ErfanMoosaviMonazzah
commited on
Commit
•
a066a32
1
Parent(s):
46a22a6
Upload 11 files
Browse files- config.json +1 -1
- optimizer.pt +3 -0
- pytorch_model.bin +1 -1
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +6 -1
- tokenizer_config.json +0 -1
- trainer_state.json +121 -0
- training_args.bin +3 -0
config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"position_embedding_type": "absolute",
|
20 |
"problem_type": "single_label_classification",
|
21 |
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
|
|
19 |
"position_embedding_type": "absolute",
|
20 |
"problem_type": "single_label_classification",
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.27.2",
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a143a74d23082f1f82a2e41ac22b1a793980ecd3231eda3e9173249c324df3
|
3 |
+
size 35113239
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17562607
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e68c6361918fc640e3bf2681c16f3c19135b3345e59ebbc8adae5d4d9294ea1
|
3 |
size 17562607
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68f058b8e93c1324dbf85d44fdc4366391103496f3ace80bdb0a4e77cf714b27
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d263d8bdf12f1cc9b949bbab432258ae5a64387694fede8f79b989437b7c1928
|
3 |
+
size 627
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -4,7 +4,6 @@
|
|
4 |
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
-
"name_or_path": "prajjwal1/bert-tiny",
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
|
|
4 |
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
|
|
7 |
"never_split": null,
|
8 |
"pad_token": "[PAD]",
|
9 |
"sep_token": "[SEP]",
|
trainer_state.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 3750,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.13,
|
12 |
+
"learning_rate": 4.3333333333333334e-05,
|
13 |
+
"loss": 0.2385,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.14,
|
18 |
+
"eval_f1": 0.9824900538642076,
|
19 |
+
"eval_loss": 0.06151168420910835,
|
20 |
+
"eval_runtime": 19.4562,
|
21 |
+
"eval_samples_per_second": 308.386,
|
22 |
+
"eval_steps_per_second": 38.548,
|
23 |
+
"step": 512
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.27,
|
27 |
+
"learning_rate": 3.6666666666666666e-05,
|
28 |
+
"loss": 0.071,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.27,
|
33 |
+
"eval_f1": 0.9883248221286651,
|
34 |
+
"eval_loss": 0.047542937099933624,
|
35 |
+
"eval_runtime": 7.5074,
|
36 |
+
"eval_samples_per_second": 799.21,
|
37 |
+
"eval_steps_per_second": 99.901,
|
38 |
+
"step": 1024
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.4,
|
42 |
+
"learning_rate": 3e-05,
|
43 |
+
"loss": 0.0659,
|
44 |
+
"step": 1500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.41,
|
48 |
+
"eval_f1": 0.9906601900273291,
|
49 |
+
"eval_loss": 0.04389449208974838,
|
50 |
+
"eval_runtime": 6.6018,
|
51 |
+
"eval_samples_per_second": 908.837,
|
52 |
+
"eval_steps_per_second": 113.605,
|
53 |
+
"step": 1536
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.53,
|
57 |
+
"learning_rate": 2.3333333333333336e-05,
|
58 |
+
"loss": 0.0679,
|
59 |
+
"step": 2000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.55,
|
63 |
+
"eval_f1": 0.9919927935141627,
|
64 |
+
"eval_loss": 0.03968248888850212,
|
65 |
+
"eval_runtime": 8.8193,
|
66 |
+
"eval_samples_per_second": 680.326,
|
67 |
+
"eval_steps_per_second": 85.041,
|
68 |
+
"step": 2048
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.67,
|
72 |
+
"learning_rate": 1.6666666666666667e-05,
|
73 |
+
"loss": 0.0414,
|
74 |
+
"step": 2500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.68,
|
78 |
+
"eval_f1": 0.9909945206661297,
|
79 |
+
"eval_loss": 0.044602639973163605,
|
80 |
+
"eval_runtime": 6.4726,
|
81 |
+
"eval_samples_per_second": 926.979,
|
82 |
+
"eval_steps_per_second": 115.872,
|
83 |
+
"step": 2560
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.8,
|
87 |
+
"learning_rate": 1e-05,
|
88 |
+
"loss": 0.0447,
|
89 |
+
"step": 3000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.82,
|
93 |
+
"eval_f1": 0.9926591496358939,
|
94 |
+
"eval_loss": 0.037685297429561615,
|
95 |
+
"eval_runtime": 7.0088,
|
96 |
+
"eval_samples_per_second": 856.061,
|
97 |
+
"eval_steps_per_second": 107.008,
|
98 |
+
"step": 3072
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.93,
|
102 |
+
"learning_rate": 3.3333333333333333e-06,
|
103 |
+
"loss": 0.0427,
|
104 |
+
"step": 3500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.96,
|
108 |
+
"eval_f1": 0.9923271737589343,
|
109 |
+
"eval_loss": 0.03635118156671524,
|
110 |
+
"eval_runtime": 8.2324,
|
111 |
+
"eval_samples_per_second": 728.825,
|
112 |
+
"eval_steps_per_second": 91.103,
|
113 |
+
"step": 3584
|
114 |
+
}
|
115 |
+
],
|
116 |
+
"max_steps": 3750,
|
117 |
+
"num_train_epochs": 1,
|
118 |
+
"total_flos": 38061091933440.0,
|
119 |
+
"trial_name": null,
|
120 |
+
"trial_params": null
|
121 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ce0b43e9ca61e7d5315b5924ce3aeee8306761553caebc433ec12aded44e211
|
3 |
+
size 3515
|