Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
089f552
·
1 Parent(s): 80b173c

Checkpoint at step 140

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-100 → checkpoint-140}/config.json +0 -0
  2. checkpoints/{checkpoint-100 → checkpoint-140}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-100 → checkpoint-140}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-100 → checkpoint-140}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-100 → checkpoint-140}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-100 → checkpoint-140}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-100 → checkpoint-140}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-100 → checkpoint-140}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-100 → checkpoint-140}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-100 → checkpoint-140}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-100 → checkpoint-140}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1755018526.5a559ada2903.7360.0 +2 -2
checkpoints/{checkpoint-100 → checkpoint-140}/config.json RENAMED
File without changes
checkpoints/{checkpoint-100 → checkpoint-140}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-100 → checkpoint-140}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-100 → checkpoint-140}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1cbf50ea23906e6aca565b6ee91174c314bbe566b1e1b5803e936def1e79810
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355f962f78f8781b3d467703655d1c7083e37559d89537656334667d6ff43ac6
3
  size 4997867120
checkpoints/{checkpoint-100 → checkpoint-140}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4409d849b1e4cf95921b4f00ad93d6cdd468f5efa9189b19bb321e50bcf8ce1
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3290e61df182c456ab7a8001602656f7e39e16b98c91fcfe83c8e4e3260fe7b6
3
  size 3856242664
checkpoints/{checkpoint-100 → checkpoint-140}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-100 → checkpoint-140}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ddbf4f1cd7d495dc794d4b957e0186183cc05d263b879fb5601b75ab461ae1a
3
  size 25858106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce6a8e273e030a886d8273cc9f71fe6be48232fe77a2a0fdc93c82376838a8c4
3
  size 25858106
checkpoints/{checkpoint-100 → checkpoint-140}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-100 → checkpoint-140}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a011c158d00fd21dc5b92c88da949c1deb5c014aa9d9a679b087568210811bf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5924776f848b4794129dd6cb3c286820b39f53340b1f965e1166d4c08f2f0219
3
  size 1064
checkpoints/{checkpoint-100 → checkpoint-140}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.004905658063368838,
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,
@@ -78,6 +78,34 @@
78
  "learning_rate": 1.618705035971223e-06,
79
  "loss": 105.5959,
80
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
  }
82
  ],
83
  "logging_steps": 10,
@@ -97,7 +125,7 @@
97
  "attributes": {}
98
  }
99
  },
100
- "total_flos": 2.682740457603072e+17,
101
  "train_batch_size": 2,
102
  "trial_name": null,
103
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.006867921288716374,
6
  "eval_steps": 500,
7
+ "global_step": 140,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
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
+ "epoch": 0.006377355482379489,
98
+ "grad_norm": 34.25,
99
+ "learning_rate": 2.1092217135382606e-06,
100
+ "loss": 106.1261,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.006867921288716374,
105
+ "grad_norm": 32.75,
106
+ "learning_rate": 2.2727272727272728e-06,
107
+ "loss": 105.1263,
108
+ "step": 140
109
  }
110
  ],
111
  "logging_steps": 10,
 
125
  "attributes": {}
126
  }
127
  },
128
+ "total_flos": 3.755836640644301e+17,
129
  "train_batch_size": 2,
130
  "trial_name": null,
131
  "trial_params": null
checkpoints/{checkpoint-100 → checkpoint-140}/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 sha256:1bb8ca0dcf5e382c5a79c7f886f3a168c28af6d24a2d4a012ba910412f9694bb
3
- size 7767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bbabe07631a41bb5d447b8215478418b537372f2d1f2df33e459d25f7f20980
3
+ size 8189