sirr commited on
Commit
a101dab
·
1 Parent(s): b7d4dc5

Training in progress, step 75, 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:ef7c5fdf5c584660000ea3821b0bb343aca0d7717476e3554bd4e6c951b0d30f
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d666a08fef23c62f9a3ecaf1d217135fe422b2fee1d56b3afc6b22c9bbc99e3
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41204acad1a4b434195acd23753cdadaa20c395eb7c460191197a3f74cd64b84
3
  size 20523679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e105913d5c68de3e7f389f76d182450082efa0cdc3a3115098dd7d1aefd80576
3
  size 20523679
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c8311292e4146b3233f0266e7ef610ebcda88f45b44b712a3f6ad5d19f9b9ba
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe33e34af503c12cd87fbdfbf505826716bb5b7f0d5a5f98c0cab0c76832510
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:580778fd68e0d8e637510e0ef056731c045f25e773de2b6a07dd38c562cff05d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea85b8fac63ff44ec4935fba6e2515cdcedd1934fed8d2f32e1523cef467b4b
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": 0.5,
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,
@@ -33,13 +33,26 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.75,
5
  "eval_steps": 25,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
33
  "eval_samples_per_second": 1.843,
34
  "eval_steps_per_second": 0.157,
35
  "step": 50
36
+ },
37
+ {
38
+ "epoch": 0.75,
39
+ "learning_rate": 0.0001,
40
+ "loss": 0.6063,
41
+ "step": 75
42
+ },
43
+ {
44
+ "epoch": 0.75,
45
+ "eval_runtime": 216.6607,
46
+ "eval_samples_per_second": 1.846,
47
+ "eval_steps_per_second": 0.157,
48
+ "step": 75
49
  }
50
  ],
51
  "logging_steps": 25,
52
  "max_steps": 200,
53
  "num_train_epochs": 2,
54
  "save_steps": 25,
55
+ "total_flos": 1.24575811633152e+16,
56
  "trial_name": null,
57
  "trial_params": null
58
  }