ramdhanfirdaus commited on
Commit
94e6075
1 Parent(s): 3352eb8

Training in progress, step 2100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:875a6046929ba8a9549dba29f8469188fd8c89f509a85081e1c373e16072c5a1
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8055cb4f26cf5e8d49322026dd258337b0f420901583dcee2f62d717821fc0b2
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34f3fcc7e72cfb0d259964f7e8934904910e3b60c7eb54cb96ba7a0ac4612f34
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f548f5b9d86727a65b850c151162aac92f6f1c6dc1c47504a26058c1c4515f79
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:ffc6ea08601dbe5c18badfb79017e147843c03bc31496ad82a5d81166631f3cc
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf3dfe2b0743dc299fda05b770346eca15b64e6cdb8c75ee2df253ac9b11e04c
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2826957702636719,
3
- "best_model_checkpoint": "./outputs/checkpoint-2000",
4
- "epoch": 1.4571948998178508,
5
  "eval_steps": 100,
6
- "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -287,13 +287,27 @@
287
  "eval_samples_per_second": 14.003,
288
  "eval_steps_per_second": 1.752,
289
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
  }
291
  ],
292
  "logging_steps": 100,
293
  "max_steps": 4116,
294
  "num_train_epochs": 3,
295
  "save_steps": 100,
296
- "total_flos": 6.484823780480748e+17,
297
  "trial_name": null,
298
  "trial_params": null
299
  }
 
1
  {
2
+ "best_metric": 1.2710933685302734,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2100",
4
+ "epoch": 1.530054644808743,
5
  "eval_steps": 100,
6
+ "global_step": 2100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
287
  "eval_samples_per_second": 14.003,
288
  "eval_steps_per_second": 1.752,
289
  "step": 2000
290
+ },
291
+ {
292
+ "epoch": 1.53,
293
+ "learning_rate": 0.0002,
294
+ "loss": 1.2659,
295
+ "step": 2100
296
+ },
297
+ {
298
+ "epoch": 1.53,
299
+ "eval_loss": 1.2710933685302734,
300
+ "eval_runtime": 417.5822,
301
+ "eval_samples_per_second": 15.025,
302
+ "eval_steps_per_second": 1.88,
303
+ "step": 2100
304
  }
305
  ],
306
  "logging_steps": 100,
307
  "max_steps": 4116,
308
  "num_train_epochs": 3,
309
  "save_steps": 100,
310
+ "total_flos": 6.808998544825129e+17,
311
  "trial_name": null,
312
  "trial_params": null
313
  }