Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
cd06c04
·
1 Parent(s): 82434ff

Checkpoint at step 60

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-20 → checkpoint-60}/config.json +0 -0
  2. checkpoints/{checkpoint-20 → checkpoint-60}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-20 → checkpoint-60}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-20 → checkpoint-60}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-20 → checkpoint-60}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-20 → checkpoint-60}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-20 → checkpoint-60}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-20 → checkpoint-60}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-20 → checkpoint-60}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-20 → checkpoint-60}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-20 → checkpoint-60}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1756423478.a504719e5285.5303.0 +2 -2
checkpoints/{checkpoint-20 → checkpoint-60}/config.json RENAMED
File without changes
checkpoints/{checkpoint-20 → checkpoint-60}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-20 → checkpoint-60}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-20 → checkpoint-60}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f95224fceb9a38e9623b5f2bf6d2d8f038fcf081128481aa23313c6710fc5a8
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b255e3590d937fef59bd217502b38b8c9f62ae8ee4b024bf4c4fec24bcfdd8
3
  size 4997867120
checkpoints/{checkpoint-20 → checkpoint-60}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6ea76c1b4617d733cc6bcec99a13d759c0eed69ef38bfd21c6e6489b9b8c862
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381d3fde8dd31775cd472861838fb01e4a32241511c0855958236a5b49b1e55b
3
  size 3856242664
checkpoints/{checkpoint-20 → checkpoint-60}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-20 → checkpoint-60}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:347aa192797912d7a2dcd8faa2f4b2cf048ffa14734e8048be7948fb391843c5
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307798a811f1a52083432f959ed0706dbdf54ac8b32047f4d820852afd78bf61
3
  size 25858571
checkpoints/{checkpoint-20 → checkpoint-60}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-20 → checkpoint-60}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:795c503600292c8c704d0cbf6e623255ed54848f02f567e3d52d4c939d5df78e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1be529198179cd559ddcb4c59a9f665944a456be4a70f4f5dcf79350fe0534
3
  size 1465
checkpoints/{checkpoint-20 → checkpoint-60}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.0009811316126737675,
6
  "eval_steps": 500,
7
- "global_step": 20,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -22,6 +22,34 @@
22
  "learning_rate": 3.106605624591236e-07,
23
  "loss": 105.2674,
24
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 10,
@@ -41,7 +69,7 @@
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 5.365480915206144e+16,
45
  "train_batch_size": 2,
46
  "trial_name": null,
47
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.0029433948380213027,
6
  "eval_steps": 500,
7
+ "global_step": 60,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
22
  "learning_rate": 3.106605624591236e-07,
23
  "loss": 105.2674,
24
  "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0014716974190106514,
28
+ "grad_norm": 46.25,
29
+ "learning_rate": 4.7416612164813603e-07,
30
+ "loss": 105.4015,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.001962263225347535,
35
+ "grad_norm": 36.25,
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
  "logging_steps": 10,
 
69
  "attributes": {}
70
  }
71
  },
72
+ "total_flos": 1.6096442745618432e+17,
73
  "train_batch_size": 2,
74
  "trial_name": null,
75
  "trial_params": null
checkpoints/{checkpoint-20 → checkpoint-60}/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:c78861a49efd0504e6bf537262b60256c2ba1502481d5a3226223927c4fe11d5
3
- size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbddf50d1af8faefbc9312e466d0fdd6ee27bf9a14af0981df2f9297c57239a
3
+ size 6486