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
7876692
·
verified ·
1 Parent(s): 996c181

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 +21 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85a52549a555458e316d9541bc8d1beb3810743c658a7c008e0c271db7120757
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d732e1fad61bf299c5356477b67e2fcef1cf549603cefbfa8ca6bab3c7521c42
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e6d5bbe0022ea47a5f6da36144a84a14f24577d0f01d7df241104b519e6ecf5
3
  size 4741923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad4e046c286f2cd811b4bb8e1206cb490af7e9616a5581fc5894fa6ca9adb0c
3
  size 4741923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32d162a27fed25729344a2bcfc01d466b3fce9828a651acf58597c5f5fce3339
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443b873fa0b8ac2f8ed37dd9058b435b4499662fdb680f826154879e6d39e07b
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55a14f50074c8ada78f60d77af81976ea4a319a828807b0fe7148cf20eea9f51
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892ebb3c022962376ff6204813305ef50eeeaf887a8e7724c977df8a91a627b6
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:778d08b3d8775920e0ddf0f813feab141bcbe1463b3aa704b47b315801d4216d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78500ab6a7d29c819aa4507554b782f06ce48268efffcde9c60d9248b7031a63
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1564,
3
- "best_metric": 0.8574339151382446,
4
- "best_model_checkpoint": "./bert-imdb-cp/checkpoint-1564",
5
- "epoch": 2.0,
6
  "eval_steps": 500,
7
- "global_step": 1564,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 55.78,
46
  "eval_steps_per_second": 1.745,
47
  "step": 1564
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 500,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1.314943543596288e+16,
68
  "train_batch_size": 32,
69
  "trial_name": null,
70
  "trial_params": null
 
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,
 
45
  "eval_samples_per_second": 55.78,
46
  "eval_steps_per_second": 1.745,
47
  "step": 1564
48
+ },
49
+ {
50
+ "epoch": 2.557544757033248,
51
+ "grad_norm": 3.2615952491760254,
52
+ "learning_rate": 4.887468030690537e-06,
53
+ "loss": 0.8982860717773438,
54
+ "step": 2000
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_loss": 0.8016525506973267,
59
+ "eval_runtime": 447.3533,
60
+ "eval_samples_per_second": 55.884,
61
+ "eval_steps_per_second": 1.748,
62
+ "step": 2346
63
  }
64
  ],
65
  "logging_steps": 500,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.972536593146512e+16,
83
  "train_batch_size": 32,
84
  "trial_name": null,
85
  "trial_params": null