nblinh63 commited on
Commit
b2c24dc
1 Parent(s): e6f533c

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:214c42ba3471cff15c9b157cf8d7703865605d59d336de3bb89c6f0e9aec1a13
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ee2b53f6805b3f8752ddef61c4d23ff6fccd115c7712b2d7809faeb13dbed8
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81c676a0a1248abb88102650a624cf8a918fa9367766672889fb83250e0624aa
3
  size 1003002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22576e885298578cdbfafdbc8d579766a1c6d6ec748fa0999ac4cf2e0b4ed7e5
3
  size 1003002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4661b5fd937f7fc4ac64474a7a07bb8f9b1fb3a173ee34b9881690e1316152dd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b6cde79fbc4b5b26bf00e97c36fd2d90b042fd30be528f298072427e071121
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0009096422073984233,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 30.485,
74
  "eval_steps_per_second": 15.243,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3257942409216.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0013644633110976349,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 30.485,
74
  "eval_steps_per_second": 15.243,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001061249241964827,
79
+ "grad_norm": 15.552982330322266,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.9988,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.001212856276531231,
86
+ "grad_norm": 14.931906700134277,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.3466,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013644633110976349,
93
+ "grad_norm": 15.584132194519043,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.5936,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013644633110976349,
100
+ "eval_loss": 10.818541526794434,
101
+ "eval_runtime": 91.1349,
102
+ "eval_samples_per_second": 30.482,
103
+ "eval_steps_per_second": 15.241,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 4886913613824.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null