duyphu commited on
Commit
9779bc4
·
verified ·
1 Parent(s): fe85ffc

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 sha256:3a07978ce6d08e786ded65fe25199212f8a3f7cf5f54d3099fba5c8035329e9d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b95b6b172784581f642d09397a5ded99482ed19a287c01a53b5defd9a3321ff
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5238afe4965e3dcd71efcd717a0408ae64b05b02a1d259761dab5032d5b13221
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b72a1aba8efc56b5e474805727eb15266b07c4a83188d11bdc204c1d001a046
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a4d40f9c4bf65078886d54e1cfc54df5ccabb01b6dd112966b8979e806e106
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0016904247192107017,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.1319,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4808867045179392.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0025356370788160525,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.1319,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0019504900606277327,
72
+ "grad_norm": 2.016071081161499,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9876,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0019504900606277327,
79
+ "eval_loss": 2.0283923149108887,
80
+ "eval_runtime": 451.3853,
81
+ "eval_samples_per_second": 14.349,
82
+ "eval_steps_per_second": 7.176,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0022755717373990213,
87
+ "grad_norm": 1.917054533958435,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.0465,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7305778780176384.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null