Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
f5a3f32
·
1 Parent(s): 01aae00

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.1755018526.5a559ada2903.7360.0 +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 sha256:9cf56939ed263f12eaca88766699734db11f7b783b9160c0d662d094a117e4c4
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0cdd96fd408cd9f8e73c3dbbf00734b77c6dfb72c9b5a41b72f06ebff4f161
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 sha256:6f527c20f18c2877aa6b30c2cd8629b2db4fda8ff54169a8c4894427428578c1
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35a698d6fe8055364b4598ae4d8db5fe09aac512f9d899407546df26a4e766a
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 sha256:793963570b42c2c54c9ed5f00059fa8c131161ab6177d1ab3716b4d17cf83373
3
  size 25858106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3f22ef0d9bf205a275a16ad19666d6a98d3dbab2c442245911eaa1b7055398
3
  size 25858106
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:fcf8dd0e6a3ad56f8210d4683034662fe849df5588f3ad98e479777855d47dee
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4829bd5085a30621b1c4179420abe78393ed12e8335dd018c0a92ec8489dbcb
3
  size 1064
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": 106.6525,
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": 106.6525,
24
  "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0014716974190106514,
28
+ "grad_norm": 46.25,
29
+ "learning_rate": 4.7416612164813603e-07,
30
+ "loss": 106.5493,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.001962263225347535,
35
+ "grad_norm": 34.25,
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
  "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.1755018526.5a559ada2903.7360.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54cae92a3632b64c0e1832403853efdc2553aa573f6e1a61b0c058b482ba3980
3
- size 6111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7bf86350557e40718bdcd78b718f6f6bbd5e165e34a3c928f81e32066f461c
3
+ size 6525