Best000 commited on
Commit
84c017f
·
verified ·
1 Parent(s): 2b6dcd3

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 sha256:48daffbd61991f1be11038ee5b1273d09b31690fa492c77fdc5d32227d5cc022
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0e405066d33a916cb69e4727fd7c317e5cb8a3db38ffc5b036994f3c9efae6
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeffcb070a92d1587f8ea511358adae34412017f129352ff427615466f9db44e
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d86e62025b58a36e780259495f023b433e2b4ec2553df79946e34240c73a5f
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3df234e5aaf8c4946e213550320cfa641d06d78d6188e95560495eed9123ce4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08feb0b8dea6185f68f1482010f68eaf6c0392818bbf986a4c66ef478d1e367
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a31de681372f89725884c16f61509c8be9fe1aabdebb5de708e80e690a719fa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dab003e9948eca4252e780eaf54f5324b8b378549ca6bfe1415f38792ae85c0
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": 0.17314095449500555,
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": 34.153,
61
  "eval_steps_per_second": 17.256,
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": 6352059230060544.0,
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": 0.22197558268590456,
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": 34.153,
61
  "eval_steps_per_second": 17.256,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.17758046614872364,
66
+ "grad_norm": 0.8697218298912048,
67
+ "learning_rate": 0.00016,
68
+ "loss": 0.3319,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.22197558268590456,
73
+ "grad_norm": 1.1075613498687744,
74
+ "learning_rate": 0.0002,
75
+ "loss": 0.1776,
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": 8143665679564800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null