ramdhanfirdaus commited on
Commit
fb9b386
1 Parent(s): c82ae5a

Training in progress, step 4000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:008cfe17180c9e4b9c257ad3d4c55cad934a8947cbf38d41aa7c9d165dd8e322
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753b925b93d925f0a579d0c1330b0dc96686bc1b39cc5c6ddbd853b341e2ebfe
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03da902808b21c37e32d452915b5124b94819e6cf999eea442d20ed434937b50
3
  size 151032837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2573bf0cb15641248a84bee29d6360bce0d4d8db72ab845cbcd44a67fb176346
3
  size 151032837
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1b836b0763d8c8c7392ab9bf480880e0c4fd0fbff6b82477d0ff13a6bddc661
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6135dea6869e11c78000d3b6bc11b1b1ade2c0fc5925996274588326a90a2389
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1067975759506226,
3
- "best_model_checkpoint": "./outputs/checkpoint-3900",
4
- "epoch": 2.8422586520947175,
5
  "eval_steps": 100,
6
- "global_step": 3900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -553,13 +553,27 @@
553
  "eval_samples_per_second": 18.397,
554
  "eval_steps_per_second": 2.302,
555
  "step": 3900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
556
  }
557
  ],
558
  "logging_steps": 100,
559
  "max_steps": 4116,
560
  "num_train_epochs": 3,
561
  "save_steps": 100,
562
- "total_flos": 1.2644892278408356e+18,
563
  "trial_name": null,
564
  "trial_params": null
565
  }
 
1
  {
2
+ "best_metric": 1.0958919525146484,
3
+ "best_model_checkpoint": "./outputs/checkpoint-4000",
4
+ "epoch": 2.9151183970856103,
5
  "eval_steps": 100,
6
+ "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
553
  "eval_samples_per_second": 18.397,
554
  "eval_steps_per_second": 2.302,
555
  "step": 3900
556
+ },
557
+ {
558
+ "epoch": 2.92,
559
+ "learning_rate": 0.0002,
560
+ "loss": 1.0811,
561
+ "step": 4000
562
+ },
563
+ {
564
+ "epoch": 2.92,
565
+ "eval_loss": 1.0958919525146484,
566
+ "eval_runtime": 340.8306,
567
+ "eval_samples_per_second": 18.408,
568
+ "eval_steps_per_second": 2.303,
569
+ "step": 4000
570
  }
571
  ],
572
  "logging_steps": 100,
573
  "max_steps": 4116,
574
  "num_train_epochs": 3,
575
  "save_steps": 100,
576
+ "total_flos": 1.2969094154866883e+18,
577
  "trial_name": null,
578
  "trial_params": null
579
  }