jmmr-8282 commited on
Commit
27529f0
·
verified ·
1 Parent(s): e559b70

Training in progress, epoch 10, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f4cc7036bbe3eb19a9cb43cb00f5785a10cdae3ef99febc6f661f8c5593af1b
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b66535ff6415d2c31921f3fe356b0fac561719725dcb426dd1c3a9773e770c5
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee57f4f9262590166ddc036d3825a8fa725dc076f622c715f90c0dd36495f28b
3
  size 4741923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45e4c9cef7b3d793962401a30cc5375b49e5f6fa7d66e64cc389d199fe8102b
3
  size 4741923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a5407a226aede66621a46e9e3803054ef849d6962b19577466fcc75f353f7e7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2e8413b53592d1e0dd4c602cd67bd1e7cb9a9ee96e69486272827e44496b7a
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca329d0121eb88fe2de990ee1c585235458116e02e705a26797da379cee59d3b
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd34198e30d2e33cdb497643e8b4ce22778c6cc08096a422300c51708bdf5a02
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f40a58d9271666cc41b4d88aaf9d64d6a4437482f5f5cb6e83be5d91903b984c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695b5daec62904ea9fe48fd42c554ece0bc33b8a351b379641efd77afed9c35f
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4203,
3
- "best_metric": 0.4572421610355377,
4
- "best_model_checkpoint": "./bert-email/checkpoint-4203",
5
- "epoch": 9.0,
6
  "eval_steps": 500,
7
- "global_step": 4203,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -136,6 +136,21 @@
136
  "eval_samples_per_second": 55.845,
137
  "eval_steps_per_second": 1.752,
138
  "step": 4203
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
  }
140
  ],
141
  "logging_steps": 500,
@@ -150,12 +165,12 @@
150
  "should_evaluate": false,
151
  "should_log": false,
152
  "should_save": true,
153
- "should_training_stop": false
154
  },
155
  "attributes": {}
156
  }
157
  },
158
- "total_flos": 3.554946091180032e+16,
159
  "train_batch_size": 32,
160
  "trial_name": null,
161
  "trial_params": null
 
1
  {
2
+ "best_global_step": 4670,
3
+ "best_metric": 0.45520129799842834,
4
+ "best_model_checkpoint": "./bert-email/checkpoint-4670",
5
+ "epoch": 10.0,
6
  "eval_steps": 500,
7
+ "global_step": 4670,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
136
  "eval_samples_per_second": 55.845,
137
  "eval_steps_per_second": 1.752,
138
  "step": 4203
139
+ },
140
+ {
141
+ "epoch": 9.635974304068522,
142
+ "grad_norm": 1.6265816688537598,
143
+ "learning_rate": 3.661670235546039e-07,
144
+ "loss": 0.4844812927246094,
145
+ "step": 4500
146
+ },
147
+ {
148
+ "epoch": 10.0,
149
+ "eval_loss": 0.45520129799842834,
150
+ "eval_runtime": 66.8894,
151
+ "eval_samples_per_second": 55.764,
152
+ "eval_steps_per_second": 1.749,
153
+ "step": 4670
154
  }
155
  ],
156
  "logging_steps": 500,
 
165
  "should_evaluate": false,
166
  "should_log": false,
167
  "should_save": true,
168
+ "should_training_stop": true
169
  },
170
  "attributes": {}
171
  }
172
  },
173
+ "total_flos": 3.947507785777152e+16,
174
  "train_batch_size": 32,
175
  "trial_name": null,
176
  "trial_params": null