sirr commited on
Commit
c91b256
·
1 Parent(s): 5abeaef

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a97e01168bb7705aceb33e32e0e4e3d587f3e1163b2c422a18c4e5807a1ccdc
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7c5fdf5c584660000ea3821b0bb343aca0d7717476e3554bd4e6c951b0d30f
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8851a73de47dbfcfe31de86bb6192dfb9990a4ac4a46f2f7ab1302c1c78989d2
3
  size 20523679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41204acad1a4b434195acd23753cdadaa20c395eb7c460191197a3f74cd64b84
3
  size 20523679
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3029f8fdae5b5a1515326241e0c15afad3612dc0f653bb9b6b93ae183483db93
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8311292e4146b3233f0266e7ef610ebcda88f45b44b712a3f6ad5d19f9b9ba
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01bd1906bbea59f9e9fca9d2fcebc7d848ace4b2b715eed5519ef909ccf2df1c
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:580778fd68e0d8e637510e0ef056731c045f25e773de2b6a07dd38c562cff05d
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.25,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -20,13 +20,26 @@
20
  "eval_samples_per_second": 1.846,
21
  "eval_steps_per_second": 0.157,
22
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "logging_steps": 25,
26
  "max_steps": 200,
27
  "num_train_epochs": 2,
28
  "save_steps": 25,
29
- "total_flos": 4152527054438400.0,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
20
  "eval_samples_per_second": 1.846,
21
  "eval_steps_per_second": 0.157,
22
  "step": 25
23
+ },
24
+ {
25
+ "epoch": 0.5,
26
+ "learning_rate": 0.0001,
27
+ "loss": 0.6312,
28
+ "step": 50
29
+ },
30
+ {
31
+ "epoch": 0.5,
32
+ "eval_runtime": 217.0379,
33
+ "eval_samples_per_second": 1.843,
34
+ "eval_steps_per_second": 0.157,
35
+ "step": 50
36
  }
37
  ],
38
  "logging_steps": 25,
39
  "max_steps": 200,
40
  "num_train_epochs": 2,
41
  "save_steps": 25,
42
+ "total_flos": 8305054108876800.0,
43
  "trial_name": null,
44
  "trial_params": null
45
  }