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
323307d
·
verified ·
1 Parent(s): e141ae5

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 +32 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7c50633206301eba4ca3a1bd42f86ae682d6ad38a9c1dabc5960c1d2fe894c6
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea6d447111a2ec8cd2317fa856caf6dd2ce70cc08dffaec690d421d24abd9f69
3
  size 437958648
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52117e2cf56a025ba21825e2d24000a74e8802e0841f1405cca203d8d2933277
3
  size 4741394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4167bc1e710d7dccff80b0c46ebfe6f40c46af346066de2c78a3a476b4ae5a4b
3
  size 4741394
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f784c6354214653b65a2a96701059993079b0d1d7e997e18e759635c154fb06
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b86e157f86b466ae19e568a6360194077a6c859bad89453623425303da4937
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fde02bdced9988ef02fefc4f313f59fd79f2a089e20f2426a345fbfd6ae60031
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f8cd99175cf2f1e028a18a1ce679621f61ba504aa460cfcd83e0fc9f96eb8c
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bf5f976e97728a02cc3c2e7520cf8903a37550fcfe623a469a4b9a272158140
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d843eceb07cded9821c401bf7f9be101ad586a3ed822931c58813c3aff990f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
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,
@@ -95,6 +95,35 @@
95
  "eval_samples_per_second": 94.175,
96
  "eval_steps_per_second": 5.888,
97
  "step": 4689
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  }
99
  ],
100
  "logging_steps": 500,
@@ -114,7 +143,7 @@
114
  "attributes": {}
115
  }
116
  },
117
- "total_flos": 1.953368130541488e+16,
118
  "train_batch_size": 16,
119
  "trial_name": null,
120
  "trial_params": null
 
2
  "best_global_step": 4689,
3
  "best_metric": 0.2437499761581421,
4
  "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-4689",
5
+ "epoch": 4.0,
6
  "eval_steps": 500,
7
+ "global_step": 6252,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
95
  "eval_samples_per_second": 94.175,
96
  "eval_steps_per_second": 5.888,
97
  "step": 4689
98
+ },
99
+ {
100
+ "epoch": 3.198976327575176,
101
+ "grad_norm": 1.4420491456985474,
102
+ "learning_rate": 3.6046065259117086e-06,
103
+ "loss": 0.27,
104
+ "step": 5000
105
+ },
106
+ {
107
+ "epoch": 3.5188739603326935,
108
+ "grad_norm": 1.480359673500061,
109
+ "learning_rate": 2.9648112603966733e-06,
110
+ "loss": 0.2678,
111
+ "step": 5500
112
+ },
113
+ {
114
+ "epoch": 3.838771593090211,
115
+ "grad_norm": 1.3382619619369507,
116
+ "learning_rate": 2.325015994881638e-06,
117
+ "loss": 0.2581,
118
+ "step": 6000
119
+ },
120
+ {
121
+ "epoch": 4.0,
122
+ "eval_loss": 0.2446114867925644,
123
+ "eval_runtime": 271.3697,
124
+ "eval_samples_per_second": 92.125,
125
+ "eval_steps_per_second": 5.76,
126
+ "step": 6252
127
  }
128
  ],
129
  "logging_steps": 500,
 
143
  "attributes": {}
144
  }
145
  },
146
+ "total_flos": 2.603344526150064e+16,
147
  "train_batch_size": 16,
148
  "trial_name": null,
149
  "trial_params": null