k4black commited on
Commit
ec94fc7
·
1 Parent(s): 870638c

Training in progress, step 10000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3f8e904a7fd900eaadbc06b512420b2cce1e9e454622d76a3fa080070f3e050
3
  size 1135685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcf1e089fce6094a43a6df148dccae971c0758feecdb68eeeb7dc88e615426f
3
  size 1135685
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8ae2563b0e8a25139da34cf6ac4768d4e4242b4cd3c4ac7ca590c4dc920c85b
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f0978cde5847e3dd7ce8a7f7c7c3254251303630f4b6281edb8558cea3d3d29
3
  size 307910149
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:909cc4fa6326c0b3925b658ea002b5681dbb40db16e29a002e73843a5ff1ce21
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40593ea88f5e9169b2d59cd6aa5b2cd985839724b0346e888aae95e4bdf14a75
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0480a19c1bb0f1d4849d6f8498c92440ead5e7dc1264bee4fc839d9a71a6e7c3
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a546360b22b38e65568c028955da704276b3a9551ee9dcac6165cd80d1258c
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 1.7871696949005127,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000",
4
- "epoch": 0.9319664492078286,
5
- "global_step": 8000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -94,11 +94,33 @@
94
  "eval_samples_per_second": 69.169,
95
  "eval_steps_per_second": 1.082,
96
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "max_steps": 85840,
100
  "num_train_epochs": 10,
101
- "total_flos": 1.09605688836096e+16,
102
  "trial_name": null,
103
  "trial_params": null
104
  }
 
1
  {
2
  "best_metric": 1.7871696949005127,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000",
4
+ "epoch": 1.1649580615097856,
5
+ "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 69.169,
95
  "eval_steps_per_second": 1.082,
96
  "step": 8000
97
+ },
98
+ {
99
+ "epoch": 1.16,
100
+ "learning_rate": 0.0009300044145779173,
101
+ "loss": 1.1155,
102
+ "step": 10000
103
+ },
104
+ {
105
+ "epoch": 1.16,
106
+ "eval_accuracy": 0.8695387116439748,
107
+ "eval_bertscore_f1": 0.9330506412037212,
108
+ "eval_bleu": 0.4022160428281426,
109
+ "eval_f1": 0.868816289704145,
110
+ "eval_loss": 1.8499114513397217,
111
+ "eval_rouge1": 0.6082846765097942,
112
+ "eval_rouge2": 0.4018899263767985,
113
+ "eval_rougeL": 0.5518885347721499,
114
+ "eval_rougeLsum": 0.5540212762276107,
115
+ "eval_runtime": 150.2024,
116
+ "eval_samples_per_second": 65.525,
117
+ "eval_steps_per_second": 1.025,
118
+ "step": 10000
119
  }
120
  ],
121
  "max_steps": 85840,
122
  "num_train_epochs": 10,
123
+ "total_flos": 1.3703196663877632e+16,
124
  "trial_name": null,
125
  "trial_params": null
126
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8ae2563b0e8a25139da34cf6ac4768d4e4242b4cd3c4ac7ca590c4dc920c85b
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f0978cde5847e3dd7ce8a7f7c7c3254251303630f4b6281edb8558cea3d3d29
3
  size 307910149