robiual-awal commited on
Commit
b50d70c
·
verified ·
1 Parent(s): 3f1cab3

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 sha256:0c08accddd1f7dbfa8f762d87a72d322c4579e3089f4a1676a70b9222184208c
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9302386f2a19cb3c2b949796b425500b69cab43e6c1b23480ebfbca4c3eae337
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0db29e2cef4de5154ce69a9781051436e88f55a65f2a8e2967771e5ea84ddf7
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365b13f154f55932e0cc101c4e2c52a517222d959b54ea1e0f78604aa3e804cb
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:962014f5ee70a609d3e0a1b1600e848f569490ce500ef477bd82377bd2656e01
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d9756a69ab6235531ea97df16d3adbab89b38f13c5341ce90427b4941392f9
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": 23.246,
61
  "eval_steps_per_second": 11.623,
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": 9077684227276800.0,
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": 23.246,
61
  "eval_steps_per_second": 11.623,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.028545941123996433,
66
+ "grad_norm": 0.6934235095977783,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.5933,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.03568242640499554,
73
+ "grad_norm": 0.6936048269271851,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.4805,
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": 1.17054349246464e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null