Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
0fc63f3
·
1 Parent(s): f5a3f32

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.1755018526.5a559ada2903.7360.0 +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 sha256:31c1d41e7136137938e8a412a56f018a711b5780186d8cf4d4c2750a5bf24497
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142626e4ad2789afdd7075a838be6094f6107528b999e8002e1027622b23f0c1
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:b7e652a824648175d8fc8a7f4239842afc7dd662fbce96095fb1c76f7c1c863c
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd33f1984554267aa9d48bff67d553952e8032dbe8adb7c06bbe0a8a31b7db1
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 sha256:5775ac51a9aecbc5b49781bee263b0008e9f2c3e3e0dd1ced8a51127d8068235
3
  size 25858106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f7b14cc2a8bd8b73bb73764b511fcbd053b47899d5940eddfdf19db2b2088b
3
  size 25858106
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 sha256:9099bb2a5def5951a9a00e949600857b5dfda24bdadd06a58a3b472699a39c01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc4bf1eb43aa71b43dcab4b0a40f3988ed0b4e5e64e925b2c6a74673e559af6
3
  size 1064
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": 106.3035,
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": 106.3035,
38
  "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.002452829031684419,
42
+ "grad_norm": 32.5,
43
+ "learning_rate": 8.011772400261609e-07,
44
+ "loss": 106.6249,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0029433948380213027,
49
+ "grad_norm": 39.75,
50
+ "learning_rate": 9.646827992151733e-07,
51
+ "loss": 105.676,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.003433960644358187,
56
+ "grad_norm": 34.0,
57
+ "learning_rate": 1.1281883584041859e-06,
58
+ "loss": 105.038,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.00392452645069507,
63
+ "grad_norm": 37.0,
64
+ "learning_rate": 1.2916939175931983e-06,
65
+ "loss": 105.8347,
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.1755018526.5a559ada2903.7360.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf7bf86350557e40718bdcd78b718f6f6bbd5e165e34a3c928f81e32066f461c
3
- size 6525
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80254d4c153ef4bd4fd22f9ebc4b956e0513a3f30c572855ca39a33569c36c0
3
+ size 6939