ramdhanfirdaus commited on
Commit
0545251
1 Parent(s): d1d3d0b

Training in progress, step 2400, 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:cd9bfe3a61b9d671b668afd9854e6e0f31dd1bfaf2c496e8b646c13b4b667b83
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76536dee9747dec8dd1f3f3ccd41b7a1b9b67ceb8b29368eb6f6a461902249e1
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83d8eadc3f5112242fcda8091f4fe5bdcc4a798387065d67067a1d1908ed110a
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c49e4cfc2242be4175f2532f1dca5492fae7031c7b3a956c83903e4d55b47c
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91ce772f9b2a32aa1626e6ccbc135efad31ff1869adac26764a35a5c73bb1216
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec38c457da9a42258377534f1711dd182dc95cdf22873640757de0b8ac5fc68
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4158506393432617,
3
- "best_model_checkpoint": "./outputs/checkpoint-2300",
4
- "epoch": 1.6757741347905282,
5
  "eval_steps": 100,
6
- "global_step": 2300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -329,13 +329,27 @@
329
  "eval_samples_per_second": 43.624,
330
  "eval_steps_per_second": 5.458,
331
  "step": 2300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
332
  }
333
  ],
334
  "logging_steps": 100,
335
  "max_steps": 4116,
336
  "num_train_epochs": 3,
337
  "save_steps": 100,
338
- "total_flos": 1.3711720075820237e+17,
339
  "trial_name": null,
340
  "trial_params": null
341
  }
 
1
  {
2
+ "best_metric": 1.4019700288772583,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2400",
4
+ "epoch": 1.748633879781421,
5
  "eval_steps": 100,
6
+ "global_step": 2400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
329
  "eval_samples_per_second": 43.624,
330
  "eval_steps_per_second": 5.458,
331
  "step": 2300
332
+ },
333
+ {
334
+ "epoch": 1.75,
335
+ "learning_rate": 0.0002,
336
+ "loss": 1.4092,
337
+ "step": 2400
338
+ },
339
+ {
340
+ "epoch": 1.75,
341
+ "eval_loss": 1.4019700288772583,
342
+ "eval_runtime": 143.831,
343
+ "eval_samples_per_second": 43.621,
344
+ "eval_steps_per_second": 5.458,
345
+ "step": 2400
346
  }
347
  ],
348
  "logging_steps": 100,
349
  "max_steps": 4116,
350
  "num_train_epochs": 3,
351
  "save_steps": 100,
352
+ "total_flos": 1.430781883693056e+17,
353
  "trial_name": null,
354
  "trial_params": null
355
  }