CodeIsAbstract commited on
Commit
1c82248
·
verified ·
1 Parent(s): c0c3ed0

Training in progress, step 70, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d661065b330d59c5ed2e4fb4b6a43688499e3bd7104b7349c11f7e3fdb9b9c21
3
  size 847599616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe0c3adfa2b79c288d7141b41f26a0882f7db5831e7593c722eb20c0d838ab0
3
  size 847599616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19a5b07dd15e1e9303ca9bdb1cc0ad4bd111d5ba5e6d141125ec478a65a221d9
3
  size 1386414411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87bbdda03bfdd726b8692763bc22d94ab384ee039a6f1c12a15c9b257cc88787
3
  size 1386414411
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dbcc51e17bf9f30305c1120d7d28bfae15fa17f68068cbc1ada9c77b923011d
3
  size 14917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c4850e630d2c2f708e778b9c35200bf94fd032b9e590527873edb08f25dbd6
3
  size 14917
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2ee555d6cd5d24cb8f2a6db7c5284d6de90ae0739e324037854549d1ee329db
3
  size 14917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd1311e0baba04fc4d7fba0b87e58c8f5a8655b05b47713d596c80eb0cbc81f
3
  size 14917
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb800e07d5790b986f99bf8623894f6a4640212bee171e17fe91e27ad2f603b1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6ae072d14b1ef8c01d65c086c7913a7e1c653f2660d5e7e962582703aa79e0
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.06,
6
  "eval_steps": 5,
7
- "global_step": 60,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -116,6 +116,24 @@
116
  "eval_samples_per_second": 13.689,
117
  "eval_steps_per_second": 6.844,
118
  "step": 60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  }
120
  ],
121
  "logging_steps": 100,
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.07,
6
  "eval_steps": 5,
7
+ "global_step": 70,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
116
  "eval_samples_per_second": 13.689,
117
  "eval_steps_per_second": 6.844,
118
  "step": 60
119
+ },
120
+ {
121
+ "epoch": 0.065,
122
+ "eval_accuracy": 0.07053333333333334,
123
+ "eval_loss": 17.156831741333008,
124
+ "eval_runtime": 40.9838,
125
+ "eval_samples_per_second": 12.2,
126
+ "eval_steps_per_second": 6.1,
127
+ "step": 65
128
+ },
129
+ {
130
+ "epoch": 0.07,
131
+ "eval_accuracy": 0.07253333333333334,
132
+ "eval_loss": 17.09288215637207,
133
+ "eval_runtime": 35.8052,
134
+ "eval_samples_per_second": 13.964,
135
+ "eval_steps_per_second": 6.982,
136
+ "step": 70
137
  }
138
  ],
139
  "logging_steps": 100,