Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
39a8774
·
1 Parent(s): e54f228

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.1756423478.a504719e5285.5303.0 +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 sha256:7a241063a39f1ff9a6cffbf934ac8f5410f497d18f46d2ce0d2c28579b8a0d78
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e21faaebae001426a76f6a3c25309632bba780041e37b7b0b22c610cbdcfbdf
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 sha256:5f7852608c5311f834372b7a4e2987475df5a4f5162eb68e6e35d2a5ec4f706a
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d42d85ae49df1bd0baaa04b9ee2464265f3ae089ed723ed7910b0a0721a2ae
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 sha256:3cd468102392da025529f8eb11dc3bc0ad37dcf17afae5eb6d4164d29b18a0b8
3
  size 25858571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba36ff3cf5aa103f2c5a162efe65287c247dccc43ee228fd9bcb3a14b6d695ae
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:acda1dbd18939debf680533b87259bb4016966fb65eb95873938a85d449a03f3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a87144f92021f7270fcad4a86cd226d4640d1deb1f882885045e9d8fc1212f
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": 103.8965,
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": 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
+ "epoch": 0.009320750320400792,
140
+ "grad_norm": 35.0,
141
+ "learning_rate": 3.090255068672335e-06,
142
+ "loss": 104.7224,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.009811316126737676,
147
+ "grad_norm": 40.5,
148
+ "learning_rate": 3.253760627861348e-06,
149
+ "loss": 105.291,
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.1756423478.a504719e5285.5303.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71a3c705e90d2d98003762e017b790b1ba73a317bad09cfaaca8257fc303f469
3
- size 8994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5944cae85a7f2e16f3337e67ae4abb612046cbe215fa9b725654b606220b44cd
3
+ size 9416