Hugging Face's logo

raqibcodes
/
c2c-checkpoints-v2

Transformers
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
 Community
raqibcodes commited on
Commit
2dfda03
·
verified ·
1 Parent(s): ceb739e

Training in progress, step 300

Browse files
Files changed (7) hide show
  1. adapter_model.safetensors +1 -1
  2. last-checkpoint/adapter_model.safetensors +2 -2
  3. last-checkpoint/optimizer.pt +2 -2
  4. last-checkpoint/rng_state.pth +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +5 -36
  7. last-checkpoint/training_args.bin +1 -1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ed9c25b5708706b6a0b740e4d5d39e9682269d0f82a597758060a5936fa63c
3
  size 139602808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c636041d5a39e5ba263480be2d95b989d0b2a2d8aaccd9baba04697672e7f5
3
  size 139602808
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ed9c25b5708706b6a0b740e4d5d39e9682269d0f82a597758060a5936fa63c
3
- size 139602808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabadd77bc689da500c9b7eda73f22b5f0612bb18ac452eb71eaa547de6076b2
3
+ size 69839888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25c4e222a4f31bf8d495402f1c8374be1d28a65bcd0806628a3c6fab8f020a4b
3
- size 279487343
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ddcaf4b49e6ae3a3e6bfed2eabe642fbe9475c2d5427243583e2339ea0754d1
3
+ size 139961199
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffa976baf87291d9fceae2498519d21057391d04b22c9721a4b3f7f4c2877fff
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45dcb26e076badfa1f9b7021eb697d18eae744725aec55db9cf2e55eb4872b0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e447966aa81e08b07c548e62a661f7d1a3227b13b3d4b1fdce5aa9ec131d06b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624edc83d795c4b4c219a679dcf9a8467dd8fc40fd38a2415b413d6849e9b256
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 175,
3
  "best_metric": 0.0012933596735820174,
4
  "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-175",
5
- "epoch": 2.75,
6
  "eval_steps": 25,
7
- "global_step": 275,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -318,43 +318,12 @@
318
  "eval_samples_per_second": 0.718,
319
  "eval_steps_per_second": 0.718,
320
  "step": 250
321
- },
322
- {
323
- "entropy": 0.9087011106312275,
324
- "epoch": 2.52,
325
- "grad_norm": 0.002573611680418253,
326
- "learning_rate": 3.920265780730897e-05,
327
- "loss": 0.0007128582801669836,
328
- "mean_token_accuracy": 1.0,
329
- "num_tokens": 3959.0,
330
- "step": 252
331
- },
332
- {
333
- "entropy": 0.924984677384297,
334
- "epoch": 2.64,
335
- "grad_norm": 0.0005084075382910669,
336
- "learning_rate": 3.122923588039867e-05,
337
- "loss": 0.0006440305539096395,
338
- "mean_token_accuracy": 1.0,
339
- "num_tokens": 26050.0,
340
- "step": 264
341
- },
342
- {
343
- "epoch": 2.75,
344
- "eval_entropy": 0.9374615728855134,
345
- "eval_loss": 0.001335766282863915,
346
- "eval_mean_token_accuracy": 0.9996986410021782,
347
- "eval_num_tokens": 45328.0,
348
- "eval_runtime": 252.969,
349
- "eval_samples_per_second": 0.791,
350
- "eval_steps_per_second": 0.791,
351
- "step": 275
352
  }
353
  ],
354
  "logging_steps": 12,
355
- "max_steps": 310,
356
  "num_input_tokens_seen": 0,
357
- "num_train_epochs": 4,
358
  "save_steps": 25,
359
  "stateful_callbacks": {
360
  "TrainerControl": {
@@ -368,7 +337,7 @@
368
  "attributes": {}
369
  }
370
  },
371
- "total_flos": 1.330615123911072e+16,
372
  "train_batch_size": 1,
373
  "trial_name": null,
374
  "trial_params": null
 
2
  "best_global_step": 175,
3
  "best_metric": 0.0012933596735820174,
4
  "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-175",
5
+ "epoch": 2.5,
6
  "eval_steps": 25,
7
+ "global_step": 250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
318
  "eval_samples_per_second": 0.718,
319
  "eval_steps_per_second": 0.718,
320
  "step": 250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
321
  }
322
  ],
323
  "logging_steps": 12,
324
+ "max_steps": 300,
325
  "num_input_tokens_seen": 0,
326
+ "num_train_epochs": 3,
327
  "save_steps": 25,
328
  "stateful_callbacks": {
329
  "TrainerControl": {
 
337
  "attributes": {}
338
  }
339
  },
340
+ "total_flos": 1.20860153697168e+16,
341
  "train_batch_size": 1,
342
  "trial_name": null,
343
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ce060488f05343f0437ad90e26b0a95fbf802432a19bd58f1082d6c190ec4c8
3
  size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d120c92ba91ddf4ca0253a099ee22d2291712c5f091a4855f1d947cb6f6a6059
3
  size 5713