Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
e54f228
·
1 Parent(s): 2906c95

Checkpoint at step 180

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-140 → checkpoint-180}/config.json +0 -0
  2. checkpoints/{checkpoint-140 → checkpoint-180}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-140 → checkpoint-180}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-140 → checkpoint-180}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-140 → checkpoint-180}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-140 → checkpoint-180}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-140 → checkpoint-180}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-140 → checkpoint-180}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-140 → checkpoint-180}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-140 → checkpoint-180}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-140 → checkpoint-180}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1756423478.a504719e5285.5303.0 +2 -2
checkpoints/{checkpoint-140 → checkpoint-180}/config.json RENAMED
File without changes
checkpoints/{checkpoint-140 → checkpoint-180}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-140 → checkpoint-180}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-140 → checkpoint-180}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c32110972218ba3abedfd7671f47d5e43f15718498bf0bb60d5cd78a463817ba
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01436b4d42fda5d0bd0d432be152b8e6daabace008a2a4da7d4c2e8a915bd5e3
3
  size 4997867120
checkpoints/{checkpoint-140 → checkpoint-180}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:924777504dd3e6a52ff8acc7e9f0371e249ad93cae127d74aec5443cbe1ce5c8
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9ae8bf67c3bc47b9ab02d718c36a60a55e1c70c350263103f0ade87ffd9fea
3
  size 3856242664
checkpoints/{checkpoint-140 → checkpoint-180}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-140 → checkpoint-180}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f62ef29820904a4e960951681d8f8f70933c3aa68af5642277d8a7f1b05826a3
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771746457b9e30a4a761ccd9f8ff96ca483dc4254e444cf3492b51bae79c89f5
3
  size 25858571
checkpoints/{checkpoint-140 → checkpoint-180}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-140 → checkpoint-180}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ec75cf6ac19343a75daf1406106e27065bad1d0cafbfb1bdf22f7c2520d0b45
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f3ab58c9031d91773d2c8c3447bb956d8f767db5abb240824f416347b50270
3
  size 1465
checkpoints/{checkpoint-140 → checkpoint-180}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.006867921288716374,
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,
@@ -106,6 +106,34 @@
106
  "learning_rate": 2.2727272727272728e-06,
107
  "loss": 104.3058,
108
  "step": 140
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
110
  ],
111
  "logging_steps": 10,
@@ -125,7 +153,7 @@
125
  "attributes": {}
126
  }
127
  },
128
- "total_flos": 3.755836640644301e+17,
129
  "train_batch_size": 2,
130
  "trial_name": null,
131
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.008830184514063909,
6
  "eval_steps": 500,
7
+ "global_step": 180,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
106
  "learning_rate": 2.2727272727272728e-06,
107
  "loss": 104.3058,
108
  "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.007358487095053257,
112
+ "grad_norm": 40.0,
113
+ "learning_rate": 2.4362328319162854e-06,
114
+ "loss": 104.7016,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.00784905290139014,
119
+ "grad_norm": 41.0,
120
+ "learning_rate": 2.5997383911052975e-06,
121
+ "loss": 103.8965,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.008339618707727025,
126
+ "grad_norm": 41.0,
127
+ "learning_rate": 2.76324395029431e-06,
128
+ "loss": 105.4974,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.008830184514063909,
133
+ "grad_norm": 32.5,
134
+ "learning_rate": 2.9267495094833227e-06,
135
+ "loss": 104.178,
136
+ "step": 180
137
  }
138
  ],
139
  "logging_steps": 10,
 
153
  "attributes": {}
154
  }
155
  },
156
+ "total_flos": 4.8289328236855296e+17,
157
  "train_batch_size": 2,
158
  "trial_name": null,
159
  "trial_params": null
checkpoints/{checkpoint-140 → checkpoint-180}/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 sha256:8dbea690e061baa450cf674bd6e421f7e190ad7bc183e118e9f19c9bcc140e4f
3
- size 8572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a3c705e90d2d98003762e017b790b1ba73a317bad09cfaaca8257fc303f469
3
+ size 8994