Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
c6fc914
·
1 Parent(s): b201f36

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.1756423478.a504719e5285.5303.0 +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:c5a982c74190fc69ae25d1f70d2c907d4344f8243e2865f7ae7d4845cf3b1592
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1089598fbbb6f42b40c814d31bde5be78a9aa6b9e1d526deecac6341630b1dbb
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 sha256:174d662d79a9dad5480e1df1b79dc2a6765be9c7bb669b113a67a1ea3d105af5
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5fa112c67dad1fe88ed491b543147a93367b9895a08c34c1cab77a38255157
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 sha256:7cea09e8640ec22a2fe51a39998e7729d3b36207f8cc3e096fc4f2c805e86035
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583766715e9d087db5ea3d414a714aed34c29f8a9aa087daf8f91541d3045939
3
  size 25858571
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:d484e81fa22cdbcf66c2585a42950fa1db3e6db36dd8936a72f76c2844202008
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1667f35815259ae6fd1ff856a03958895cb054d32709d591bfa61b2107504cb1
3
  size 1465
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": 104.4941,
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": 104.4941,
66
  "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0044150922570319545,
70
+ "grad_norm": 40.0,
71
+ "learning_rate": 1.4551994767822106e-06,
72
+ "loss": 104.7141,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.004905658063368838,
77
+ "grad_norm": 41.5,
78
+ "learning_rate": 1.618705035971223e-06,
79
+ "loss": 104.9211,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.005396223869705722,
84
+ "grad_norm": 51.25,
85
+ "learning_rate": 1.7822105951602354e-06,
86
+ "loss": 103.7137,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0058867896760426055,
91
+ "grad_norm": 39.5,
92
+ "learning_rate": 1.945716154349248e-06,
93
+ "loss": 105.1651,
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.1756423478.a504719e5285.5303.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ecf2532e683eb82d26fb1c501b3d6e50b658dece5a98a9708c44abd77fdc2c2
3
- size 7314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94ddd6f3ce5a34609e4a30b2a802bed19dba49401dd1ae7e88295d6021db591
3
+ size 7728