rendchevi commited on
Commit
ae10fef
·
verified ·
1 Parent(s): ae07e31

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3e4cf0f4856a6e6f56b18e9e50d8071fba50d1de4c9a3651203574256ed0771
3
  size 5923472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b4c341c1f6e38b018a91527e20a50a8a47fba3fc594cc9eac764c40c6a664f
3
  size 5923472
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eb98fa47c71554c71d92d77f55240183681222d6e4028c7b5c84c9f2c7187df
3
  size 15380683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0a75270c4c1aab635aa24596f87bb5eb324c9f3e368c579b1b66508e7d696c5
3
  size 15380683
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27ab3f95bb1ac111e6efedaa17909ea89e5e838d4cebcb0588f8b31b70905244
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb67c0079b7a0236a758f25c62f579a989df8e152ab878b9e35a57181641f39
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a53320edab235c21487b7069195478dd15c40c497eb77473a2fb8b3a6590567
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca08c3f20018396cb1b58625cf16f0249c311373253deb820f8c47c2bac784ba
3
  size 1465
last-checkpoint/speaker_projector.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ee44fd22d08d8f0309e043c5e9020904117477da52a3e9080818b67fd1a8dcc
3
  size 1710977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4523af57f0e547436d2a2a2e23a3094b3fbb9b4183b1f6a530cbee4b52b8fa8f
3
  size 1710977
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.256,
6
  "eval_steps": 100,
7
- "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -23,6 +23,21 @@
23
  "eval_samples_per_second": 115.95,
24
  "eval_steps_per_second": 14.517,
25
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  ],
28
  "logging_steps": 100,
@@ -42,7 +57,7 @@
42
  "attributes": {}
43
  }
44
  },
45
- "total_flos": 5009860711845888.0,
46
  "train_batch_size": 8,
47
  "trial_name": null,
48
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.512,
6
  "eval_steps": 100,
7
+ "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
23
  "eval_samples_per_second": 115.95,
24
  "eval_steps_per_second": 14.517,
25
  "step": 100
26
+ },
27
+ {
28
+ "epoch": 0.512,
29
+ "grad_norm": 0.14562372863292694,
30
+ "learning_rate": 9.998009998009998e-05,
31
+ "loss": 6.89924072265625,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.512,
36
+ "eval_loss": 6.9076080322265625,
37
+ "eval_runtime": 21.3341,
38
+ "eval_samples_per_second": 117.184,
39
+ "eval_steps_per_second": 14.671,
40
+ "step": 200
41
  }
42
  ],
43
  "logging_steps": 100,
 
57
  "attributes": {}
58
  }
59
  },
60
+ "total_flos": 1.0038252361580544e+16,
61
  "train_batch_size": 8,
62
  "trial_name": null,
63
  "trial_params": null