pedrosperber760 commited on
Commit
5d9b678
·
verified ·
1 Parent(s): 3563266

Training in progress, step 6, 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:e572d11235b1593f63e471e76d6395ef3d87b6c936b006145c36fe380a813436
3
  size 619632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff7fe906f4008bca90ec8ad280c5c4820037d0958f5eb64a38d2d14d0979e59
3
  size 619632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:302a9bd18fddb8144a5f10c3c177ebfd4574a4f4d5963aebaec470d48353bcf0
3
  size 1324026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58176b1acbdde910a84e51caa6768dcfd6bcc9c377b84c7e9bf7f291e9f7ed78
3
  size 1324026
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd7949088d7233b9cf27831b62c9b3897ec0e564f2b4de82b056a51e812411f4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce130a6508516f2ee2745c17e33c27e5668578cdda338261a4d0d39ad0480ace
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0425531914893617,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 144.505,
45
  "eval_steps_per_second": 48.168,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 2285124452352.0,
67
  "train_batch_size": 3,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0851063829787234,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 144.505,
45
  "eval_steps_per_second": 48.168,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.05673758865248227,
50
+ "grad_norm": 0.2697097957134247,
51
+ "learning_rate": 8e-05,
52
+ "loss": 11.926,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.07092198581560284,
57
+ "grad_norm": 0.26272961497306824,
58
+ "learning_rate": 0.0001,
59
+ "loss": 11.9299,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0851063829787234,
64
+ "grad_norm": 0.2433949112892151,
65
+ "learning_rate": 0.00012,
66
+ "loss": 11.9302,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0851063829787234,
71
+ "eval_loss": 11.927234649658203,
72
+ "eval_runtime": 0.7783,
73
+ "eval_samples_per_second": 138.757,
74
+ "eval_steps_per_second": 46.252,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 4570248904704.0,
96
  "train_batch_size": 3,
97
  "trial_name": null,
98
  "trial_params": null