ramdhanfirdaus commited on
Commit
80fd4c1
1 Parent(s): 03f024d

Training in progress, step 3200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fde2cd0cf6d40cb850b65d1bc5d18b30cd332d6d9c120818d3fc4a0e538baa40
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c10ad5672fa6956bbf04c1b96fd2b2719147a5e664f4f9009b8fe97dc82e8b
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:665a1e527fd239417ff50a71f133d7f3a3697d1ea1306dacc8961dd283167746
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08c7f6d071898b733f9f3b29ebde584ae43530e79c0cf46213b50657c839f7f
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab6b545b6dd6418e570a8474ea31c45a1baed67ab97da8014ad68491fbcf9bed
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a23ae123df196910708f98be91e053c8f90bebc5c98dc406a1231586d281c2
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1677733659744263,
3
- "best_model_checkpoint": "./outputs/checkpoint-3100",
4
- "epoch": 2.2586520947176685,
5
  "eval_steps": 100,
6
- "global_step": 3100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -441,13 +441,27 @@
441
  "eval_samples_per_second": 15.028,
442
  "eval_steps_per_second": 1.88,
443
  "step": 3100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
444
  }
445
  ],
446
  "logging_steps": 100,
447
  "max_steps": 4116,
448
  "num_train_epochs": 3,
449
  "save_steps": 100,
450
- "total_flos": 1.0050782869364552e+18,
451
  "trial_name": null,
452
  "trial_params": null
453
  }
 
1
  {
2
+ "best_metric": 1.1579593420028687,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3200",
4
+ "epoch": 2.3315118397085612,
5
  "eval_steps": 100,
6
+ "global_step": 3200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
441
  "eval_samples_per_second": 15.028,
442
  "eval_steps_per_second": 1.88,
443
  "step": 3100
444
+ },
445
+ {
446
+ "epoch": 2.33,
447
+ "learning_rate": 0.0002,
448
+ "loss": 1.1424,
449
+ "step": 3200
450
+ },
451
+ {
452
+ "epoch": 2.33,
453
+ "eval_loss": 1.1579593420028687,
454
+ "eval_runtime": 417.5279,
455
+ "eval_samples_per_second": 15.027,
456
+ "eval_steps_per_second": 1.88,
457
+ "step": 3200
458
  }
459
  ],
460
  "logging_steps": 100,
461
  "max_steps": 4116,
462
  "num_train_epochs": 3,
463
  "save_steps": 100,
464
+ "total_flos": 1.0374437719049441e+18,
465
  "trial_name": null,
466
  "trial_params": null
467
  }