Hugging Face's logo

Saeedabdf
/
gemma2-27b-biomedical-5k

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Community
Saeedabdf commited on
Commit
0ba52dd
·
verified ·
1 Parent(s): 1e1c491

Training in progress, step 1084, checkpoint

Browse files
Files changed (7) hide show
  1. last-checkpoint/adapter_config.json +5 -5
  2. last-checkpoint/adapter_model.safetensors +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/rng_state.pth +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +32 -4
  7. last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "up_proj",
25
  "v_proj",
26
- "k_proj",
27
  "gate_proj",
28
- "o_proj",
29
- "down_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
 
24
  "v_proj",
 
25
  "gate_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c99f0910b1d464cc9dd34ad013a78fc83c4e0e247274aa55f8ab30adb94fafd5
3
  size 1826969312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e945ecb1105ccbd7db50609dd1debf061390155256fb3e7e171d4e4ff5c5cb3f
3
  size 1826969312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e232076aca1d3fcd682dcf1388b713a0cf363f3d1c8f2c12a286c416a372802
3
  size 917657642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7608df305ea5de432c6e9824330a963c962321810e1114f34ce97e8baf43cd
3
  size 917657642
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac0420f99ddd52aad9a6f9534d329d57d42e52c6afff3a202493d8fac4921ba2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14bf956cf6d8fbb7489f32fd451c5aa20421badd8b0dbc258528eb49d130239
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5204f9ec8b9d069eef9619035e1e46f89a9b2b30dc326e967f107c3b83b63f3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50942b3c969aa466776eba40c03ac32e185a5fec3820381b12aaaffc91809f9f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.5745736360549927,
3
  "best_model_checkpoint": "/checkpoints/gemma2-27b-biomedical/checkpoint-500",
4
- "epoch": 1.8445930366612866,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -437,6 +437,34 @@
437
  "eval_samples_per_second": 0.685,
438
  "eval_steps_per_second": 0.685,
439
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
440
  }
441
  ],
442
  "logging_steps": 20,
@@ -451,12 +479,12 @@
451
  "should_evaluate": false,
452
  "should_log": false,
453
  "should_save": true,
454
- "should_training_stop": false
455
  },
456
  "attributes": {}
457
  }
458
  },
459
- "total_flos": 2.605468946006016e+18,
460
  "train_batch_size": 1,
461
  "trial_name": null,
462
  "trial_params": null
 
1
  {
2
  "best_metric": 1.5745736360549927,
3
  "best_model_checkpoint": "/checkpoints/gemma2-27b-biomedical/checkpoint-500",
4
+ "epoch": 1.9997694258704173,
5
  "eval_steps": 100,
6
+ "global_step": 1084,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
437
  "eval_samples_per_second": 0.685,
438
  "eval_steps_per_second": 0.685,
439
  "step": 1000
440
+ },
441
+ {
442
+ "epoch": 1.8817154715240951,
443
+ "grad_norm": 0.5792846083641052,
444
+ "learning_rate": 1.824312967136299e-06,
445
+ "loss": 1.1208,
446
+ "step": 1020
447
+ },
448
+ {
449
+ "epoch": 1.9186073322573207,
450
+ "grad_norm": 0.6999746561050415,
451
+ "learning_rate": 8.636614587030356e-07,
452
+ "loss": 1.1133,
453
+ "step": 1040
454
+ },
455
+ {
456
+ "epoch": 1.9554991929905463,
457
+ "grad_norm": 0.6022835373878479,
458
+ "learning_rate": 2.572175119379683e-07,
459
+ "loss": 1.1469,
460
+ "step": 1060
461
+ },
462
+ {
463
+ "epoch": 1.9923910537237721,
464
+ "grad_norm": 0.6285136342048645,
465
+ "learning_rate": 7.1479108360916754e-09,
466
+ "loss": 1.1502,
467
+ "step": 1080
468
  }
469
  ],
470
  "logging_steps": 20,
 
479
  "should_evaluate": false,
480
  "should_log": false,
481
  "should_save": true,
482
+ "should_training_stop": true
483
  },
484
  "attributes": {}
485
  }
486
  },
487
+ "total_flos": 2.8243283374705213e+18,
488
  "train_batch_size": 1,
489
  "trial_name": null,
490
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d72e5e897f7eeedb9a537d5a8eb67237cc9f0dc00099162f6e856b5955d6dfe
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84391dd2b6644a409861092551791dc6672e3d530edb0e666c77c87dd747030
3
  size 5496