smilemikan commited on
Commit
af03f50
1 Parent(s): 1c33b74

Training in progress, step 3000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e83191e9de77954f10ec8d943f4fdd1215b54f4fab154b17120e1a226fb4528
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d806657a3fcb11e861c5e0e2449f115aa999822a821ad28b8314f5dcb5b05f0
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d24372e3cafb13ca988fb39ee3aa6f6339fcfad36ed0d32e5ed1a482b1347d1
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a36ff9352357969b0caead584a1f16d63786d1175c0792e23b1a8f7e50981d
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:fd154127396e5deb43e241ef5d251275e538c90f80c3d28ad6fc02d2af77d898
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c481b4d8439a487e25df91b61940cbb7a1cf50f4dd7c1f0db2cc8fe8f2f6aab1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7e7fc7cce7c11a9cf69d6eb62bc6fa1462ffebea3d00eeb12026f2494eafd55
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e1b950837b9d2a345ea077700263f207e496e38d5422ab64b4e4d5b308c780
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.5206823348999023,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-2500",
4
- "epoch": 0.5507821105970478,
5
  "eval_steps": 500,
6
- "global_step": 2500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -77,13 +77,27 @@
77
  "eval_samples_per_second": 211.959,
78
  "eval_steps_per_second": 13.262,
79
  "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  }
81
  ],
82
  "logging_steps": 500,
83
  "max_steps": 60000,
84
  "num_train_epochs": 14,
85
  "save_steps": 500,
86
- "total_flos": 2528570877542400.0,
87
  "trial_name": null,
88
  "trial_params": null
89
  }
 
1
  {
2
+ "best_metric": 2.394014835357666,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-3000",
4
+ "epoch": 0.6609385327164574,
5
  "eval_steps": 500,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
77
  "eval_samples_per_second": 211.959,
78
  "eval_steps_per_second": 13.262,
79
  "step": 2500
80
+ },
81
+ {
82
+ "epoch": 0.66,
83
+ "learning_rate": 1.9000333333333335e-05,
84
+ "loss": 2.6105,
85
+ "step": 3000
86
+ },
87
+ {
88
+ "epoch": 0.66,
89
+ "eval_loss": 2.394014835357666,
90
+ "eval_runtime": 42.8022,
91
+ "eval_samples_per_second": 212.092,
92
+ "eval_steps_per_second": 13.27,
93
+ "step": 3000
94
  }
95
  ],
96
  "logging_steps": 500,
97
  "max_steps": 60000,
98
  "num_train_epochs": 14,
99
  "save_steps": 500,
100
+ "total_flos": 3028697986498560.0,
101
  "trial_name": null,
102
  "trial_params": null
103
  }