kk-aivio commited on
Commit
efb8c94
·
verified ·
1 Parent(s): e727610

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 sha256:1e1df190c4160825ea3a5b170c868688c30480839bb163ad395699e030883083
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2120cc47272f72f23eaa7261dc5d3788c6898b2805505aa81125518dd6449206
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:273a51d1a661bde2b80d5d839bf42ece2c900bdf9bb6a7f77639cf58afa06855
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29381de58d3792b67160ada82e66816d9569274d8c1183137a044ffcaa3297b0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
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": 5.328821597713935e-05,
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": 27.103,
74
  "eval_steps_per_second": 13.552,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1139235360866304.0,
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": 7.993232396570903e-05,
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": 27.103,
74
  "eval_steps_per_second": 13.552,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 6.216958530666259e-05,
79
+ "grad_norm": 27.524154663085938,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.5708,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 7.105095463618581e-05,
86
+ "grad_norm": 34.48584747314453,
87
+ "learning_rate": 0.00016,
88
+ "loss": 9.1664,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 7.993232396570903e-05,
93
+ "grad_norm": 28.674095153808594,
94
+ "learning_rate": 0.00018,
95
+ "loss": 7.6291,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 7.993232396570903e-05,
100
+ "eval_loss": 1.760007619857788,
101
+ "eval_runtime": 1751.4367,
102
+ "eval_samples_per_second": 27.069,
103
+ "eval_steps_per_second": 13.535,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1752669785948160.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null