Hugging Face's logo

jmmr-8282
/
llm

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
jmmr-8282 commited on
Commit
e5f1308
·
verified ·
1 Parent(s): a69aa9c

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 +28 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d732e1fad61bf299c5356477b67e2fcef1cf549603cefbfa8ca6bab3c7521c42
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c056c3378f5d58d4584775046ce97b8d16de39aa589668238c1423d31b1662b
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad4e046c286f2cd811b4bb8e1206cb490af7e9616a5581fc5894fa6ca9adb0c
3
  size 4741923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df12f0a471877cef6d700eb1c766ae445f98309a61a39a10186a2b6aeebe1eb4
3
  size 4741923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:443b873fa0b8ac2f8ed37dd9058b435b4499662fdb680f826154879e6d39e07b
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 sha256:78500ab6a7d29c819aa4507554b782f06ce48268efffcde9c60d9248b7031a63
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9663833f02fe99567660dbbf033273979d059bd123e7db38679c72f2ea5889
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 2346,
3
- "best_metric": 0.8016525506973267,
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": 55.884,
61
  "eval_steps_per_second": 1.748,
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
 
1
  {
2
+ "best_global_step": 3128,
3
+ "best_metric": 0.7798203825950623,
4
+ "best_model_checkpoint": "./bert-imdb-cp/checkpoint-3128",
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": 55.884,
61
  "eval_steps_per_second": 1.748,
62
  "step": 2346
63
+ },
64
+ {
65
+ "epoch": 3.1969309462915603,
66
+ "grad_norm": 3.32869029045105,
67
+ "learning_rate": 3.6086956521739134e-06,
68
+ "loss": 0.8506306762695313,
69
+ "step": 2500
70
+ },
71
+ {
72
+ "epoch": 3.836317135549872,
73
+ "grad_norm": 4.591386795043945,
74
+ "learning_rate": 2.329923273657289e-06,
75
+ "loss": 0.83572509765625,
76
+ "step": 3000
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_loss": 0.7798203825950623,
81
+ "eval_runtime": 448.1623,
82
+ "eval_samples_per_second": 55.783,
83
+ "eval_steps_per_second": 1.745,
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