Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
9642275
·
1 Parent(s): c6fc914

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.1756423478.a504719e5285.5303.0 +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 sha256:2f2a7dd8f4b6011ef5f44ba373ff1dcd8757c035c7047c8e7af8bd84d5e39882
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32110972218ba3abedfd7671f47d5e43f15718498bf0bb60d5cd78a463817ba
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 sha256:46bcb4c83a6f9f83bfc8618f5026dd78a3d7a7961af385dd09494f5e905dae20
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924777504dd3e6a52ff8acc7e9f0371e249ad93cae127d74aec5443cbe1ce5c8
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 sha256:88d3b502cc4419b44570d5077db62780d22ad4dcdd51b2d3ac3539385b2fb954
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62ef29820904a4e960951681d8f8f70933c3aa68af5642277d8a7f1b05826a3
3
  size 25858571
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 sha256:528392556c02087909bc6166c540e006acf7c36a66f3053e5688b159ec58a0e0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec75cf6ac19343a75daf1406106e27065bad1d0cafbfb1bdf22f7c2520d0b45
3
  size 1465
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": 104.9211,
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": 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
+ "epoch": 0.006377355482379489,
98
+ "grad_norm": 37.75,
99
+ "learning_rate": 2.1092217135382606e-06,
100
+ "loss": 105.2588,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.006867921288716374,
105
+ "grad_norm": 38.25,
106
+ "learning_rate": 2.2727272727272728e-06,
107
+ "loss": 104.3058,
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.1756423478.a504719e5285.5303.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f94ddd6f3ce5a34609e4a30b2a802bed19dba49401dd1ae7e88295d6021db591
3
- size 7728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc912cce9c971c2228a279552d23f535c7f9e93d9f8fc1310ecb3a06c65cbcdb
3
+ size 8150