jmmr-8282 commited on
Commit
0d9bb23
·
verified ·
1 Parent(s): 2c2dbb0

Training in progress, epoch 2, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0f99c0a1d1d8601cc90cee92896572e038623c62a04d513e834071085735bf4
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2504430537c86429c831cb87475da1a37293c832d75fdbc2c76e8c003e349fe3
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f388a234b944d24d6b13babc2afa760f8b6ea45d70dcbdd48602fda5c8e8b6
3
  size 4741923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969fb5cb053036ac4607423c1b8a26ca93f3503b7c222101ab366e90a91636e8
3
  size 4741923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:740b7d41a98e10cd23f22d1b717b2bb89cec87134d461b501222345379d883d7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01207a23a5faa8c448d013264f398497de2ce6615dc97dd68163a13d7d3721fa
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:502ad7c3c4d5253b1f44405955d9838a35d94c121f4b31e5b4b2577f45e77fc4
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e2485f9cc4d9a14b61c17cc2a9f7de40a955c074dd4c7b0be8112172a69b04
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a74b55cce95abbc76b9ea5dad7883d1846de435936a36621080a71d14d7512d1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e184712ae4999fc432bd7f5befda6ba193f8f17a1241d9d5e440f43f8dda0c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 467,
3
- "best_metric": 0.9388861656188965,
4
- "best_model_checkpoint": "./bert-email/checkpoint-467",
5
- "epoch": 1.0,
6
  "eval_steps": 500,
7
- "global_step": 467,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -16,6 +16,21 @@
16
  "eval_samples_per_second": 55.682,
17
  "eval_steps_per_second": 1.747,
18
  "step": 467
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
@@ -35,7 +50,7 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 3925616945971200.0,
39
  "train_batch_size": 32,
40
  "trial_name": null,
41
  "trial_params": null
 
1
  {
2
+ "best_global_step": 934,
3
+ "best_metric": 0.7270694971084595,
4
+ "best_model_checkpoint": "./bert-email/checkpoint-934",
5
+ "epoch": 2.0,
6
  "eval_steps": 500,
7
+ "global_step": 934,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
16
  "eval_samples_per_second": 55.682,
17
  "eval_steps_per_second": 1.747,
18
  "step": 467
19
+ },
20
+ {
21
+ "epoch": 1.0706638115631693,
22
+ "grad_norm": 3.0445573329925537,
23
+ "learning_rate": 7.862955032119916e-06,
24
+ "loss": 1.1060218505859376,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.7270694971084595,
30
+ "eval_runtime": 66.8664,
31
+ "eval_samples_per_second": 55.783,
32
+ "eval_steps_per_second": 1.75,
33
+ "step": 934
34
  }
35
  ],
36
  "logging_steps": 500,
 
50
  "attributes": {}
51
  }
52
  },
53
+ "total_flos": 7851233891942400.0,
54
  "train_batch_size": 32,
55
  "trial_name": null,
56
  "trial_params": null