alvarobartt HF staff commited on
Commit
6f1b2ef
1 Parent(s): 3de5727

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: zephyr-gemma-dpo
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
+ # zephyr-gemma-dpo
17
+
18
+ This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4446
21
+ - Rewards/chosen: -1.7969
22
+ - Rewards/rejected: -3.6406
23
+ - Rewards/accuracies: 0.7447
24
+ - Rewards/margins: 1.8359
25
+ - Logps/rejected: -480.0
26
+ - Logps/chosen: -388.0
27
+ - Logits/rejected: 84.0
28
+ - Logits/chosen: 82.0
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-07
48
+ - train_batch_size: 2
49
+ - eval_batch_size: 4
50
+ - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - num_devices: 4
53
+ - gradient_accumulation_steps: 8
54
+ - total_train_batch_size: 64
55
+ - total_eval_batch_size: 16
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: cosine
58
+ - lr_scheduler_warmup_ratio: 0.1
59
+ - lr_scheduler_warmup_steps: 100
60
+ - num_epochs: 2
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
66
+ | 0.5324 | 0.95 | 100 | 0.4852 | -1.1641 | -2.4688 | 0.7340 | 1.3047 | -456.0 | -376.0 | 94.0 | 92.0 |
67
+ | 0.1822 | 1.9 | 200 | 0.4446 | -1.7969 | -3.6406 | 0.7447 | 1.8359 | -480.0 | -388.0 | 84.0 | 82.0 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.38.0
73
+ - Pytorch 2.1.1+cu121
74
+ - Datasets 2.16.1
75
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.99,
3
+ "train_loss": 0.4030106709116981,
4
+ "train_runtime": 4928.2992,
5
+ "train_samples_per_second": 2.739,
6
+ "train_steps_per_second": 0.043
7
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-gemma-sft-v0.1",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.38.0",
26
+ "use_cache": false,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.0"
7
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6642460db843313f7cc8b840ea1dda693d5a280a860bd9212b523c9096e4c05
3
+ size 4995496656
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2cf4f90a72cedfc036cb993e6712b1e526a545834465e4c3ecd8d7553e656f1
3
+ size 4982953168
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93383b83000884724276b9bef13c55cba22a151fb2452b9cb479518cc2ae3f3b
3
+ size 4982953200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bafa492ded63cd4ab39be3b382d524a4dff27a4f53ca49863763d0c201f9b6e
3
+ size 2113988336
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17075361792
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.norm.weight": "model-00004-of-00004.safetensors"
260
+ }
261
+ }
runs/Mar12_08-51-27_b4ec5bfe1a9b/events.out.tfevents.1710233566.b4ec5bfe1a9b.17558.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a4dc18c256bec257e39b722f9ea86e639736b2c3b6a4b6e0798458b54125e8
3
+ size 21636
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
3
+ size 17477473
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "106": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<|im_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 2048,
64
+ "pad_token": "<pad>",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "tokenizer_class": "GemmaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.99,
3
+ "train_loss": 0.4030106709116981,
4
+ "train_runtime": 4928.2992,
5
+ "train_samples_per_second": 2.739,
6
+ "train_steps_per_second": 0.043
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9905213270142181,
5
+ "eval_steps": 100,
6
+ "global_step": 210,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 177.85299255533252,
14
+ "learning_rate": 5e-09,
15
+ "logits/chosen": 129.0,
16
+ "logits/rejected": 125.5,
17
+ "logps/chosen": -428.0,
18
+ "logps/rejected": -470.0,
19
+ "loss": 0.6914,
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": 0.09,
28
+ "grad_norm": 171.69218216908772,
29
+ "learning_rate": 5e-08,
30
+ "logits/chosen": 125.5,
31
+ "logits/rejected": 133.0,
32
+ "logps/chosen": -414.0,
33
+ "logps/rejected": -448.0,
34
+ "loss": 0.7199,
35
+ "rewards/accuracies": 0.3888888955116272,
36
+ "rewards/chosen": -0.017822265625,
37
+ "rewards/margins": -0.0498046875,
38
+ "rewards/rejected": 0.031982421875,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.19,
43
+ "grad_norm": 180.59129253006714,
44
+ "learning_rate": 1e-07,
45
+ "logits/chosen": 136.0,
46
+ "logits/rejected": 136.0,
47
+ "logps/chosen": -400.0,
48
+ "logps/rejected": -430.0,
49
+ "loss": 0.7187,
50
+ "rewards/accuracies": 0.4437499940395355,
51
+ "rewards/chosen": -0.0242919921875,
52
+ "rewards/margins": -0.02197265625,
53
+ "rewards/rejected": -0.0023956298828125,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.28,
58
+ "grad_norm": 171.658251860157,
59
+ "learning_rate": 1.5e-07,
60
+ "logits/chosen": 130.0,
61
+ "logits/rejected": 130.0,
62
+ "logps/chosen": -374.0,
63
+ "logps/rejected": -388.0,
64
+ "loss": 0.7132,
65
+ "rewards/accuracies": 0.4625000059604645,
66
+ "rewards/chosen": 0.09521484375,
67
+ "rewards/margins": 0.004791259765625,
68
+ "rewards/rejected": 0.09033203125,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.38,
73
+ "grad_norm": 170.37244697891163,
74
+ "learning_rate": 2e-07,
75
+ "logits/chosen": 114.5,
76
+ "logits/rejected": 128.0,
77
+ "logps/chosen": -336.0,
78
+ "logps/rejected": -428.0,
79
+ "loss": 0.659,
80
+ "rewards/accuracies": 0.625,
81
+ "rewards/chosen": 0.30859375,
82
+ "rewards/margins": 0.23828125,
83
+ "rewards/rejected": 0.0712890625,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.47,
88
+ "grad_norm": 156.01063486797565,
89
+ "learning_rate": 2.5e-07,
90
+ "logits/chosen": 124.5,
91
+ "logits/rejected": 124.0,
92
+ "logps/chosen": -372.0,
93
+ "logps/rejected": -388.0,
94
+ "loss": 0.6405,
95
+ "rewards/accuracies": 0.5874999761581421,
96
+ "rewards/chosen": 0.173828125,
97
+ "rewards/margins": 0.318359375,
98
+ "rewards/rejected": -0.14453125,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.57,
103
+ "grad_norm": 191.09116619653446,
104
+ "learning_rate": 3e-07,
105
+ "logits/chosen": 116.0,
106
+ "logits/rejected": 124.0,
107
+ "logps/chosen": -342.0,
108
+ "logps/rejected": -416.0,
109
+ "loss": 0.5833,
110
+ "rewards/accuracies": 0.731249988079071,
111
+ "rewards/chosen": -0.0191650390625,
112
+ "rewards/margins": 0.67578125,
113
+ "rewards/rejected": -0.69140625,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.66,
118
+ "grad_norm": 155.04958273291422,
119
+ "learning_rate": 3.5e-07,
120
+ "logits/chosen": 122.0,
121
+ "logits/rejected": 117.5,
122
+ "logps/chosen": -386.0,
123
+ "logps/rejected": -394.0,
124
+ "loss": 0.5745,
125
+ "rewards/accuracies": 0.7124999761581421,
126
+ "rewards/chosen": -0.09375,
127
+ "rewards/margins": 0.79296875,
128
+ "rewards/rejected": -0.88671875,
129
+ "step": 70
130
+ },
131
+ {
132
+ "epoch": 0.76,
133
+ "grad_norm": 142.1796149100647,
134
+ "learning_rate": 4e-07,
135
+ "logits/chosen": 116.5,
136
+ "logits/rejected": 116.5,
137
+ "logps/chosen": -338.0,
138
+ "logps/rejected": -406.0,
139
+ "loss": 0.537,
140
+ "rewards/accuracies": 0.7562500238418579,
141
+ "rewards/chosen": -0.33203125,
142
+ "rewards/margins": 0.96484375,
143
+ "rewards/rejected": -1.296875,
144
+ "step": 80
145
+ },
146
+ {
147
+ "epoch": 0.85,
148
+ "grad_norm": 199.30217047660693,
149
+ "learning_rate": 4.5e-07,
150
+ "logits/chosen": 130.0,
151
+ "logits/rejected": 132.0,
152
+ "logps/chosen": -412.0,
153
+ "logps/rejected": -444.0,
154
+ "loss": 0.4894,
155
+ "rewards/accuracies": 0.7437499761581421,
156
+ "rewards/chosen": -0.8515625,
157
+ "rewards/margins": 1.0078125,
158
+ "rewards/rejected": -1.859375,
159
+ "step": 90
160
+ },
161
+ {
162
+ "epoch": 0.95,
163
+ "grad_norm": 130.24358680507126,
164
+ "learning_rate": 5e-07,
165
+ "logits/chosen": 117.5,
166
+ "logits/rejected": 126.5,
167
+ "logps/chosen": -392.0,
168
+ "logps/rejected": -490.0,
169
+ "loss": 0.5324,
170
+ "rewards/accuracies": 0.7250000238418579,
171
+ "rewards/chosen": -0.98828125,
172
+ "rewards/margins": 1.2578125,
173
+ "rewards/rejected": -2.25,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.95,
178
+ "eval_logits/chosen": 92.0,
179
+ "eval_logits/rejected": 94.0,
180
+ "eval_logps/chosen": -376.0,
181
+ "eval_logps/rejected": -456.0,
182
+ "eval_loss": 0.4851927161216736,
183
+ "eval_rewards/accuracies": 0.7340425252914429,
184
+ "eval_rewards/chosen": -1.1640625,
185
+ "eval_rewards/margins": 1.3046875,
186
+ "eval_rewards/rejected": -2.46875,
187
+ "eval_runtime": 130.6909,
188
+ "eval_samples_per_second": 5.739,
189
+ "eval_steps_per_second": 0.36,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 1.04,
194
+ "grad_norm": 73.74185148689295,
195
+ "learning_rate": 4.898732434036243e-07,
196
+ "logits/chosen": 119.5,
197
+ "logits/rejected": 114.5,
198
+ "logps/chosen": -406.0,
199
+ "logps/rejected": -458.0,
200
+ "loss": 0.3895,
201
+ "rewards/accuracies": 0.8187500238418579,
202
+ "rewards/chosen": -1.109375,
203
+ "rewards/margins": 1.6953125,
204
+ "rewards/rejected": -2.8125,
205
+ "step": 110
206
+ },
207
+ {
208
+ "epoch": 1.14,
209
+ "grad_norm": 77.9102123166481,
210
+ "learning_rate": 4.603133832077953e-07,
211
+ "logits/chosen": 113.5,
212
+ "logits/rejected": 122.0,
213
+ "logps/chosen": -352.0,
214
+ "logps/rejected": -470.0,
215
+ "loss": 0.2308,
216
+ "rewards/accuracies": 0.918749988079071,
217
+ "rewards/chosen": -0.04150390625,
218
+ "rewards/margins": 2.859375,
219
+ "rewards/rejected": -2.90625,
220
+ "step": 120
221
+ },
222
+ {
223
+ "epoch": 1.23,
224
+ "grad_norm": 72.1155658512914,
225
+ "learning_rate": 4.137151834863213e-07,
226
+ "logits/chosen": 107.0,
227
+ "logits/rejected": 108.5,
228
+ "logps/chosen": -392.0,
229
+ "logps/rejected": -462.0,
230
+ "loss": 0.2175,
231
+ "rewards/accuracies": 0.949999988079071,
232
+ "rewards/chosen": -0.68359375,
233
+ "rewards/margins": 2.796875,
234
+ "rewards/rejected": -3.46875,
235
+ "step": 130
236
+ },
237
+ {
238
+ "epoch": 1.33,
239
+ "grad_norm": 83.89189869364462,
240
+ "learning_rate": 3.5385375325047163e-07,
241
+ "logits/chosen": 116.0,
242
+ "logits/rejected": 123.0,
243
+ "logps/chosen": -396.0,
244
+ "logps/rejected": -510.0,
245
+ "loss": 0.2066,
246
+ "rewards/accuracies": 0.9312499761581421,
247
+ "rewards/chosen": -1.6875,
248
+ "rewards/margins": 2.796875,
249
+ "rewards/rejected": -4.46875,
250
+ "step": 140
251
+ },
252
+ {
253
+ "epoch": 1.42,
254
+ "grad_norm": 67.05775374408921,
255
+ "learning_rate": 2.8557870956832133e-07,
256
+ "logits/chosen": 104.5,
257
+ "logits/rejected": 107.5,
258
+ "logps/chosen": -390.0,
259
+ "logps/rejected": -490.0,
260
+ "loss": 0.1569,
261
+ "rewards/accuracies": 0.9312499761581421,
262
+ "rewards/chosen": -1.484375,
263
+ "rewards/margins": 3.25,
264
+ "rewards/rejected": -4.71875,
265
+ "step": 150
266
+ },
267
+ {
268
+ "epoch": 1.52,
269
+ "grad_norm": 91.02831609820949,
270
+ "learning_rate": 2.1442129043167873e-07,
271
+ "logits/chosen": 101.5,
272
+ "logits/rejected": 121.0,
273
+ "logps/chosen": -394.0,
274
+ "logps/rejected": -506.0,
275
+ "loss": 0.1956,
276
+ "rewards/accuracies": 0.918749988079071,
277
+ "rewards/chosen": -1.28125,
278
+ "rewards/margins": 3.671875,
279
+ "rewards/rejected": -4.9375,
280
+ "step": 160
281
+ },
282
+ {
283
+ "epoch": 1.61,
284
+ "grad_norm": 78.82758233414538,
285
+ "learning_rate": 1.461462467495284e-07,
286
+ "logits/chosen": 109.5,
287
+ "logits/rejected": 110.5,
288
+ "logps/chosen": -406.0,
289
+ "logps/rejected": -476.0,
290
+ "loss": 0.1575,
291
+ "rewards/accuracies": 0.956250011920929,
292
+ "rewards/chosen": -0.9375,
293
+ "rewards/margins": 3.484375,
294
+ "rewards/rejected": -4.4375,
295
+ "step": 170
296
+ },
297
+ {
298
+ "epoch": 1.71,
299
+ "grad_norm": 95.52959889189601,
300
+ "learning_rate": 8.628481651367875e-08,
301
+ "logits/chosen": 105.0,
302
+ "logits/rejected": 117.0,
303
+ "logps/chosen": -406.0,
304
+ "logps/rejected": -536.0,
305
+ "loss": 0.1574,
306
+ "rewards/accuracies": 0.9624999761581421,
307
+ "rewards/chosen": -0.83203125,
308
+ "rewards/margins": 3.3125,
309
+ "rewards/rejected": -4.15625,
310
+ "step": 180
311
+ },
312
+ {
313
+ "epoch": 1.8,
314
+ "grad_norm": 67.11817234106277,
315
+ "learning_rate": 3.968661679220467e-08,
316
+ "logits/chosen": 114.0,
317
+ "logits/rejected": 115.0,
318
+ "logps/chosen": -414.0,
319
+ "logps/rejected": -512.0,
320
+ "loss": 0.1866,
321
+ "rewards/accuracies": 0.918749988079071,
322
+ "rewards/chosen": -0.8125,
323
+ "rewards/margins": 3.5625,
324
+ "rewards/rejected": -4.375,
325
+ "step": 190
326
+ },
327
+ {
328
+ "epoch": 1.9,
329
+ "grad_norm": 83.00810869226768,
330
+ "learning_rate": 1.0126756596375685e-08,
331
+ "logits/chosen": 96.5,
332
+ "logits/rejected": 104.0,
333
+ "logps/chosen": -384.0,
334
+ "logps/rejected": -464.0,
335
+ "loss": 0.1822,
336
+ "rewards/accuracies": 0.887499988079071,
337
+ "rewards/chosen": -1.265625,
338
+ "rewards/margins": 3.125,
339
+ "rewards/rejected": -4.375,
340
+ "step": 200
341
+ },
342
+ {
343
+ "epoch": 1.9,
344
+ "eval_logits/chosen": 82.0,
345
+ "eval_logits/rejected": 84.0,
346
+ "eval_logps/chosen": -388.0,
347
+ "eval_logps/rejected": -480.0,
348
+ "eval_loss": 0.4446233808994293,
349
+ "eval_rewards/accuracies": 0.7446808218955994,
350
+ "eval_rewards/chosen": -1.796875,
351
+ "eval_rewards/margins": 1.8359375,
352
+ "eval_rewards/rejected": -3.640625,
353
+ "eval_runtime": 133.5481,
354
+ "eval_samples_per_second": 5.616,
355
+ "eval_steps_per_second": 0.352,
356
+ "step": 200
357
+ },
358
+ {
359
+ "epoch": 1.99,
360
+ "grad_norm": 47.68700617963266,
361
+ "learning_rate": 0.0,
362
+ "logits/chosen": 96.5,
363
+ "logits/rejected": 98.5,
364
+ "logps/chosen": -390.0,
365
+ "logps/rejected": -446.0,
366
+ "loss": 0.2176,
367
+ "rewards/accuracies": 0.918749988079071,
368
+ "rewards/chosen": -1.140625,
369
+ "rewards/margins": 3.125,
370
+ "rewards/rejected": -4.28125,
371
+ "step": 210
372
+ },
373
+ {
374
+ "epoch": 1.99,
375
+ "step": 210,
376
+ "total_flos": 0.0,
377
+ "train_loss": 0.4030106709116981,
378
+ "train_runtime": 4928.2992,
379
+ "train_samples_per_second": 2.739,
380
+ "train_steps_per_second": 0.043
381
+ }
382
+ ],
383
+ "logging_steps": 10,
384
+ "max_steps": 210,
385
+ "num_input_tokens_seen": 0,
386
+ "num_train_epochs": 2,
387
+ "save_steps": 500,
388
+ "total_flos": 0.0,
389
+ "train_batch_size": 2,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415c6c4092ee1d61560d4142eb0d813f20c24faed870580c52ff4f0a7b9abb49
3
+ size 6136