smilemikan commited on
Commit
e4456fe
1 Parent(s): 3ae9904

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:078d8071521ede112852e855f8810ba95c3f181a89a694ada8beb7269d3fb0ad
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedf4971a7157fd6bf2d6feebbaf0240f131c23a6aaa72257b8d4af3408f99e4
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84a29e30a075284b9ca0004c0fbc0946bc886a09ebab5725f1a735c2e5c00f6b
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7686f4fb6dccf6ef68f65a46df2006c3d78f5fe61e8dba208e3cb0272df797c
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29c2aa74deb31db2b12469b47a7fce16317bcec2c98e85828fe8c23d20d8ef5a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca32586bfda8fd1d34bb7ca8e64a65d045528f0ab228f5d414f71d2c61b4989
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29da31604d6d4c40d5fac4d688da87a17172e648b9960b502678a992f7f9b1f5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5466d8ea9c57da5074af2cc5d48a8f8664876c6c924307fbf397a610d232702d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.8919074535369873,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-1500",
4
- "epoch": 0.3304692663582287,
5
  "eval_steps": 500,
6
- "global_step": 1500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -49,13 +49,27 @@
49
  "eval_samples_per_second": 211.977,
50
  "eval_steps_per_second": 13.263,
51
  "step": 1500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  }
53
  ],
54
  "logging_steps": 500,
55
  "max_steps": 60000,
56
  "num_train_epochs": 14,
57
  "save_steps": 500,
58
- "total_flos": 1527571717423104.0,
59
  "trial_name": null,
60
  "trial_params": null
61
  }
 
1
  {
2
+ "best_metric": 2.679006338119507,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-2000",
4
+ "epoch": 0.4406256884776382,
5
  "eval_steps": 500,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
49
  "eval_samples_per_second": 211.977,
50
  "eval_steps_per_second": 13.263,
51
  "step": 1500
52
+ },
53
+ {
54
+ "epoch": 0.44,
55
+ "learning_rate": 1.9333333333333333e-05,
56
+ "loss": 2.902,
57
+ "step": 2000
58
+ },
59
+ {
60
+ "epoch": 0.44,
61
+ "eval_loss": 2.679006338119507,
62
+ "eval_runtime": 43.6162,
63
+ "eval_samples_per_second": 208.134,
64
+ "eval_steps_per_second": 13.023,
65
+ "step": 2000
66
  }
67
  ],
68
  "logging_steps": 500,
69
  "max_steps": 60000,
70
  "num_train_epochs": 14,
71
  "save_steps": 500,
72
+ "total_flos": 2025260833701888.0,
73
  "trial_name": null,
74
  "trial_params": null
75
  }