adammandic87 commited on
Commit
1a15b49
·
verified ·
1 Parent(s): f12e4cd

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c0bd8f74426e7b16d281e54d6df8729a4a88380905c05c16587817202245a47
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694385e8d04a9a1ca6681d7185dcf5d527e1c256339fd758dc53326c2d6bc464
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d215ac821c7544b6f3690d90110e2cd69af235737b3114821ec19023878bc05
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399514694f7822672f1e3a8bf71aa4bf7c9b65432b54b86e7e47d86f038bb2f4
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6debe644a2ddea872c951fc5b4b0a5b9add66484b6ad380c12bb0e5663ff3132
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b59bb5720e2348fa011207dba6244b4ac3914957063d9e0a58933fc8ef38190
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.018361581920903956,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 17.954,
61
  "eval_steps_per_second": 8.987,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.313974731669504e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.023540489642184557,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 17.954,
61
  "eval_steps_per_second": 8.987,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.018832391713747645,
66
+ "grad_norm": 5.605700492858887,
67
+ "learning_rate": 1.4644660940672627e-05,
68
+ "loss": 8.0464,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.023540489642184557,
73
+ "grad_norm": 6.283052444458008,
74
+ "learning_rate": 0.0,
75
+ "loss": 8.2204,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.693919232393216e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null