Henk717 commited on
Commit
f9acfa3
1 Parent(s): 87f23e5

Initial Upload

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.451919929750504,
4
+ "train_runtime": 105114.6028,
5
+ "train_samples": 99200,
6
+ "train_samples_per_second": 0.944,
7
+ "train_steps_per_second": 0.118
8
+ }
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-2.7B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local",
33
+ "global",
34
+ "local",
35
+ "global",
36
+ "local",
37
+ "global",
38
+ "local",
39
+ "global",
40
+ "local"
41
+ ],
42
+ "attention_types": [
43
+ [
44
+ [
45
+ "global",
46
+ "local"
47
+ ],
48
+ 16
49
+ ]
50
+ ],
51
+ "bos_token_id": 50256,
52
+ "embed_dropout": 0,
53
+ "eos_token_id": 50256,
54
+ "gradient_checkpointing": true,
55
+ "hidden_size": 2560,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": null,
58
+ "layer_norm_epsilon": 1e-05,
59
+ "max_position_embeddings": 2048,
60
+ "model_type": "gpt_neo",
61
+ "num_heads": 20,
62
+ "num_layers": 32,
63
+ "resid_dropout": 0,
64
+ "summary_activation": null,
65
+ "summary_first_dropout": 0.1,
66
+ "summary_proj_to_labels": true,
67
+ "summary_type": "cls_index",
68
+ "summary_use_proj": true,
69
+ "task_specific_params": {
70
+ "text-generation": {
71
+ "do_sample": true,
72
+ "max_length": 50,
73
+ "temperature": 0.9
74
+ }
75
+ },
76
+ "tokenizer_class": "GPT2Tokenizer",
77
+ "transformers_version": "4.7.0",
78
+ "use_cache": false,
79
+ "vocab_size": 50257,
80
+ "window_size": 256
81
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d1e1858932d9e8035339abcf6434943efb4c599cf48b7dcaf3f8633e324b16
3
+ size 5369795578
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-2.7B", "tokenizer_file": null}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.451919929750504,
4
+ "train_runtime": 105114.6028,
5
+ "train_samples": 99200,
6
+ "train_samples_per_second": 0.944,
7
+ "train_steps_per_second": 0.118
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 12400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 5e-06,
13
+ "loss": 2.5068,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 5e-06,
19
+ "loss": 2.4984,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.12,
24
+ "learning_rate": 5e-06,
25
+ "loss": 2.4857,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.16,
30
+ "learning_rate": 5e-06,
31
+ "loss": 2.4827,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.2,
36
+ "learning_rate": 5e-06,
37
+ "loss": 2.4825,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.24,
42
+ "learning_rate": 5e-06,
43
+ "loss": 2.4707,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.28,
48
+ "learning_rate": 5e-06,
49
+ "loss": 2.4708,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.32,
54
+ "learning_rate": 5e-06,
55
+ "loss": 2.4553,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.36,
60
+ "learning_rate": 5e-06,
61
+ "loss": 2.4716,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.4,
66
+ "learning_rate": 5e-06,
67
+ "loss": 2.4503,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.44,
72
+ "learning_rate": 5e-06,
73
+ "loss": 2.4546,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.48,
78
+ "learning_rate": 5e-06,
79
+ "loss": 2.4485,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.52,
84
+ "learning_rate": 5e-06,
85
+ "loss": 2.4421,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.56,
90
+ "learning_rate": 5e-06,
91
+ "loss": 2.4296,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.6,
96
+ "learning_rate": 5e-06,
97
+ "loss": 2.4372,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.65,
102
+ "learning_rate": 5e-06,
103
+ "loss": 2.4359,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.69,
108
+ "learning_rate": 5e-06,
109
+ "loss": 2.4368,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.73,
114
+ "learning_rate": 5e-06,
115
+ "loss": 2.4307,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.77,
120
+ "learning_rate": 5e-06,
121
+ "loss": 2.4352,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.81,
126
+ "learning_rate": 5e-06,
127
+ "loss": 2.4364,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.85,
132
+ "learning_rate": 5e-06,
133
+ "loss": 2.4279,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.89,
138
+ "learning_rate": 5e-06,
139
+ "loss": 2.4309,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.93,
144
+ "learning_rate": 5e-06,
145
+ "loss": 2.4218,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.97,
150
+ "learning_rate": 5e-06,
151
+ "loss": 2.4255,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.0,
156
+ "step": 12400,
157
+ "total_flos": 3.23186320404906e+18,
158
+ "train_loss": 2.451919929750504,
159
+ "train_runtime": 105114.6028,
160
+ "train_samples_per_second": 0.944,
161
+ "train_steps_per_second": 0.118
162
+ }
163
+ ],
164
+ "max_steps": 12400,
165
+ "num_train_epochs": 1,
166
+ "total_flos": 3.23186320404906e+18,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19ce18086c701c8e16e656b9a99b78a4eccb3ed80a766aa83bc7a5b0bc12b8a
3
+ size 3503
vocab.json ADDED
The diff for this file is too large to render. See raw diff