Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
3707ed9
·
1 Parent(s): 0fc63f3

Checkpoint at step 100

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-60 → checkpoint-100}/config.json +0 -0
  2. checkpoints/{checkpoint-60 → checkpoint-100}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-60 → checkpoint-100}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-60 → checkpoint-100}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-60 → checkpoint-100}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-60 → checkpoint-100}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-60 → checkpoint-100}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-60 → checkpoint-100}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-60 → checkpoint-100}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-60 → checkpoint-100}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-60 → checkpoint-100}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1755018526.5a559ada2903.7360.0 +2 -2
checkpoints/{checkpoint-60 → checkpoint-100}/config.json RENAMED
File without changes
checkpoints/{checkpoint-60 → checkpoint-100}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-60 → checkpoint-100}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-60 → checkpoint-100}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db0cdd96fd408cd9f8e73c3dbbf00734b77c6dfb72c9b5a41b72f06ebff4f161
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1cbf50ea23906e6aca565b6ee91174c314bbe566b1e1b5803e936def1e79810
3
  size 4997867120
checkpoints/{checkpoint-60 → checkpoint-100}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c35a698d6fe8055364b4598ae4d8db5fe09aac512f9d899407546df26a4e766a
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4409d849b1e4cf95921b4f00ad93d6cdd468f5efa9189b19bb321e50bcf8ce1
3
  size 3856242664
checkpoints/{checkpoint-60 → checkpoint-100}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-60 → checkpoint-100}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff3f22ef0d9bf205a275a16ad19666d6a98d3dbab2c442245911eaa1b7055398
3
  size 25858106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ddbf4f1cd7d495dc794d4b957e0186183cc05d263b879fb5601b75ab461ae1a
3
  size 25858106
checkpoints/{checkpoint-60 → checkpoint-100}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-60 → checkpoint-100}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4829bd5085a30621b1c4179420abe78393ed12e8335dd018c0a92ec8489dbcb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a011c158d00fd21dc5b92c88da949c1deb5c014aa9d9a679b087568210811bf
3
  size 1064
checkpoints/{checkpoint-60 → checkpoint-100}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.0029433948380213027,
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,
@@ -50,6 +50,34 @@
50
  "learning_rate": 9.646827992151733e-07,
51
  "loss": 105.676,
52
  "step": 60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  }
54
  ],
55
  "logging_steps": 10,
@@ -69,7 +97,7 @@
69
  "attributes": {}
70
  }
71
  },
72
- "total_flos": 1.6096442745618432e+17,
73
  "train_batch_size": 2,
74
  "trial_name": null,
75
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.004905658063368838,
6
  "eval_steps": 500,
7
+ "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
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
+ "epoch": 0.0044150922570319545,
70
+ "grad_norm": 34.5,
71
+ "learning_rate": 1.4551994767822106e-06,
72
+ "loss": 105.1578,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.004905658063368838,
77
+ "grad_norm": 37.75,
78
+ "learning_rate": 1.618705035971223e-06,
79
+ "loss": 105.5959,
80
+ "step": 100
81
  }
82
  ],
83
  "logging_steps": 10,
 
97
  "attributes": {}
98
  }
99
  },
100
+ "total_flos": 2.682740457603072e+17,
101
  "train_batch_size": 2,
102
  "trial_name": null,
103
  "trial_params": null
checkpoints/{checkpoint-60 → checkpoint-100}/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:d80254d4c153ef4bd4fd22f9ebc4b956e0513a3f30c572855ca39a33569c36c0
3
- size 6939
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ca3cb47d3945f64625637c9d3916df0da4f4481f773389a2f43c2670adb233
3
+ size 7353