robiual-awal commited on
Commit
55bb6ca
·
verified ·
1 Parent(s): f8951f1

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:aeadcf027aafd6039a257c1af57c3ff81f613b3a3f78532e788328c2db94cdcd
3
  size 28350504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09db1aff73c8a5535c8b9415561d2e7fd5a119e00aee2077e70faffa3bb060f
3
  size 28350504
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:692b69cdcd73aec5f69053697e97ad1b332effa351752a59a59462c7f77b99ef
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded9febde415d5ac711da329f56c52c8d2e58c596f85c091b116470c44cb234d
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8393701a28790c8c79452e41d5b55d2d1be9b256b489bdf590de0c78efcbc8f4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba9454fe65eed13f4a230b19361ef94ae18444780d438f5a4aa748d41d24b44
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0948905109489051,
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": 32.448,
61
  "eval_steps_per_second": 16.318,
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": 2330089349971968.0,
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": 0.12165450121654502,
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": 32.448,
61
  "eval_steps_per_second": 16.318,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.09732360097323602,
66
+ "grad_norm": 2.61189866065979,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 10.2041,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.12165450121654502,
73
+ "grad_norm": 2.5197603702545166,
74
+ "learning_rate": 0.0,
75
+ "loss": 10.1863,
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": 2987294038425600.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null