Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
b201f36
·
1 Parent(s): 6150d3a

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.1756423478.a504719e5285.5303.0 +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 sha256:62b255e3590d937fef59bd217502b38b8c9f62ae8ee4b024bf4c4fec24bcfdd8
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2a7dd8f4b6011ef5f44ba373ff1dcd8757c035c7047c8e7af8bd84d5e39882
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 sha256:381d3fde8dd31775cd472861838fb01e4a32241511c0855958236a5b49b1e55b
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bcb4c83a6f9f83bfc8618f5026dd78a3d7a7961af385dd09494f5e905dae20
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 sha256:307798a811f1a52083432f959ed0706dbdf54ac8b32047f4d820852afd78bf61
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d3b502cc4419b44570d5077db62780d22ad4dcdd51b2d3ac3539385b2fb954
3
  size 25858571
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 sha256:6e1be529198179cd559ddcb4c59a9f665944a456be4a70f4f5dcf79350fe0534
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528392556c02087909bc6166c540e006acf7c36a66f3053e5688b159ec58a0e0
3
  size 1465
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": 104.8549,
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": 104.8549,
52
  "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.003433960644358187,
56
+ "grad_norm": 35.5,
57
+ "learning_rate": 1.1281883584041859e-06,
58
+ "loss": 103.9609,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.00392452645069507,
63
+ "grad_norm": 37.25,
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
  "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.1756423478.a504719e5285.5303.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52392e9a4b3e1c6d8df347aa91bba441e6b320951e784461aa04460fbf9c5246
3
- size 6900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ecf2532e683eb82d26fb1c501b3d6e50b658dece5a98a9708c44abd77fdc2c2
3
+ size 7314