nat-hunt commited on
Commit
d34d322
·
verified ·
1 Parent(s): 403d979

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 sha256:7e4b665aeeb24f91e0ab08013acc27cac5de8efd8614eea8b3825e15821a2760
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768eab5c73613ca0a6eb60ec9a5268ee3e424d74362f12e3caa861d69add73dd
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cde6b9c195acdefd04aabcc7288ccf9a5a462cbc4d06655521da2f43d1c06ca
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b2cced94148d7ca0e714f0b5c132242a9230853e47b5cea54cd8a5657b55f2
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:cbfb2a8ca86973e6a99dc8ef1752a3330ab1606af691b0f01cfb2f43295f96d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc67008a77feb0ab06a9f86c940276291c2c83e8db9dde3d8741465edb44648
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": 0.04460966542750929,
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": 14.67,
61
  "eval_steps_per_second": 7.355,
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": 1.2541369163710464e+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": 0.057191878753217046,
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": 14.67,
61
  "eval_steps_per_second": 7.355,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.04575350300257364,
66
+ "grad_norm": 1.1591876745224,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 4.6645,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.057191878753217046,
73
+ "grad_norm": 1.2325793504714966,
74
+ "learning_rate": 0.0,
75
+ "loss": 4.5842,
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": 1.6124617496199168e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null