Hugging Face's logo

Hanzalwi
/
bloom-1b-finetuned-aings-validation-automatic-try-3

PEFT
TensorBoard
Safetensors
bloom
Model card Files
xet
 Metrics Community
Hanzalwi commited on
Commit
e51fcf5
·
1 Parent(s): 752741f

Training in progress, step 2000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +19 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b934623644b2cad72bce18be279967285a692175ebd40ccea73ffe3ed34434f
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681b2d24ea28ee82e6aae8302d1382a0f77801f9e454db5217e47a9a66bc37bf
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc16809c7607f921c1b36704dd4b322eed592cf003c38877592000a5dfcef12e
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def6fc0dd6afafd9683b85026dd4b02c505c3ac9637eb824f80b7e3df0b7d2b7
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a82d713e666f36b9ace8a6054cfde823b8feae9a07812ff4e3a4e51f579dbc1
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8270fb5b98b86da8550d75dc7fb5d84906b144754ea3444bb49fbaae1ee321
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8645176887512207,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 2.6988636363636362,
5
  "eval_steps": 100,
6
- "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -273,6 +273,20 @@
273
  "eval_samples_per_second": 18.99,
274
  "eval_steps_per_second": 2.38,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
@@ -280,7 +294,7 @@
280
  "num_input_tokens_seen": 0,
281
  "num_train_epochs": 3,
282
  "save_steps": 100,
283
- "total_flos": 5.78668418399232e+16,
284
  "trial_name": null,
285
  "trial_params": null
286
  }
 
1
  {
2
+ "best_metric": 1.8587623834609985,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 2.840909090909091,
5
  "eval_steps": 100,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
273
  "eval_samples_per_second": 18.99,
274
  "eval_steps_per_second": 2.38,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 2.84,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.981,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 2.84,
285
+ "eval_loss": 1.8587623834609985,
286
+ "eval_runtime": 78.4761,
287
+ "eval_samples_per_second": 19.012,
288
+ "eval_steps_per_second": 2.383,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
 
294
  "num_input_tokens_seen": 0,
295
  "num_train_epochs": 3,
296
  "save_steps": 100,
297
+ "total_flos": 6.090842007484416e+16,
298
  "trial_name": null,
299
  "trial_params": null
300
  }