trenden commited on
Commit
050ac49
·
verified ·
1 Parent(s): 53dc5f4

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 sha256:10e24eb6f2ee5d1e050a651951cf2de06a516ea9d76a737ff2803f6159b01761
3
  size 16794864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aed70f6dcebd57e9ebcbcb385b495538a1ea8f786ab02636265a54ffe07d911
3
  size 16794864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:239fb36e72e17a2fa7f04d31fc3ff5adb45cfc5137fc6775b8f3a9ea2d124b18
3
  size 8671162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3604bfc87fe036628977f55234d100f5be0549ba0fbf4cc9d8ed20ba53639c97
3
  size 8671162
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b88f1c8f29deec72fdb86411eef34c00d861bf676cb3ace988ec0111b482ed57
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
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": 0.02783229259589652,
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": 132.417,
61
  "eval_steps_per_second": 66.208,
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": 875032913903616.0,
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": 0.03568242640499554,
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": 132.417,
61
  "eval_steps_per_second": 66.208,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.028545941123996433,
66
+ "grad_norm": 7.938344478607178,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 5.2656,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.03568242640499554,
73
+ "grad_norm": 8.023124694824219,
74
+ "learning_rate": 0.0,
75
+ "loss": 5.2916,
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": 1121837069107200.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null