Hugging Face's logo

alex2awesome
/
source-exploration__quote-attribution__gpt-neo-2.7

Text Generation
Transformers
PyTorch
gpt_neo
Model card Files Community
1
alex2awesome commited on
Commit
bf57257
·
1 Parent(s): f9d8fd4

model trained with deepspeed 2

Browse files
Files changed (6) hide show
  1. all_results.json +8 -0
  2. config.json +82 -0
  3. pytorch_model.bin +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +169 -0
  6. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.3908403631165627,
4
+ "train_runtime": 5877.8179,
5
+ "train_samples": 8277,
6
+ "train_samples_per_second": 4.225,
7
+ "train_steps_per_second": 2.113
8
+ }
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
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
+ "torch_dtype": "float16",
78
+ "transformers_version": "4.25.1",
79
+ "use_cache": true,
80
+ "vocab_size": 50257,
81
+ "window_size": 256
82
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72318149dec2476f6df4a5d1936d282ed1f8342139bb26b8079453084ecc6a0
3
+ size 5436986151
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.3908403631165627,
4
+ "train_runtime": 5877.8179,
5
+ "train_samples": 8277,
6
+ "train_samples_per_second": 4.225,
7
+ "train_steps_per_second": 2.113
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 12417,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.12,
12
+ "learning_rate": 5e-05,
13
+ "loss": 1.3449,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.24,
18
+ "learning_rate": 5e-05,
19
+ "loss": 0.7563,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.36,
24
+ "learning_rate": 5e-05,
25
+ "loss": 0.6765,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.48,
30
+ "learning_rate": 5e-05,
31
+ "loss": 0.6569,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.6,
36
+ "learning_rate": 5e-05,
37
+ "loss": 0.6397,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.72,
42
+ "learning_rate": 5e-05,
43
+ "loss": 0.699,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.85,
48
+ "learning_rate": 5e-05,
49
+ "loss": 0.7582,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.97,
54
+ "learning_rate": 5e-05,
55
+ "loss": 0.7195,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.09,
60
+ "learning_rate": 5e-05,
61
+ "loss": 0.7019,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.21,
66
+ "learning_rate": 5e-05,
67
+ "loss": 0.7357,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.33,
72
+ "learning_rate": 5e-05,
73
+ "loss": 0.9785,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.45,
78
+ "learning_rate": 5e-05,
79
+ "loss": 1.0095,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.57,
84
+ "learning_rate": 5e-05,
85
+ "loss": 0.8665,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.69,
90
+ "learning_rate": 5e-05,
91
+ "loss": 1.0729,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.81,
96
+ "learning_rate": 5e-05,
97
+ "loss": 1.0456,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.93,
102
+ "learning_rate": 5e-05,
103
+ "loss": 1.2755,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.05,
108
+ "learning_rate": 5e-05,
109
+ "loss": 1.3613,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 2.17,
114
+ "learning_rate": 5e-05,
115
+ "loss": 1.6865,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 2.3,
120
+ "learning_rate": 5e-05,
121
+ "loss": 2.7641,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 2.42,
126
+ "learning_rate": 5e-05,
127
+ "loss": 3.1421,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 2.54,
132
+ "learning_rate": 5e-05,
133
+ "loss": 3.5798,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 2.66,
138
+ "learning_rate": 5e-05,
139
+ "loss": 3.576,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.78,
144
+ "learning_rate": 5e-05,
145
+ "loss": 3.6311,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.9,
150
+ "learning_rate": 5e-05,
151
+ "loss": 3.7422,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 3.0,
156
+ "step": 12417,
157
+ "total_flos": 3.9972132497024614e+17,
158
+ "train_loss": 1.3908403631165627,
159
+ "train_runtime": 5877.8179,
160
+ "train_samples_per_second": 4.225,
161
+ "train_steps_per_second": 2.113
162
+ }
163
+ ],
164
+ "max_steps": 12417,
165
+ "num_train_epochs": 3,
166
+ "total_flos": 3.9972132497024614e+17,
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:fa6ba15f43834d5a4d3a9b0c309b3b865f21be6521fa90f4891b1ec2da605120
3
+ size 4463