ameerazam08 commited on
Commit
3328618
·
1 Parent(s): df93d1e
Files changed (6) hide show
  1. optimizer.pt +1 -1
  2. pytorch_model.bin +1 -1
  3. rng_state.pth +1 -1
  4. scaler.pt +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +3 -18
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3175558e8e61233286d0233755e426ebc33a4a0ee9d88efeabc91b0969dd0d6c
3
  size 2498522505
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2251f8fb6941a79db7b7c8f419235cd1d3a8ab37174d57517d90234d4e41a471
3
  size 2498522505
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b83378c33a6ea5b49584394b6889d866dda8704d4223b7e012cbbcb8bc2469dc
3
  size 1266130541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93536e6e0a8eb02eb18680c9457964a62569508e9def6f8c9dc2c61aac2fa178
3
  size 1266130541
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2d6c598ad1ff03fdbae199c042313f72c379e59a7adc5c986920487ec0ef0f0
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d3437cc781f60db7f0c4ec11b98c7820ced9da2ab517212a97208c81e0a031
3
  size 14503
scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4b9accfbdcb85276435ad005655da973cd6905daf1d6df04732beae9fcc5608
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8139a2d5a513b92ca7751a538153ea76a749e3742836b6044f8c530ae1149fb6
3
  size 559
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0408533f367f94f43315c4942763b084245dd96c78cefc95eb3b423200fa39bb
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748aacfdb5198e403336e1866da3fd45d311cf7ebe83e327e4ae797f20a0f0f0
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.5694444444444446,
5
- "global_step": 740,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1101,26 +1101,11 @@
1101
  "eval_samples_per_second": 6.423,
1102
  "eval_steps_per_second": 1.606,
1103
  "step": 730
1104
- },
1105
- {
1106
- "epoch": 2.57,
1107
- "learning_rate": 1.4467592592592593e-05,
1108
- "loss": 0.3625,
1109
- "step": 740
1110
- },
1111
- {
1112
- "epoch": 2.57,
1113
- "eval_accuracy": 0.8003472089767456,
1114
- "eval_loss": 0.5525452494621277,
1115
- "eval_runtime": 90.5733,
1116
- "eval_samples_per_second": 6.359,
1117
- "eval_steps_per_second": 1.59,
1118
- "step": 740
1119
  }
1120
  ],
1121
  "max_steps": 864,
1122
  "num_train_epochs": 3,
1123
- "total_flos": 2.187634079192584e+18,
1124
  "trial_name": null,
1125
  "trial_params": null
1126
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.5347222222222223,
5
+ "global_step": 730,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1101
  "eval_samples_per_second": 6.423,
1102
  "eval_steps_per_second": 1.606,
1103
  "step": 730
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1104
  }
1105
  ],
1106
  "max_steps": 864,
1107
  "num_train_epochs": 3,
1108
+ "total_flos": 2.1573660231214095e+18,
1109
  "trial_name": null,
1110
  "trial_params": null
1111
  }