Hugging Face's logo

harsith05
/
imdbdata

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
harsith05 commited on
Commit
79b37fb
·
verified ·
1 Parent(s): 60bdd25

Training in progress, epoch 2, 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 +35 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:757c0164d062683a7a4c6ff5b9f448c93742b5e19b9f491fa1522e8c7e7a8e1e
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db41f294599793f7fae28d41845320edb0650d2456d64fc7fb5f005c59382125
3
  size 437958648
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27cd83b39879058c79b84636f93dcd76608027e78b3632e7118bc67c01834baf
3
  size 4741394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43616082499029184e2f13e90fb9f4a37d52b594b75bf071e65666f62cb053b1
3
  size 4741394
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fde5d78d467270e6f38169a48e70e420d3afe1146078e423f8499685461bf22
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691b3b85e42c089d2bdb72309424d3454b990e0596c27b15f218b3f6e4c39e55
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:713ce80c4477b3cfcc8aacd01e948331f6b151bcde4f5963a683f54fa49aa3e3
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8243327b567e29221b3b0a60eae4c9072058f5c8b9c0d230403fabc381ad170
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4bdd482695b42169ef7246f76d1bdfc504014258754e59317c8db3044fb3370
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277d64c1fa62b94de5cd9fbaae8d5305a494ee0d592658983f99038ab090e62e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1563,
3
- "best_metric": 0.2548043727874756,
4
- "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-1563",
5
- "epoch": 1.0,
6
  "eval_steps": 500,
7
- "global_step": 1563,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 90.342,
38
  "eval_steps_per_second": 5.648,
39
  "step": 1563
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 500,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 6515172397265280.0,
60
  "train_batch_size": 16,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
+ "best_global_step": 3126,
3
+ "best_metric": 0.2492910772562027,
4
+ "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-3126",
5
+ "epoch": 2.0,
6
  "eval_steps": 500,
7
+ "global_step": 3126,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 90.342,
38
  "eval_steps_per_second": 5.648,
39
  "step": 1563
40
+ },
41
+ {
42
+ "epoch": 1.2795905310300704,
43
+ "grad_norm": 1.6743276119232178,
44
+ "learning_rate": 7.44209852847089e-06,
45
+ "loss": 0.2704,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 1.599488163787588,
50
+ "grad_norm": 2.1094255447387695,
51
+ "learning_rate": 6.802303262955855e-06,
52
+ "loss": 0.2619,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.9193857965451055,
57
+ "grad_norm": 1.2479547262191772,
58
+ "learning_rate": 6.16250799744082e-06,
59
+ "loss": 0.2723,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "eval_loss": 0.2492910772562027,
65
+ "eval_runtime": 271.0728,
66
+ "eval_samples_per_second": 92.226,
67
+ "eval_steps_per_second": 5.766,
68
+ "step": 3126
69
  }
70
  ],
71
  "logging_steps": 500,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1.302353679597312e+16,
89
  "train_batch_size": 16,
90
  "trial_name": null,
91
  "trial_params": null