Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
6150d3a
·
1 Parent(s): cd06c04

Checkpoint at step 80

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-40 → checkpoint-80}/config.json +0 -0
  2. checkpoints/{checkpoint-40 → checkpoint-80}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-40 → checkpoint-80}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-40 → checkpoint-80}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-40 → checkpoint-80}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-40 → checkpoint-80}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-40 → checkpoint-80}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-40 → checkpoint-80}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-40 → checkpoint-80}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-40 → checkpoint-80}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-40 → checkpoint-80}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1756423478.a504719e5285.5303.0 +2 -2
checkpoints/{checkpoint-40 → checkpoint-80}/config.json RENAMED
File without changes
checkpoints/{checkpoint-40 → checkpoint-80}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-40 → checkpoint-80}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-40 → checkpoint-80}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a1a0f839d6a2c442a4fe3043bcf607fdfbdfa3d6a0942f4d20f3dbbe512371b
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a982c74190fc69ae25d1f70d2c907d4344f8243e2865f7ae7d4845cf3b1592
3
  size 4997867120
checkpoints/{checkpoint-40 → checkpoint-80}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1165b491ede4d47a18e46fdbd9d0fe457379f44ce922fa65f76664951db526a9
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:174d662d79a9dad5480e1df1b79dc2a6765be9c7bb669b113a67a1ea3d105af5
3
  size 3856242664
checkpoints/{checkpoint-40 → checkpoint-80}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-40 → checkpoint-80}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c02580c15819380ed72ac48a0204bc5c9c9259473c19346cd6df2a02ded0bd6e
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cea09e8640ec22a2fe51a39998e7729d3b36207f8cc3e096fc4f2c805e86035
3
  size 25858571
checkpoints/{checkpoint-40 → checkpoint-80}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-40 → checkpoint-80}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b724dee474d2f28b5e7cd28f30ad6358e8e4bd90e6205eb9f6ebd8fb296e614
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d484e81fa22cdbcf66c2585a42950fa1db3e6db36dd8936a72f76c2844202008
3
  size 1465
checkpoints/{checkpoint-40 → checkpoint-80}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.001962263225347535,
6
  "eval_steps": 500,
7
- "global_step": 40,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -36,6 +36,34 @@
36
  "learning_rate": 6.376716808371485e-07,
37
  "loss": 105.1723,
38
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "logging_steps": 10,
@@ -55,7 +83,7 @@
55
  "attributes": {}
56
  }
57
  },
58
- "total_flos": 1.0730961830412288e+17,
59
  "train_batch_size": 2,
60
  "trial_name": null,
61
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.00392452645069507,
6
  "eval_steps": 500,
7
+ "global_step": 80,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
36
  "learning_rate": 6.376716808371485e-07,
37
  "loss": 105.1723,
38
  "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.002452829031684419,
42
+ "grad_norm": 32.75,
43
+ "learning_rate": 8.011772400261609e-07,
44
+ "loss": 105.2332,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0029433948380213027,
49
+ "grad_norm": 42.25,
50
+ "learning_rate": 9.646827992151733e-07,
51
+ "loss": 104.8549,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.003433960644358187,
56
+ "grad_norm": 35.5,
57
+ "learning_rate": 1.1281883584041859e-06,
58
+ "loss": 103.9609,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.00392452645069507,
63
+ "grad_norm": 37.25,
64
+ "learning_rate": 1.2916939175931983e-06,
65
+ "loss": 104.4941,
66
+ "step": 80
67
  }
68
  ],
69
  "logging_steps": 10,
 
83
  "attributes": {}
84
  }
85
  },
86
+ "total_flos": 2.1461923660824576e+17,
87
  "train_batch_size": 2,
88
  "trial_name": null,
89
  "trial_params": null
checkpoints/{checkpoint-40 → checkpoint-80}/training_args.bin RENAMED
File without changes
logs/events.out.tfevents.1756423478.a504719e5285.5303.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cbddf50d1af8faefbc9312e466d0fdd6ee27bf9a14af0981df2f9297c57239a
3
- size 6486
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52392e9a4b3e1c6d8df347aa91bba441e6b320951e784461aa04460fbf9c5246
3
+ size 6900