Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
80b173c
·
1 Parent(s): 3707ed9

Checkpoint at step 120

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-80 → checkpoint-120}/config.json +0 -0
  2. checkpoints/{checkpoint-80 → checkpoint-120}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-80 → checkpoint-120}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-80 → checkpoint-120}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-80 → checkpoint-120}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-80 → checkpoint-120}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-80 → checkpoint-120}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-80 → checkpoint-120}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-80 → checkpoint-120}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-80 → checkpoint-120}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-80 → checkpoint-120}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1755018526.5a559ada2903.7360.0 +2 -2
checkpoints/{checkpoint-80 → checkpoint-120}/config.json RENAMED
File without changes
checkpoints/{checkpoint-80 → checkpoint-120}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-80 → checkpoint-120}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-80 → checkpoint-120}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:142626e4ad2789afdd7075a838be6094f6107528b999e8002e1027622b23f0c1
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5615c30ffbef9dcbabbb88bdf8bda5de53e109059695928c3e80ed7c5c536c5d
3
  size 4997867120
checkpoints/{checkpoint-80 → checkpoint-120}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bd33f1984554267aa9d48bff67d553952e8032dbe8adb7c06bbe0a8a31b7db1
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8250cb53fc35a98fe7145aa158861fe045df6cff246a01758c8d8c176d0937b
3
  size 3856242664
checkpoints/{checkpoint-80 → checkpoint-120}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-80 → checkpoint-120}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29f7b14cc2a8bd8b73bb73764b511fcbd053b47899d5940eddfdf19db2b2088b
3
  size 25858106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a241ff062993549ac49fa24163cf51992066e992da6820a9e3149bc642bcbf0
3
  size 25858106
checkpoints/{checkpoint-80 → checkpoint-120}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-80 → checkpoint-120}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fc4bf1eb43aa71b43dcab4b0a40f3988ed0b4e5e64e925b2c6a74673e559af6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c9fedc86646e64b96512db063b15c14c85acb4804f8449868608613e4e35e1c
3
  size 1064
checkpoints/{checkpoint-80 → checkpoint-120}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.00392452645069507,
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,
@@ -64,6 +64,34 @@
64
  "learning_rate": 1.2916939175931983e-06,
65
  "loss": 105.8347,
66
  "step": 80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  }
68
  ],
69
  "logging_steps": 10,
@@ -83,7 +111,7 @@
83
  "attributes": {}
84
  }
85
  },
86
- "total_flos": 2.1461923660824576e+17,
87
  "train_batch_size": 2,
88
  "trial_name": null,
89
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.0058867896760426055,
6
  "eval_steps": 500,
7
+ "global_step": 120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
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
+ "epoch": 0.005396223869705722,
84
+ "grad_norm": 38.75,
85
+ "learning_rate": 1.7822105951602354e-06,
86
+ "loss": 104.6849,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0058867896760426055,
91
+ "grad_norm": 36.75,
92
+ "learning_rate": 1.945716154349248e-06,
93
+ "loss": 106.1561,
94
+ "step": 120
95
  }
96
  ],
97
  "logging_steps": 10,
 
111
  "attributes": {}
112
  }
113
  },
114
+ "total_flos": 3.2192885491236864e+17,
115
  "train_batch_size": 2,
116
  "trial_name": null,
117
  "trial_params": null
checkpoints/{checkpoint-80 → checkpoint-120}/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:b5ca3cb47d3945f64625637c9d3916df0da4f4481f773389a2f43c2670adb233
3
- size 7353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb8ca0dcf5e382c5a79c7f886f3a168c28af6d24a2d4a012ba910412f9694bb
3
+ size 7767