Hugging Face's logo

uripper
/
AVA

Text Generation
Transformers
PyTorch
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
1
uripper commited on
Commit
e878194
·
1 Parent(s): 8ac86ed

Updated model

Browse files
Files changed (6) hide show
  1. rng_state.pth +3 -0
  2. scheduler.pt +3 -0
  3. tokenizer.json +2 -2
  4. trainer_state.json +142 -0
  5. training_args.bin +1 -1
  6. vocab.json +0 -0
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488486fdd1b1a0034a39f3e9e3b2054ddc41a4cdf9466c4afe498e8f258003fa
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bceb1f245ca1f9094b4c189b4fdf6422b5a8caeb3b9924c35523a4f67426612
3
+ size 623
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510e560c9624313899b0a23b5a1025c0e5d2ca744868b09210dddf1ef3d37e57
3
- size 16394089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bda4f1ac6dbf09f1aa73e2c1d40dc5c1c9abe00fc5b2f7c354eb0f202871137
3
+ size 14932759
trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.3264334201812744,
3
+ "best_model_checkpoint": "uripper/ReviewTrainingBot/checkpoint-45000",
4
+ "epoch": 1.0144274120829577,
5
+ "global_step": 45000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 0.0009818840579710146,
13
+ "loss": 4.0894,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "eval_loss": 3.8452765941619873,
19
+ "eval_runtime": 381.5421,
20
+ "eval_samples_per_second": 129.184,
21
+ "eval_steps_per_second": 6.461,
22
+ "step": 5000
23
+ },
24
+ {
25
+ "epoch": 0.23,
26
+ "learning_rate": 0.0009592391304347826,
27
+ "loss": 3.7663,
28
+ "step": 10000
29
+ },
30
+ {
31
+ "epoch": 0.23,
32
+ "eval_loss": 3.625126600265503,
33
+ "eval_runtime": 382.09,
34
+ "eval_samples_per_second": 128.998,
35
+ "eval_steps_per_second": 6.451,
36
+ "step": 10000
37
+ },
38
+ {
39
+ "epoch": 0.34,
40
+ "learning_rate": 0.0009365942028985508,
41
+ "loss": 3.6267,
42
+ "step": 15000
43
+ },
44
+ {
45
+ "epoch": 0.34,
46
+ "eval_loss": 3.5167148113250732,
47
+ "eval_runtime": 379.2329,
48
+ "eval_samples_per_second": 129.97,
49
+ "eval_steps_per_second": 6.5,
50
+ "step": 15000
51
+ },
52
+ {
53
+ "epoch": 0.45,
54
+ "learning_rate": 0.0009139492753623188,
55
+ "loss": 3.5371,
56
+ "step": 20000
57
+ },
58
+ {
59
+ "epoch": 0.45,
60
+ "eval_loss": 3.4787251949310303,
61
+ "eval_runtime": 379.8968,
62
+ "eval_samples_per_second": 129.743,
63
+ "eval_steps_per_second": 6.489,
64
+ "step": 20000
65
+ },
66
+ {
67
+ "epoch": 0.56,
68
+ "learning_rate": 0.0008913043478260869,
69
+ "loss": 3.4932,
70
+ "step": 25000
71
+ },
72
+ {
73
+ "epoch": 0.56,
74
+ "eval_loss": 3.4222865104675293,
75
+ "eval_runtime": 380.3957,
76
+ "eval_samples_per_second": 129.573,
77
+ "eval_steps_per_second": 6.48,
78
+ "step": 25000
79
+ },
80
+ {
81
+ "epoch": 0.68,
82
+ "learning_rate": 0.0008686594202898551,
83
+ "loss": 3.4695,
84
+ "step": 30000
85
+ },
86
+ {
87
+ "epoch": 0.68,
88
+ "eval_loss": 3.398277997970581,
89
+ "eval_runtime": 379.1493,
90
+ "eval_samples_per_second": 129.999,
91
+ "eval_steps_per_second": 6.501,
92
+ "step": 30000
93
+ },
94
+ {
95
+ "epoch": 0.79,
96
+ "learning_rate": 0.0008460144927536231,
97
+ "loss": 3.4292,
98
+ "step": 35000
99
+ },
100
+ {
101
+ "epoch": 0.79,
102
+ "eval_loss": 3.3613269329071045,
103
+ "eval_runtime": 379.3995,
104
+ "eval_samples_per_second": 129.913,
105
+ "eval_steps_per_second": 6.497,
106
+ "step": 35000
107
+ },
108
+ {
109
+ "epoch": 0.9,
110
+ "learning_rate": 0.0008233695652173913,
111
+ "loss": 3.401,
112
+ "step": 40000
113
+ },
114
+ {
115
+ "epoch": 0.9,
116
+ "eval_loss": 3.334460973739624,
117
+ "eval_runtime": 380.9663,
118
+ "eval_samples_per_second": 129.379,
119
+ "eval_steps_per_second": 6.47,
120
+ "step": 40000
121
+ },
122
+ {
123
+ "epoch": 1.01,
124
+ "learning_rate": 0.0008007246376811594,
125
+ "loss": 3.3928,
126
+ "step": 45000
127
+ },
128
+ {
129
+ "epoch": 1.01,
130
+ "eval_loss": 3.3264334201812744,
131
+ "eval_runtime": 381.4314,
132
+ "eval_samples_per_second": 129.221,
133
+ "eval_steps_per_second": 6.462,
134
+ "step": 45000
135
+ }
136
+ ],
137
+ "max_steps": 221800,
138
+ "num_train_epochs": 5,
139
+ "total_flos": 9186152646574080.0,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdcb5bab7e2df84176238902483a596eb0b068ab32c9f3ba992175b3971ff3e4
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8525e5ec9879205b268919326fcb3fb922c9ca3dadc3e1ff4d3baaf550967071
3
  size 3311
vocab.json CHANGED
The diff for this file is too large to render. See raw diff