Hugging Face's logo

sara-nabhani
/
ltp-roberta-large-defaultltp-roberta-large-default-0

Text Classification
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
sara-nabhani commited on
Commit
9ab49ae
·
1 Parent(s): 5229d0e

Training in progress, step 800

Browse files
Files changed (6) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +2 -2
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +116 -5
  6. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f6ab4f5ab496647bd725d368b62f9262efa69dfbf88faa37d634f8baacd29f8
3
  size 2843370360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bbc7079009dcb015a118d176ee96ef3fa9f81f5e32596bd48e471250f7cd019
3
  size 2843370360
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c46f7008e814a57fd863fe4d6b32b204d12bc103e89a9e029c1ec3761a9e6684
3
  size 1421660981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d9a7aedcce194e7334bb3ff1bbd48d5ae2a679ca306c2690cc2f3503f52f78
3
  size 1421660981
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19f993d576aad282362d3ca490d6b3442b5e729ea10296bb1d19b837eadc6c8f
3
- size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cb7810664b13600938b962e95e12c94aaeb9d2b88cf011246a5ed3f6f5583d
3
+ size 14639
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8636707e906db799535a0e24d8b11f4682008d2f9dce23ea4add566cf191f0eb
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31560d2c60ddf21d021e78a5d14bba7dc363334c5f64fc9eb49d0b82d96fc2a
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.14004634931160595,
3
- "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-0/checkpoint-200",
4
- "epoch": 1.183431952662722,
5
- "global_step": 200,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -43,11 +43,122 @@
43
  "eval_samples_per_second": 500.363,
44
  "eval_steps_per_second": 15.834,
45
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  }
47
  ],
48
  "max_steps": 1690,
49
  "num_train_epochs": 10,
50
- "total_flos": 1089807110512800.0,
51
  "trial_name": null,
52
  "trial_params": null
53
  }
 
1
  {
2
+ "best_metric": 0.35946421270983664,
3
+ "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-0/checkpoint-800",
4
+ "epoch": 4.733727810650888,
5
+ "global_step": 800,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
43
  "eval_samples_per_second": 500.363,
44
  "eval_steps_per_second": 15.834,
45
  "step": 200
46
+ },
47
+ {
48
+ "epoch": 2.37,
49
+ "learning_rate": 8.037383177570094e-06,
50
+ "loss": 0.3303,
51
+ "step": 400
52
+ },
53
+ {
54
+ "epoch": 2.37,
55
+ "eval_f1": 0.26419617591690636,
56
+ "eval_f1_all": [
57
+ 0.43804034582132567,
58
+ 0.31333333333333335,
59
+ 0.0,
60
+ 0.0,
61
+ 0.616,
62
+ 0.03592814371257485,
63
+ 0.3128491620111732,
64
+ 0.0,
65
+ 0.7331058020477816,
66
+ 0.5398601398601399,
67
+ 0.16580310880829016,
68
+ 0.391025641025641,
69
+ 0.0,
70
+ 0.0,
71
+ 0.13119533527696794,
72
+ 0.0,
73
+ 0.6373056994818653,
74
+ 0.6169154228855722,
75
+ 0.02643171806167401,
76
+ 0.32612966601178783
77
+ ],
78
+ "eval_loss": 0.32742321491241455,
79
+ "eval_runtime": 3.2193,
80
+ "eval_samples_per_second": 588.954,
81
+ "eval_steps_per_second": 18.638,
82
+ "step": 400
83
+ },
84
+ {
85
+ "epoch": 3.55,
86
+ "learning_rate": 6.791277258566978e-06,
87
+ "loss": 0.2955,
88
+ "step": 600
89
+ },
90
+ {
91
+ "epoch": 3.55,
92
+ "eval_f1": 0.33856925982901875,
93
+ "eval_f1_all": [
94
+ 0.5025125628140703,
95
+ 0.5899632802937577,
96
+ 0.0,
97
+ 0.07407407407407407,
98
+ 0.6084275436793423,
99
+ 0.0588235294117647,
100
+ 0.3567567567567568,
101
+ 0.0,
102
+ 0.7440944881889764,
103
+ 0.6120481927710844,
104
+ 0.3916666666666666,
105
+ 0.49431818181818177,
106
+ 0.0,
107
+ 0.015625,
108
+ 0.5071868583162218,
109
+ 0.06382978723404255,
110
+ 0.6857597454256166,
111
+ 0.6403940886699507,
112
+ 0.10526315789473682,
113
+ 0.3206412825651303
114
+ ],
115
+ "eval_loss": 0.31045234203338623,
116
+ "eval_runtime": 3.1516,
117
+ "eval_samples_per_second": 601.599,
118
+ "eval_steps_per_second": 19.038,
119
+ "step": 600
120
+ },
121
+ {
122
+ "epoch": 4.73,
123
+ "learning_rate": 5.545171339563863e-06,
124
+ "loss": 0.275,
125
+ "step": 800
126
+ },
127
+ {
128
+ "epoch": 4.73,
129
+ "eval_f1": 0.35946421270983664,
130
+ "eval_f1_all": [
131
+ 0.5432692307692307,
132
+ 0.5728770595690748,
133
+ 0.055944055944055944,
134
+ 0.125,
135
+ 0.6434782608695652,
136
+ 0.11891891891891894,
137
+ 0.33513513513513515,
138
+ 0.0,
139
+ 0.7636594663278272,
140
+ 0.638655462184874,
141
+ 0.41071428571428564,
142
+ 0.5251396648044693,
143
+ 0.0,
144
+ 0.015503875968992248,
145
+ 0.5346733668341709,
146
+ 0.07017543859649122,
147
+ 0.657762938230384,
148
+ 0.6666666666666667,
149
+ 0.11244979919678717,
150
+ 0.39926062846580407
151
+ ],
152
+ "eval_loss": 0.3056282103061676,
153
+ "eval_runtime": 3.1101,
154
+ "eval_samples_per_second": 609.632,
155
+ "eval_steps_per_second": 19.292,
156
+ "step": 800
157
  }
158
  ],
159
  "max_steps": 1690,
160
  "num_train_epochs": 10,
161
+ "total_flos": 4392119246594136.0,
162
  "trial_name": null,
163
  "trial_params": null
164
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c46f7008e814a57fd863fe4d6b32b204d12bc103e89a9e029c1ec3761a9e6684
3
  size 1421660981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d9a7aedcce194e7334bb3ff1bbd48d5ae2a679ca306c2690cc2f3503f52f78
3
  size 1421660981