shibajustfor commited on
Commit
8ae811b
·
verified ·
1 Parent(s): 7c1f828

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 sha256:031b938450736bef555b228264f8e63f2fad7b23b11d795f714b586d5ee85ee7
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8406588f6bb81fb312bc8f4a701c1c8294fd77904418950fcdb8f1fe8b79ba06
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae331157e0e9f0d5f3f7f8c363e2026fa9041f37f4f063f328fe88baa5bc4e42
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b791f443275ce40a87e759b0490f50fde4c79adb112a9b1472b40c955025e178
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97f0ba37f2582b0808c60874389116e3bfc24b3757aa1b434c61187a53734e05
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9382c0adb0352b8a5e8e3993ee3636614295d559a8ea9875a161d896da15545b
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": 0.034597471723220224,
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": 22.621,
61
  "eval_steps_per_second": 11.334,
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": 1.002015726501888e+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": 0.04435573297848747,
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": 22.621,
61
  "eval_steps_per_second": 11.334,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.03548458638278998,
66
+ "grad_norm": 0.6771432161331177,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.2139,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.04435573297848747,
73
+ "grad_norm": 0.6208946108818054,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.1801,
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": 1.285194083991552e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null