Hugging Face's logo

harsith05
/
imdb_practice

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
harsith05 commited on
Commit
71dfe06
·
verified ·
1 Parent(s): 2bf8a0b

Training in progress, epoch 4, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +25 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51d797ff01f1fd3309ceb5fc8260f2ecf04aedbbeb1a79ee7fe2bb07661397a3
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4f05918cf3e0821509d1f232f7d97ea029bdd126ea1537c67cfa9006e04918
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc64b9b0d3c14bceb03ffc28596bf3b9b531e18554fd42268cf9f632e6f41a4a
3
  size 113448011
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906e9f067e8bf73d5d4a109927af671f0b87f006fe575c05c75925b326c4b9aa
3
  size 113448011
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:443b873fa0b8ac2f8ed37dd9058b435b4499662fdb680f826154879e6d39e07b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d553173fafc1568aba563e8b2ebc65b521fc7ac5272baf9b3276c61a1b3955
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:892ebb3c022962376ff6204813305ef50eeeaf887a8e7724c977df8a91a627b6
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0635f5ee8287266c95252541d63a4925053f9e404f1dbe420921c5ed9e5141ff
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8339cf9263254706ceb68449b256ba0478aa77f160333d61186b08aa24621c61
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92fc37e37e0b888ef62e0325f1183d633f1932258d154ae97aef1f17c6ac55b8
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 2346,
3
  "best_metric": 0.38437092304229736,
4
  "best_model_checkpoint": "./bert-imdb-cp/checkpoint-2346",
5
- "epoch": 3.0,
6
  "eval_steps": 500,
7
- "global_step": 2346,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -60,6 +60,28 @@
60
  "eval_samples_per_second": 53.809,
61
  "eval_steps_per_second": 1.683,
62
  "step": 2346
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 500,
@@ -79,7 +101,7 @@
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.972536593146512e+16,
83
  "train_batch_size": 32,
84
  "trial_name": null,
85
  "trial_params": null
 
2
  "best_global_step": 2346,
3
  "best_metric": 0.38437092304229736,
4
  "best_model_checkpoint": "./bert-imdb-cp/checkpoint-2346",
5
+ "epoch": 4.0,
6
  "eval_steps": 500,
7
+ "global_step": 3128,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 53.809,
61
  "eval_steps_per_second": 1.683,
62
  "step": 2346
63
+ },
64
+ {
65
+ "epoch": 3.1969309462915603,
66
+ "grad_norm": 5.991187572479248,
67
+ "learning_rate": 7.217391304347827e-06,
68
+ "loss": 0.3858807067871094,
69
+ "step": 2500
70
+ },
71
+ {
72
+ "epoch": 3.836317135549872,
73
+ "grad_norm": 6.665840148925781,
74
+ "learning_rate": 4.659846547314578e-06,
75
+ "loss": 0.3582411193847656,
76
+ "step": 3000
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_loss": 0.38614124059677124,
81
+ "eval_runtime": 465.1758,
82
+ "eval_samples_per_second": 53.743,
83
+ "eval_steps_per_second": 1.681,
84
+ "step": 3128
85
  }
86
  ],
87
  "logging_steps": 500,
 
101
  "attributes": {}
102
  }
103
  },
104
+ "total_flos": 2.63008072048488e+16,
105
  "train_batch_size": 32,
106
  "trial_name": null,
107
  "trial_params": null