smilemikan commited on
Commit
e66ae1e
1 Parent(s): dcbad1c

Training in progress, step 40000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:549ed9c913a34c98d736c418920b93aee75ea5f338f8a72583152dffe9394f92
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a74952ccd19e322f3ff1f755b9e0610d0e006869fd5053ac8d16d2e6ad029fc7
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27ff65060cdc15a19f53dbdc9d93d815f11b1fcfc429e330347d40a1a3048044
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32807b3d432b1309ac4288019434f632854ba21e246d0b0a13ada84a16407b03
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d3f524deadc79201158d2a1b6e198e466fb4975698a11b51acf1fa7cfaec074
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c5b7259d9afb3f8d1a1cc6302ca0d8c380983ba1d5c16d5468223fd5c7698d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd3582066fafbc8f34b4818574951b7cb4867e414999f0ebd504c560b18f73e7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2228727576b2e89bbf087c11e447c0430a7a9c1eb48fa7b8c4ac01deb07414db
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3474962711334229,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-39500",
4
- "epoch": 8.702357347433356,
5
  "eval_steps": 500,
6
- "global_step": 39500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1113,13 +1113,27 @@
1113
  "eval_samples_per_second": 203.074,
1114
  "eval_steps_per_second": 12.706,
1115
  "step": 39500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 500,
1119
  "max_steps": 60000,
1120
  "num_train_epochs": 14,
1121
  "save_steps": 500,
1122
- "total_flos": 4.002692991614976e+16,
1123
  "trial_name": null,
1124
  "trial_params": null
1125
  }
 
1
  {
2
+ "best_metric": 1.3451054096221924,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-40000",
4
+ "epoch": 8.812513769552766,
5
  "eval_steps": 500,
6
+ "global_step": 40000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1113
  "eval_samples_per_second": 203.074,
1114
  "eval_steps_per_second": 12.706,
1115
  "step": 39500
1116
+ },
1117
+ {
1118
+ "epoch": 8.81,
1119
+ "learning_rate": 6.671000000000001e-06,
1120
+ "loss": 1.1651,
1121
+ "step": 40000
1122
+ },
1123
+ {
1124
+ "epoch": 8.81,
1125
+ "eval_loss": 1.3451054096221924,
1126
+ "eval_runtime": 44.3384,
1127
+ "eval_samples_per_second": 204.743,
1128
+ "eval_steps_per_second": 12.811,
1129
+ "step": 40000
1130
  }
1131
  ],
1132
  "logging_steps": 500,
1133
  "max_steps": 60000,
1134
  "num_train_epochs": 14,
1135
  "save_steps": 500,
1136
+ "total_flos": 4.052519466958848e+16,
1137
  "trial_name": null,
1138
  "trial_params": null
1139
  }