houck2040 commited on
Commit
b97c753
·
1 Parent(s): 834050a

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.29.2",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.29.2"
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6d9c90e2feb552e7d5089888871f3f4c0c1f5aafe8b1b756084f8cd3687d1d
3
+ size 655345093
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912b89916af1fb9d6d2263e822dd3e1b13199dfd7102086cee706f6cfe0aa7ef
3
+ size 333970169
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2c6c5856cd066b97ae2f121f69a46613b785f766c2967a685e508ab4e17858
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afeed9f2b045b3489c8fba7c4a75372ef933bfc65534bba826bbeaafc70fa4d
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.959422903516682,
5
+ "global_step": 11000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.23,
12
+ "learning_rate": 1.909828674481515e-05,
13
+ "loss": 2.3025,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.45,
18
+ "learning_rate": 1.81965734896303e-05,
19
+ "loss": 1.9624,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.68,
24
+ "learning_rate": 1.729486023444545e-05,
25
+ "loss": 1.8381,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.9,
30
+ "learning_rate": 1.6393146979260597e-05,
31
+ "loss": 1.7487,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "eval_loss": 1.6010558605194092,
37
+ "eval_runtime": 7.739,
38
+ "eval_samples_per_second": 1142.27,
39
+ "eval_steps_per_second": 142.784,
40
+ "step": 2218
41
+ },
42
+ {
43
+ "epoch": 1.13,
44
+ "learning_rate": 1.5491433724075746e-05,
45
+ "loss": 1.699,
46
+ "step": 2500
47
+ },
48
+ {
49
+ "epoch": 1.35,
50
+ "learning_rate": 1.4589720468890894e-05,
51
+ "loss": 1.657,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 1.58,
56
+ "learning_rate": 1.3688007213706042e-05,
57
+ "loss": 1.6196,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 1.8,
62
+ "learning_rate": 1.2786293958521191e-05,
63
+ "loss": 1.5819,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "eval_loss": 1.468666672706604,
69
+ "eval_runtime": 8.211,
70
+ "eval_samples_per_second": 1076.611,
71
+ "eval_steps_per_second": 134.576,
72
+ "step": 4436
73
+ },
74
+ {
75
+ "epoch": 2.03,
76
+ "learning_rate": 1.1884580703336339e-05,
77
+ "loss": 1.562,
78
+ "step": 4500
79
+ },
80
+ {
81
+ "epoch": 2.25,
82
+ "learning_rate": 1.098286744815149e-05,
83
+ "loss": 1.54,
84
+ "step": 5000
85
+ },
86
+ {
87
+ "epoch": 2.48,
88
+ "learning_rate": 1.0081154192966638e-05,
89
+ "loss": 1.5266,
90
+ "step": 5500
91
+ },
92
+ {
93
+ "epoch": 2.71,
94
+ "learning_rate": 9.179440937781785e-06,
95
+ "loss": 1.5093,
96
+ "step": 6000
97
+ },
98
+ {
99
+ "epoch": 2.93,
100
+ "learning_rate": 8.277727682596934e-06,
101
+ "loss": 1.4967,
102
+ "step": 6500
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "eval_loss": 1.411802887916565,
107
+ "eval_runtime": 8.223,
108
+ "eval_samples_per_second": 1075.038,
109
+ "eval_steps_per_second": 134.38,
110
+ "step": 6654
111
+ },
112
+ {
113
+ "epoch": 3.16,
114
+ "learning_rate": 7.376014427412083e-06,
115
+ "loss": 1.4714,
116
+ "step": 7000
117
+ },
118
+ {
119
+ "epoch": 3.38,
120
+ "learning_rate": 6.474301172227232e-06,
121
+ "loss": 1.4786,
122
+ "step": 7500
123
+ },
124
+ {
125
+ "epoch": 3.61,
126
+ "learning_rate": 5.572587917042381e-06,
127
+ "loss": 1.4602,
128
+ "step": 8000
129
+ },
130
+ {
131
+ "epoch": 3.83,
132
+ "learning_rate": 4.670874661857529e-06,
133
+ "loss": 1.4769,
134
+ "step": 8500
135
+ },
136
+ {
137
+ "epoch": 4.0,
138
+ "eval_loss": 1.383550763130188,
139
+ "eval_runtime": 8.2365,
140
+ "eval_samples_per_second": 1073.27,
141
+ "eval_steps_per_second": 134.159,
142
+ "step": 8872
143
+ },
144
+ {
145
+ "epoch": 4.06,
146
+ "learning_rate": 3.7691614066726782e-06,
147
+ "loss": 1.441,
148
+ "step": 9000
149
+ },
150
+ {
151
+ "epoch": 4.28,
152
+ "learning_rate": 2.867448151487827e-06,
153
+ "loss": 1.4561,
154
+ "step": 9500
155
+ },
156
+ {
157
+ "epoch": 4.51,
158
+ "learning_rate": 1.9657348963029757e-06,
159
+ "loss": 1.4494,
160
+ "step": 10000
161
+ },
162
+ {
163
+ "epoch": 4.73,
164
+ "learning_rate": 1.0640216411181244e-06,
165
+ "loss": 1.4381,
166
+ "step": 10500
167
+ },
168
+ {
169
+ "epoch": 4.96,
170
+ "learning_rate": 1.6230838593327323e-07,
171
+ "loss": 1.4314,
172
+ "step": 11000
173
+ }
174
+ ],
175
+ "max_steps": 11090,
176
+ "num_train_epochs": 5,
177
+ "total_flos": 561354220339200.0,
178
+ "trial_name": null,
179
+ "trial_params": null
180
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7ed286e14a875d25b978fbc2aa103973ac23082ca77e802dd860d00690d8b9
3
+ size 3899