sirr commited on
Commit
c1ac544
·
1 Parent(s): 7dc0558

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d666a08fef23c62f9a3ecaf1d217135fe422b2fee1d56b3afc6b22c9bbc99e3
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cc7f4de672c480450afd7b2ecc815f1a648886726cf5200264464ac63a58c3
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e105913d5c68de3e7f389f76d182450082efa0cdc3a3115098dd7d1aefd80576
3
  size 20523679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039637b8b389137879b303679fa583684724a9b94a0142e14cdaeabb5b2054f0
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:fbe33e34af503c12cd87fbdfbf505826716bb5b7f0d5a5f98c0cab0c76832510
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb439cc7745e50177086dc51c98138686500e54700396db181a6a504f1ce367
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ea85b8fac63ff44ec4935fba6e2515cdcedd1934fed8d2f32e1523cef467b4b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac50daf1bc36d76b3b1e01379287cfbfcbbe7ebea9864f699ceb21bbe636b01
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": 0.75,
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,
@@ -46,13 +46,26 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
  "eval_steps": 25,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
46
  "eval_samples_per_second": 1.846,
47
  "eval_steps_per_second": 0.157,
48
  "step": 75
49
+ },
50
+ {
51
+ "epoch": 1.0,
52
+ "learning_rate": 0.0001,
53
+ "loss": 0.5707,
54
+ "step": 100
55
+ },
56
+ {
57
+ "epoch": 1.0,
58
+ "eval_runtime": 216.7207,
59
+ "eval_samples_per_second": 1.846,
60
+ "eval_steps_per_second": 0.157,
61
+ "step": 100
62
  }
63
  ],
64
  "logging_steps": 25,
65
  "max_steps": 200,
66
  "num_train_epochs": 2,
67
  "save_steps": 25,
68
+ "total_flos": 1.66101082177536e+16,
69
  "trial_name": null,
70
  "trial_params": null
71
  }