adammandic87 commited on
Commit
cb34b54
·
verified ·
1 Parent(s): 0c6655e

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 sha256:8d3fb15f9888108da5871576ab1d5a08e4fa6fd90e815fe2e450e909d8b91c42
3
  size 16794864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05523af3987b0e2b0763257b67409701066e171d822f236c1e339014ba4ef8d
3
  size 16794864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cc04a52cdc19d6958743e47d313f08557e6b987515a676551acbfe972c4d579
3
  size 8671162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488bc405317f03f75b69aed4292b654c734be8ecba2acc4c6830aa9a4f19bb4d
3
  size 8671162
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:832ded70908c9963ab955f29ee60dc5db43fe03d8fd12b850a50e21c3b1d2b47
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312d96e490115fb5f81ceabdaccfead5b5cb5f6936cb303414eb41d20de16aca
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": 0.003699487763232783,
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": 86.915,
61
  "eval_steps_per_second": 43.467,
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": 1733238271770624.0,
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": 0.00474293302978562,
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": 86.915,
61
  "eval_steps_per_second": 43.467,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0037943464238284954,
66
+ "grad_norm": 1.7808252573013306,
67
+ "learning_rate": 1.4644660940672627e-05,
68
+ "loss": 9.6828,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.00474293302978562,
73
+ "grad_norm": 1.7304259538650513,
74
+ "learning_rate": 0.0,
75
+ "loss": 9.6331,
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": 2226846582177792.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null