Hugging Face's logo

bhuvanmdev
/
falcon-7b-chess-beta

Transformers
TensorBoard
Safetensors
Model card Files
xet
Metrics Community
bhuvanmdev commited on
Commit
5b9499c
·
verified ·
1 Parent(s): d88eecd

Training in progress, step 410, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +0 -0
  4. last-checkpoint/scheduler.pt +0 -0
  5. last-checkpoint/trainer_state.json +11 -4
  6. last-checkpoint/training_args.bin +0 -0
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19ed79b11216a51a61c91ceb6718a283c1617543152b0ba5f4b575170cbc1765
3
  size 1316913776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11b8289b6979a3a9ed14a7accec5c01d78ed8b59f16ef55d63813d0fb7d3b90
3
  size 1316913776
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79e122fe10c25f35bb9aa91f429c7959bcc622d43d2158400d186b24f4a4c6df
3
  size 8908124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702d79b9a60168e54a3dba75dd6d7584064140c012b5c05650563b846a20f797
3
  size 8908124
last-checkpoint/rng_state.pth CHANGED
Binary files a/last-checkpoint/rng_state.pth and b/last-checkpoint/rng_state.pth differ
 
last-checkpoint/scheduler.pt CHANGED
Binary files a/last-checkpoint/scheduler.pt and b/last-checkpoint/scheduler.pt differ
 
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.08587376556462001,
5
  "eval_steps": 500,
6
- "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -287,14 +287,21 @@
287
  "learning_rate": 0.00045706311721769,
288
  "loss": 0.8542,
289
  "step": 400
 
 
 
 
 
 
 
290
  }
291
  ],
292
  "logging_steps": 10,
293
  "max_steps": 4658,
294
  "num_input_tokens_seen": 0,
295
  "num_train_epochs": 1,
296
- "save_steps": 30,
297
- "total_flos": 2.976872891771059e+16,
298
  "train_batch_size": 3,
299
  "trial_name": null,
300
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.08802060970373551,
5
  "eval_steps": 500,
6
+ "global_step": 410,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
287
  "learning_rate": 0.00045706311721769,
288
  "loss": 0.8542,
289
  "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.08802060970373551,
293
+ "grad_norm": 1.278136968612671,
294
+ "learning_rate": 0.00045598969514813227,
295
+ "loss": 0.8485,
296
+ "step": 410
297
  }
298
  ],
299
  "logging_steps": 10,
300
  "max_steps": 4658,
301
  "num_input_tokens_seen": 0,
302
  "num_train_epochs": 1,
303
+ "save_steps": 10,
304
+ "total_flos": 3.0559577475303936e+16,
305
  "train_batch_size": 3,
306
  "trial_name": null,
307
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
Binary files a/last-checkpoint/training_args.bin and b/last-checkpoint/training_args.bin differ