adammandic87 commited on
Commit
8a2ec4e
·
verified ·
1 Parent(s): 94ba62a

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 sha256:59b580750888ea7d8abce7a14d4f56dbd00f7db466644347e0d4b6e0599a474d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b310a150f466af3e87b2d8c7910c988f3a28ca60695ecc9ce4cfab85d7aca87
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a138952f84f9a99f08b97d104ff0a77c31e83057ec5e554c490cbc21ac96237
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfc86e157a779abdea7fc6ebca3c6312de1b64f5d99d48231a3f08b853d88cf
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:a0472ce311e84cd5509f168867d58579c252d4413aee368c17e4cfad44ac2bb7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f62f4f0647707d8997af292a57de347f3a5bed990d5d90f499237f40b50a0b
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": 0.11935730680948738,
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": 26.64,
61
  "eval_steps_per_second": 13.32,
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": 8970386603507712.0,
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": 0.1530221882172915,
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": 26.64,
61
  "eval_steps_per_second": 13.32,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.12241775057383321,
66
+ "grad_norm": 0.4938279986381531,
67
+ "learning_rate": 1.4644660940672627e-05,
68
+ "loss": 0.4451,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.1530221882172915,
73
+ "grad_norm": 0.5841078758239746,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.452,
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": 1.1282341913690112e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null