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
b75f56b
·
verified ·
1 Parent(s): 79b37fb

Training in progress, epoch 3, 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:db41f294599793f7fae28d41845320edb0650d2456d64fc7fb5f005c59382125
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c50633206301eba4ca3a1bd42f86ae682d6ad38a9c1dabc5960c1d2fe894c6
3
  size 437958648
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43616082499029184e2f13e90fb9f4a37d52b594b75bf071e65666f62cb053b1
3
  size 4741394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52117e2cf56a025ba21825e2d24000a74e8802e0841f1405cca203d8d2933277
3
  size 4741394
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:691b3b85e42c089d2bdb72309424d3454b990e0596c27b15f218b3f6e4c39e55
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f784c6354214653b65a2a96701059993079b0d1d7e997e18e759635c154fb06
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8243327b567e29221b3b0a60eae4c9072058f5c8b9c0d230403fabc381ad170
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde02bdced9988ef02fefc4f313f59fd79f2a089e20f2426a345fbfd6ae60031
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:277d64c1fa62b94de5cd9fbaae8d5305a494ee0d592658983f99038ab090e62e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf5f976e97728a02cc3c2e7520cf8903a37550fcfe623a469a4b9a272158140
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
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,
@@ -66,6 +66,35 @@
66
  "eval_samples_per_second": 92.226,
67
  "eval_steps_per_second": 5.766,
68
  "step": 3126
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 500,
@@ -85,7 +114,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1.302353679597312e+16,
89
  "train_batch_size": 16,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
+ "best_global_step": 4689,
3
+ "best_metric": 0.2437499761581421,
4
+ "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-4689",
5
+ "epoch": 3.0,
6
  "eval_steps": 500,
7
+ "global_step": 4689,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
66
  "eval_samples_per_second": 92.226,
67
  "eval_steps_per_second": 5.766,
68
  "step": 3126
69
+ },
70
+ {
71
+ "epoch": 2.239283429302623,
72
+ "grad_norm": 2.0263354778289795,
73
+ "learning_rate": 5.522712731925784e-06,
74
+ "loss": 0.2574,
75
+ "step": 3500
76
+ },
77
+ {
78
+ "epoch": 2.5591810620601407,
79
+ "grad_norm": 0.6032302379608154,
80
+ "learning_rate": 4.882917466410749e-06,
81
+ "loss": 0.2674,
82
+ "step": 4000
83
+ },
84
+ {
85
+ "epoch": 2.8790786948176583,
86
+ "grad_norm": 0.584612250328064,
87
+ "learning_rate": 4.2444017914267435e-06,
88
+ "loss": 0.271,
89
+ "step": 4500
90
+ },
91
+ {
92
+ "epoch": 3.0,
93
+ "eval_loss": 0.2437499761581421,
94
+ "eval_runtime": 265.4633,
95
+ "eval_samples_per_second": 94.175,
96
+ "eval_steps_per_second": 5.888,
97
+ "step": 4689
98
  }
99
  ],
100
  "logging_steps": 500,
 
114
  "attributes": {}
115
  }
116
  },
117
+ "total_flos": 1.953368130541488e+16,
118
  "train_batch_size": 16,
119
  "trial_name": null,
120
  "trial_params": null