shibajustfor commited on
Commit
242c014
·
verified ·
1 Parent(s): 07ccce5

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 sha256:3e2beec9e70f3e6e5b8be8e0d47d6c08bb36e5de9ca665720a59ad98b4916fba
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dc828c30eb9b40edaccf6d97ec99781a7222e8acfe0e55f576927c0f58cf15f
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e3ab7b37c4ea93da4a86681b6b3eab3cfca629de7038d1ad66bb1dbda73c2d8
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720ce6caed034a5fa09dfd67ae848762d7d62e4ef55f93acc65fdfb000ed4079
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ec80c42722702637d7b76af048c5e8229c9a8ba738c0d6bedd3cdb2a5529ce
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924b914667800f2a22ea049cac2c652f17755855f4eb687d11ce831ff485a455
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": 0.04097714736012608,
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": 16.637,
61
  "eval_steps_per_second": 8.339,
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": 1.456454498254848e+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": 0.052534804307853955,
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": 16.637,
61
  "eval_steps_per_second": 8.339,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.042027843446283165,
66
+ "grad_norm": 0.0701930969953537,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.1017,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.052534804307853955,
73
+ "grad_norm": 0.10752475261688232,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.0807,
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": 1.931385312903168e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null