havinash-ai commited on
Commit
b0bd6b1
·
verified ·
1 Parent(s): 14575e0

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 sha256:94755a411dfda40291208c5897f0646a7ed9bd9e329f55d55797060daf86d19c
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac7a55a1771c1a0a0680b6b7cd9f3dbee883b738330f68cc05105a2f0d53b20
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d91f99fe164a0eca87817065088c7319e5406cbe0fac1c37ed5e43c68e9a9824
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6c5c4221cb99ca6089a63867b9bc4cf87c8e418bf85b2d60ea66c0721bef712
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbba3e37f3da5eebd20241eda5b6317a6fa8037aef8c40511f6d82de78527891
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c892e11d40117d2be5c6d056d9523f3cdf40bb7bcf617fd97f9bb318d6c7fc5c
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": 0.008251785241999472,
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": 60.318,
61
  "eval_steps_per_second": 30.159,
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": 347248838836224.0,
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": 0.01057921184871727,
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": 60.318,
61
  "eval_steps_per_second": 30.159,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.008463369478973817,
66
+ "grad_norm": 1.3363937139511108,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 2.3986,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.01057921184871727,
73
+ "grad_norm": 1.235545039176941,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.3348,
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": 445190819020800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null