jssky commited on
Commit
f16be62
1 Parent(s): d75e8a5

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:bb1a21df5aaaf46d18ad732a489f8c3845221c341d465ebf9be6eeaaac6666de
3
  size 161533192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36fb18f8272f2b6c70619819e01b1cb8f22d1147f35bb778cbaf83dc85e7635d
3
  size 161533192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd0e0076ad6d43c74a3a58dbae61e4dec432c50c350d45632fae2aececfc37b2
3
  size 82460660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9328e38c0279fbcf8648aaaf9d962e2f9d9ff6428a9ea6f3b55a0bbd90fcdd6
3
  size 82460660
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b184aea029f3721657bcfebf3500fc97ea749134c5f6570a032a92790adab8f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623fb9bddd1501e2540f9214d6610cbcc7bd89bc3e4795cd57afb5fe1a5754f3
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": 0.001751441290228417,
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": 4.601,
74
  "eval_steps_per_second": 4.601,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4194232159961088.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0026271619353426257,
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": 4.601,
74
  "eval_steps_per_second": 4.601,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0020433481719331534,
79
+ "grad_norm": 0.948012113571167,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.2248,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0023352550536378893,
86
+ "grad_norm": 1.4153283834457397,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.2715,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0026271619353426257,
93
+ "grad_norm": 1.536092758178711,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.5885,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0026271619353426257,
100
+ "eval_loss": 2.1300644874572754,
101
+ "eval_runtime": 156.9377,
102
+ "eval_samples_per_second": 4.601,
103
+ "eval_steps_per_second": 4.601,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6291348239941632.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null