havinash-ai commited on
Commit
bffc072
·
verified ·
1 Parent(s): 05f53be

Training in progress, step 39, 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:cd23a4391d041aa98494dfeb17ce92f09f528ea0f0704518acfbc745e91dd82f
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec10ea63bbc7f60d7a55d56d76b2ed44e6cd758b49bf79ced40ff16984d2b94
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7514f59803526661ae61feabe3f3c1d385ea56e596ea259c74ac0f16466be787
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5dea273525115b1f3c9e9adc484d25289d1f2eb7f2940764c924fd533399bc
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d2d6bc08ef3abdbd8d1e9ebf2fe9eda911a26db8affa656809086ee10975bba
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f22ee2bd42680b5f198191658fb24f22c66fd0968ab26c6e7ce687248687a73
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0456140350877193,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 59.127,
46
  "eval_steps_per_second": 29.563,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1697668241817600.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06842105263157895,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 59.127,
46
  "eval_steps_per_second": 29.563,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.05263157894736842,
51
+ "grad_norm": 6.356601715087891,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 6.6724,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.06842105263157895,
58
+ "eval_loss": 1.6223626136779785,
59
+ "eval_runtime": 4.0474,
60
+ "eval_samples_per_second": 59.298,
61
+ "eval_steps_per_second": 29.649,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 2546502362726400.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null