ramdhanfirdaus commited on
Commit
a6c71d0
1 Parent(s): 1d68166

Training in progress, step 3300, 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:c7bc2843f0fd169ec0e697244a3a0a7452441a39e39f7afd090c6d3e821de63c
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129452df5b3c4db39242dc46567b4b76e0fee472c875a16d7b0a677459554e1f
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e5b83ea9b0e96c9eddfd2dd55a39acedc50bb6a8d05a56dd62e5474a554468f
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2186b4e72a0c8b9581a9f1fd64b77b87075f84d605783f258bf6ff56d2b1d5d6
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c5fb36a2763d3fef892adf419cc9436c9f330cbe7d391f0331a0f3f75f5135
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ecee011d9ea190091aa42a43d90b7c2a3d0f7b5ed88ab6e56f648d5f21aad0a
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3046828508377075,
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,
@@ -455,13 +455,27 @@
455
  "eval_samples_per_second": 43.613,
456
  "eval_steps_per_second": 5.457,
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": 1.9076371527344947e+17,
465
  "trial_name": null,
466
  "trial_params": null
467
  }
 
1
  {
2
+ "best_metric": 1.2920022010803223,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3300",
4
+ "epoch": 2.4043715846994536,
5
  "eval_steps": 100,
6
+ "global_step": 3300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
455
  "eval_samples_per_second": 43.613,
456
  "eval_steps_per_second": 5.457,
457
  "step": 3200
458
+ },
459
+ {
460
+ "epoch": 2.4,
461
+ "learning_rate": 0.0002,
462
+ "loss": 1.2715,
463
+ "step": 3300
464
+ },
465
+ {
466
+ "epoch": 2.4,
467
+ "eval_loss": 1.2920022010803223,
468
+ "eval_runtime": 143.7686,
469
+ "eval_samples_per_second": 43.64,
470
+ "eval_steps_per_second": 5.46,
471
+ "step": 3300
472
  }
473
  ],
474
  "logging_steps": 100,
475
  "max_steps": 4116,
476
  "num_train_epochs": 3,
477
  "save_steps": 100,
478
+ "total_flos": 1.9672423394930688e+17,
479
  "trial_name": null,
480
  "trial_params": null
481
  }