Hugging Face's logo

jmmr-8282
/
email

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
jmmr-8282 commited on
Commit
31b11b9
·
verified ·
1 Parent(s): 7315839

Training in progress, epoch 5, 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 +22 -7
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb7b9ee5d5a289ecee12276ea139b3446e5d2b0749738e76ee12ab4e6815011a
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210856a64940b579b6ac438055db28bb7947047d7b751c78767ac9a639d94c3e
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f52c9c737c0616d379ccd0e217fd4da602c37c20f09befad90a3b45ec2414448
3
  size 4741923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11bbc5b49b7537c8c7e5902cd575557135d769301c92827b5f9ddf71ab88e3d7
3
  size 4741923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fb370ab700093b2f074f90e23d7f00c5453a68d643bf15d029b1e8596742be3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44b4f35543873087c1cf6328742bd57e22ab2a916a6a3f007a76de03ee9cbab
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9343bdb5d2121fead6995ccf81e3591c0ddf27b60c835e5527a4bd7a66af257
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e1ac30298048a080369699ec7fa0a715c4c2d28ff44da425171525f8394b890
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e8e008c9fcdd6b519f5ca1b89689630a9e27532a04ab80fd57e825818c9a4a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2909836fc184f92a445a91a7ebd6fe5b3c1c5b6a8f29fd49d1721b035d5f5860
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1868,
3
- "best_metric": 0.5720958113670349,
4
- "best_model_checkpoint": "./bert-email/checkpoint-1868",
5
- "epoch": 4.0,
6
  "eval_steps": 500,
7
- "global_step": 1868,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -61,6 +61,21 @@
61
  "eval_samples_per_second": 55.764,
62
  "eval_steps_per_second": 1.749,
63
  "step": 1868
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  }
65
  ],
66
  "logging_steps": 500,
@@ -75,12 +90,12 @@
75
  "should_evaluate": false,
76
  "should_log": false,
77
  "should_save": true,
78
- "should_training_stop": false
79
  },
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 1.57024677838848e+16,
84
  "train_batch_size": 32,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_global_step": 2335,
3
+ "best_metric": 0.5627617239952087,
4
+ "best_model_checkpoint": "./bert-email/checkpoint-2335",
5
+ "epoch": 5.0,
6
  "eval_steps": 500,
7
+ "global_step": 2335,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
61
  "eval_samples_per_second": 55.764,
62
  "eval_steps_per_second": 1.749,
63
  "step": 1868
64
+ },
65
+ {
66
+ "epoch": 4.282655246252677,
67
+ "grad_norm": 1.6766972541809082,
68
+ "learning_rate": 1.4389721627408994e-06,
69
+ "loss": 0.6073400268554687,
70
+ "step": 2000
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.5627617239952087,
75
+ "eval_runtime": 66.8913,
76
+ "eval_samples_per_second": 55.762,
77
+ "eval_steps_per_second": 1.749,
78
+ "step": 2335
79
  }
80
  ],
81
  "logging_steps": 500,
 
90
  "should_evaluate": false,
91
  "should_log": false,
92
  "should_save": true,
93
+ "should_training_stop": true
94
  },
95
  "attributes": {}
96
  }
97
  },
98
+ "total_flos": 1.9628084729856e+16,
99
  "train_batch_size": 32,
100
  "trial_name": null,
101
  "trial_params": null