ramdhanfirdaus commited on
Commit
94dcbb1
·
1 Parent(s): a7d3641

Training in progress, step 3900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7904de6f3a6c81434524363955086f270d6e1bc9602b5eb50481becd62e1c130
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bd53816dec1f54087c7a98a07ce3e939ca34b4f4b6d19c7d7deda012989e55
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24015c4376f4fabd69ec52827faf5405a347f818b5fb5e0c4305578d2a137c59
3
  size 100691721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00177b501de8ddd7c362d6cf0908f8399182383eaec609ad095a19b45401d4a1
3
  size 100691721
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6ef7c5a570735e8b6e72739891f16a22a1d772533cbc85af1fbd69a57a8ec31
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34985e8b1e69a205583c6b9115293e324729ed0c191fbcce181660393717f45d
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3516861200332642,
3
- "best_model_checkpoint": "./outputs/checkpoint-3800",
4
- "epoch": 2.769398907103825,
5
  "eval_steps": 100,
6
- "global_step": 3800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -539,13 +539,27 @@
539
  "eval_samples_per_second": 47.173,
540
  "eval_steps_per_second": 5.902,
541
  "step": 3800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
542
  }
543
  ],
544
  "logging_steps": 100,
545
  "max_steps": 4116,
546
  "num_train_epochs": 3,
547
  "save_steps": 100,
548
- "total_flos": 2.2625907263034163e+17,
549
  "trial_name": null,
550
  "trial_params": null
551
  }
 
1
  {
2
+ "best_metric": 1.340726613998413,
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,
 
539
  "eval_samples_per_second": 47.173,
540
  "eval_steps_per_second": 5.902,
541
  "step": 3800
542
+ },
543
+ {
544
+ "epoch": 2.84,
545
+ "learning_rate": 0.0002,
546
+ "loss": 1.3085,
547
+ "step": 3900
548
+ },
549
+ {
550
+ "epoch": 2.84,
551
+ "eval_loss": 1.340726613998413,
552
+ "eval_runtime": 132.9904,
553
+ "eval_samples_per_second": 47.176,
554
+ "eval_steps_per_second": 5.903,
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": 2.3221217626762445e+17,
563
  "trial_name": null,
564
  "trial_params": null
565
  }