ramdhanfirdaus commited on
Commit
95ede48
1 Parent(s): f151776

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:570eb3dd12b84235f2eb1bab4b9692f783af04a8595d18e3c58f692bd0a0d54b
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875a6046929ba8a9549dba29f8469188fd8c89f509a85081e1c373e16072c5a1
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3862bf7351b4f10337ce1b12e0d0db786c5e6c8a0dfb3e0deb9831326baf84c9
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f3fcc7e72cfb0d259964f7e8934904910e3b60c7eb54cb96ba7a0ac4612f34
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33f46d5f46a39d3f20a23a4d774b317112c87965ce81d67ef582ca315c5d19ed
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc6ea08601dbe5c18badfb79017e147843c03bc31496ad82a5d81166631f3cc
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2934125661849976,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 1.384335154826958,
5
  "eval_steps": 100,
6
- "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -273,13 +273,27 @@
273
  "eval_samples_per_second": 15.019,
274
  "eval_steps_per_second": 1.879,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
279
  "max_steps": 4116,
280
  "num_train_epochs": 3,
281
  "save_steps": 100,
282
- "total_flos": 6.160625093682708e+17,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
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,
 
273
  "eval_samples_per_second": 15.019,
274
  "eval_steps_per_second": 1.879,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.276,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 1.2826957702636719,
286
+ "eval_runtime": 448.0598,
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
  }