Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
Charlie81 commited on
Commit
b61765b
·
1 Parent(s): ebae231

Checkpoint at step 200

Browse files
Files changed (12) hide show
  1. checkpoints/{checkpoint-160 → checkpoint-200}/config.json +0 -0
  2. checkpoints/{checkpoint-160 → checkpoint-200}/generation_config.json +0 -0
  3. checkpoints/{checkpoint-160 → checkpoint-200}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-160 → checkpoint-200}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-160 → checkpoint-200}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-160 → checkpoint-200}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-160 → checkpoint-200}/optimizer.pt +1 -1
  8. checkpoints/{checkpoint-160 → checkpoint-200}/rng_state.pth +0 -0
  9. checkpoints/{checkpoint-160 → checkpoint-200}/scheduler.pt +1 -1
  10. checkpoints/{checkpoint-160 → checkpoint-200}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-160 → checkpoint-200}/training_args.bin +0 -0
  12. logs/events.out.tfevents.1755708105.f52801bf383c.3138.0 +2 -2
checkpoints/{checkpoint-160 → checkpoint-200}/config.json RENAMED
File without changes
checkpoints/{checkpoint-160 → checkpoint-200}/generation_config.json RENAMED
File without changes
checkpoints/{checkpoint-160 → checkpoint-200}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-160 → checkpoint-200}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:362fba0f5440311d58f9742afb1011980e265ac400b841e48fcc86b73f8d75c4
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64eba0824f749668e63e4bebd2144d948f37509c73c0a6e005194f81266f89b
3
  size 4997867120
checkpoints/{checkpoint-160 → checkpoint-200}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:936916f03e1eed79db8c330d0ca13b451cdf9bef259f446c282d75dab47e7f75
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f850ced2844955f8a3c6042bf242458bb14dbc8b79f78cdf0740e75a3ea5b9
3
  size 3856242664
checkpoints/{checkpoint-160 → checkpoint-200}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-160 → checkpoint-200}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b104e341708a5ac49c5e7ed90179ee7dcea95f03745fe87c08cbcce45df982d2
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0250bddff29b4c260fb8c62749c611f98f1158690a33c40de9a2a99f017ff500
3
  size 25858571
checkpoints/{checkpoint-160 → checkpoint-200}/rng_state.pth RENAMED
File without changes
checkpoints/{checkpoint-160 → checkpoint-200}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9731ce17f2d0010b75e925e116d52b0e68917a8f0d0c747bbbecd19f5a908393
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d04ed7040a6b8e0b8ddcc91364b4f390e9a8347b10dc72c335fac537d9656ea
3
  size 1465
checkpoints/{checkpoint-160 → checkpoint-200}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.00784905290139014,
6
  "eval_steps": 500,
7
- "global_step": 160,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -120,6 +120,34 @@
120
  "learning_rate": 2.5997383911052975e-06,
121
  "loss": 105.0039,
122
  "step": 160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
123
  }
124
  ],
125
  "logging_steps": 10,
@@ -139,7 +167,7 @@
139
  "attributes": {}
140
  }
141
  },
142
- "total_flos": 4.292384732164915e+17,
143
  "train_batch_size": 2,
144
  "trial_name": null,
145
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.009811316126737676,
6
  "eval_steps": 500,
7
+ "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
120
  "learning_rate": 2.5997383911052975e-06,
121
  "loss": 105.0039,
122
  "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.008339618707727025,
126
+ "grad_norm": 33.0,
127
+ "learning_rate": 2.76324395029431e-06,
128
+ "loss": 106.5098,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.008830184514063909,
133
+ "grad_norm": 32.75,
134
+ "learning_rate": 2.9267495094833227e-06,
135
+ "loss": 104.8353,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.009320750320400792,
140
+ "grad_norm": 32.5,
141
+ "learning_rate": 3.090255068672335e-06,
142
+ "loss": 105.7017,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.009811316126737676,
147
+ "grad_norm": 36.0,
148
+ "learning_rate": 3.253760627861348e-06,
149
+ "loss": 105.7483,
150
+ "step": 200
151
  }
152
  ],
153
  "logging_steps": 10,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 5.365480915206144e+17,
171
  "train_batch_size": 2,
172
  "trial_name": null,
173
  "trial_params": null
checkpoints/{checkpoint-160 → checkpoint-200}/training_args.bin RENAMED
File without changes
logs/events.out.tfevents.1755708105.f52801bf383c.3138.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e936cf5c3bfc863a71e18e1ca29355a396cdc35a57fcc7e4c0037f5304d5f06
3
- size 6127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af98f7909cbd0c8a36a5a30a6585ce0a032f28c927f3d3d68717245a6017014c
3
+ size 6549