BramVanroy commited on
Commit
394b5d5
1 Parent(s): aabeff7

Model save

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: BramVanroy/fietje-2b-sft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: fietje-2b-dpo-lr2.0e-6-beta0.2-gradaccum2-v6
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
+ # fietje-2b-dpo-lr2.0e-6-beta0.2-gradaccum2-v6
17
+
18
+ This model is a fine-tuned version of [BramVanroy/fietje-2b-sft](https://huggingface.co/BramVanroy/fietje-2b-sft) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2842
21
+ - Rewards/chosen: -1.1549
22
+ - Rewards/rejected: -3.6363
23
+ - Rewards/accuracies: 0.8867
24
+ - Rewards/margins: 2.4815
25
+ - Logps/rejected: -657.6813
26
+ - Logps/chosen: -451.3364
27
+ - Logits/rejected: -1.2868
28
+ - Logits/chosen: -1.3528
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: 2e-06
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 4
50
+ - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - gradient_accumulation_steps: 2
53
+ - total_train_batch_size: 16
54
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
55
+ - lr_scheduler_type: cosine
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 1.0
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.2515 | 1.0 | 1166 | 0.2842 | -1.1549 | -3.6363 | 0.8867 | 2.4815 | -657.6813 | -451.3364 | -1.2868 | -1.3528 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.39.1
69
+ - Pytorch 2.1.2+cu121
70
+ - Datasets 2.18.0
71
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.3634731802597361,
4
+ "train_runtime": 16591.2723,
5
+ "train_samples": 18653,
6
+ "train_samples_per_second": 1.124,
7
+ "train_steps_per_second": 0.07
8
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50295,
4
+ "eos_token_id": 50296,
5
+ "pad_token_id": 50296,
6
+ "transformers_version": "4.39.1"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e738b079913369d46164d298ea2383ae644e637d2874c03ab2e5712c151010
3
+ size 4990961488
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbbe7ec19b53a1fa62bc73fc61c14dd39fd30b1ee3c15d07aa9b47fdd8085443
3
+ size 559207842
model.safetensors.index.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5550119154
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00002-of-00002.safetensors",
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
10
+ "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
94
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
108
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
118
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
130
+ "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
132
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
142
+ "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
154
+ "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
156
+ "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
166
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
168
+ "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
178
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
180
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
190
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
192
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
202
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
214
+ "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
226
+ "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
228
+ "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
+ "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
+ "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
252
+ "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
262
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
264
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
276
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
280
+ "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
286
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
298
+ "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
300
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
304
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
310
+ "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
312
+ "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
316
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
322
+ "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
324
+ "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
326
+ "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
328
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
334
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
336
+ "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
338
+ "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
340
+ "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
346
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
348
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
356
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
358
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
360
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
368
+ "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
370
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
374
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
382
+ "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
394
+ "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
396
+ "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
406
+ "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
408
+ "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
448
+ "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
459
+ }
460
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.3634731802597361,
4
+ "train_runtime": 16591.2723,
5
+ "train_samples": 18653,
6
+ "train_samples_per_second": 1.124,
7
+ "train_steps_per_second": 0.07
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff