learning_rate": 1.81041563348297e-08,
1306
+ "logits/chosen": -2.837439775466919,
1307
+ "logits/rejected": -2.818183660507202,
1308
+ "logps/chosen": -1.0866570472717285,
1309
+ "logps/rejected": -1.2705637216567993,
1310
+ "loss": 1.8716,
1311
+ "rewards/accuracies": 0.699999988079071,
1312
+ "rewards/chosen": -1.0866570472717285,
1313
+ "rewards/margins": 0.1839066594839096,
1314
+ "rewards/rejected": -1.2705637216567993,
1315
+ "step": 430
1316
+ },
1317
+ {
1318
+ "epoch": 0.9323509711989283,
1319
+ "grad_norm": 37.275898794915584,
1320
+ "learning_rate": 1.3445562735912962e-08,
1321
+ "logits/chosen": -2.9299168586730957,
1322
+ "logits/rejected": -2.9030609130859375,
1323
+ "logps/chosen": -0.9819711446762085,
1324
+ "logps/rejected": -1.2765450477600098,
1325
+ "loss": 1.8211,
1326
+ "rewards/accuracies": 0.706250011920929,
1327
+ "rewards/chosen": -0.9819711446762085,
1328
+ "rewards/margins": 0.29457393288612366,
1329
+ "rewards/rejected": -1.2765450477600098,
1330
+ "step": 435
1331
+ },
1332
+ {
1333
+ "epoch": 0.943067649028801,
1334
+ "grad_norm": 27.67934081660638,
1335
+ "learning_rate": 9.470711172611722e-09,
1336
+ "logits/chosen": -2.852858066558838,
1337
+ "logits/rejected": -2.8415844440460205,
1338
+ "logps/chosen": -0.9760105013847351,
1339
+ "logps/rejected": -1.2501945495605469,
1340
+ "loss": 1.8076,
1341
+ "rewards/accuracies": 0.6937500238418579,
1342
+ "rewards/chosen": -0.9760105013847351,
1343
+ "rewards/margins": 0.27418413758277893,
1344
+ "rewards/rejected": -1.2501945495605469,
1345
+ "step": 440
1346
+ },
1347
+ {
1348
+ "epoch": 0.9537843268586738,
1349
+ "grad_norm": 31.020987107038604,
1350
+ "learning_rate": 6.185187398319691e-09,
1351
+ "logits/chosen": -2.848702907562256,
1352
+ "logits/rejected": -2.8342273235321045,
1353
+ "logps/chosen": -1.029883623123169,
1354
+ "logps/rejected": -1.24784255027771,
1355
+ "loss": 1.8487,
1356
+ "rewards/accuracies": 0.6812499761581421,
1357
+ "rewards/chosen": -1.029883623123169,
1358
+ "rewards/margins": 0.2179589569568634,
1359
+ "rewards/rejected": -1.24784255027771,
1360
+ "step": 445
1361
+ },
1362
+ {
1363
+ "epoch": 0.9645010046885466,
1364
+ "grad_norm": 30.471294839063304,
1365
+ "learning_rate": 3.593608472386045e-09,
1366
+ "logits/chosen": -2.8422036170959473,
1367
+ "logits/rejected": -2.8164522647857666,
1368
+ "logps/chosen": -0.9777735471725464,
1369
+ "logps/rejected": -1.1690075397491455,
1370
+ "loss": 1.8265,
1371
+ "rewards/accuracies": 0.612500011920929,
1372
+ "rewards/chosen": -0.9777735471725464,
1373
+ "rewards/margins": 0.19123412668704987,
1374
+ "rewards/rejected": -1.1690075397491455,
1375
+ "step": 450
1376
+ },
1377
+ {
1378
+ "epoch": 0.9752176825184193,
1379
+ "grad_norm": 30.36082211778746,
1380
+ "learning_rate": 1.6996162718847518e-09,
1381
+ "logits/chosen": -2.811438798904419,
1382
+ "logits/rejected": -2.8197503089904785,
1383
+ "logps/chosen": -0.9904121160507202,
1384
+ "logps/rejected": -1.257320523262024,
1385
+ "loss": 1.8079,
1386
+ "rewards/accuracies": 0.6812499761581421,
1387
+ "rewards/chosen": -0.9904121160507202,
1388
+ "rewards/margins": 0.2669083774089813,
1389
+ "rewards/rejected": -1.257320523262024,
1390
+ "step": 455
1391
+ },
1392
+ {
1393
+ "epoch": 0.9859343603482921,
1394
+ "grad_norm": 38.11034342674612,
1395
+ "learning_rate": 5.058723737811355e-10,
1396
+ "logits/chosen": -2.829425096511841,
1397
+ "logits/rejected": -2.828883647918701,
1398
+ "logps/chosen": -1.0095789432525635,
1399
+ "logps/rejected": -1.2887779474258423,
1400
+ "loss": 1.8606,
1401
+ "rewards/accuracies": 0.6875,
1402
+ "rewards/chosen": -1.0095789432525635,
1403
+ "rewards/margins": 0.27919891476631165,
1404
+ "rewards/rejected": -1.2887779474258423,
1405
+ "step": 460
1406
+ },
1407
+ {
1408
+ "epoch": 0.9966510381781648,
1409
+ "grad_norm": 31.577486151371264,
1410
+ "learning_rate": 1.405431468848306e-11,
1411
+ "logits/chosen": -2.846008777618408,
1412
+ "logits/rejected": -2.832801580429077,
1413
+ "logps/chosen": -1.0791490077972412,
1414
+ "logps/rejected": -1.249805212020874,
1415
+ "loss": 1.8779,
1416
+ "rewards/accuracies": 0.65625,
1417
+ "rewards/chosen": -1.0791490077972412,
1418
+ "rewards/margins": 0.170656219124794,
1419
+ "rewards/rejected": -1.249805212020874,
1420
+ "step": 465
1421
+ },
1422
+ {
1423
+ "epoch": 0.9987943737441393,
1424
+ "step": 466,
1425
+ "total_flos": 0.0,
1426
+ "train_loss": 1.899593046294773,
1427
+ "train_runtime": 19390.7723,
1428
+ "train_samples_per_second": 3.08,
1429
+ "train_steps_per_second": 0.024
1430
+ }
1431
+ ],
1432
+ "logging_steps": 5,
1433
+ "max_steps": 466,
1434
+ "num_input_tokens_seen": 0,
1435
+ "num_train_epochs": 1,
1436
+ "save_steps": 1000000,
1437
+ "stateful_callbacks": {
1438
+ "TrainerControl": {
1439
+ "args": {
1440
+ "should_epoch_stop": false,
1441
+ "should_evaluate": false,
1442
+ "should_log": false,
1443
+ "should_save": true,
1444
+ "should_training_stop": true
1445
+ },
1446
+ "attributes": {}
1447
+ }
1448
+ },
1449
+ "total_flos": 0.0,
1450
+ "train_batch_size": 2,
1451
+ "trial_name": null,
1452
+ "trial_params": null
1453
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e56140629906a9d4a1a573b5aa246d36f62d134a327ddfd1868226e7fef7fa
3
+ size 7416