nblinh63 commited on
Commit
f6661be
·
verified ·
1 Parent(s): af72134

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7da23c7d7bd6e4f664540227d16a33254726e335ed96babdcc5b21f3f68ae3cb
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214c42ba3471cff15c9b157cf8d7703865605d59d336de3bb89c6f0e9aec1a13
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0fb0e68a47404fcbacdb9e8ed3940ca2dfceedde82a66c84ec0752d7b39cf8
3
  size 1003002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c676a0a1248abb88102650a624cf8a918fa9367766672889fb83250e0624aa
3
  size 1003002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efe25b2690f9ab834a90d397c4e90e64c7888efd1d8b4dbe6c81769591b024c5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4661b5fd937f7fc4ac64474a7a07bb8f9b1fb3a173ee34b9881690e1316152dd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.00045482110369921165,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 30.45,
45
  "eval_steps_per_second": 15.225,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1628971204608.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009096422073984233,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 30.45,
45
  "eval_steps_per_second": 15.225,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0006064281382656155,
50
+ "grad_norm": 21.273990631103516,
51
+ "learning_rate": 8e-05,
52
+ "loss": 11.3351,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0007580351728320194,
57
+ "grad_norm": 16.648815155029297,
58
+ "learning_rate": 0.0001,
59
+ "loss": 11.359,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0009096422073984233,
64
+ "grad_norm": 19.553115844726562,
65
+ "learning_rate": 0.00012,
66
+ "loss": 11.2096,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0009096422073984233,
71
+ "eval_loss": 11.353554725646973,
72
+ "eval_runtime": 91.1262,
73
+ "eval_samples_per_second": 30.485,
74
+ "eval_steps_per_second": 15.243,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3257942409216.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null