ClarenceDan commited on
Commit
95850a7
·
verified ·
1 Parent(s): 0b569ec

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 sha256:0a4c5337c60782a5204e784ef71afcc65b6bc240a19682135c29d745b61e55e2
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe51b77767cd2b4ba40d925c5c7607763987d3e81728ec1ec66200b086956ce2
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac398850b3e5c1a35e201c2b85bab3c46afddf8426e1861c4b64e7351875e194
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe3171afd2ea42089e2f7438eaf6a4db6a7b036f63a00a4f0ab8e44894a5772
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb56808f227cffab5506c67c7ca72d0b81732eb7ee6a29a97678d6fd959473c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0544437218d662c0331fc45dbd0a84fa21f64f8aa75da97b647d8e2fdd47d56a
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": 0.0002405074707633106,
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": 19.641,
74
  "eval_steps_per_second": 9.821,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1711683215032320.0,
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": 0.00036076120614496587,
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": 19.641,
74
  "eval_steps_per_second": 9.821,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00028059204922386237,
79
+ "grad_norm": 2.9132041931152344,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.8312,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003206766276844141,
86
+ "grad_norm": 3.3039796352386475,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.2596,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00036076120614496587,
93
+ "grad_norm": 2.855940580368042,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.4523,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00036076120614496587,
100
+ "eval_loss": 1.5837900638580322,
101
+ "eval_runtime": 534.4382,
102
+ "eval_samples_per_second": 19.656,
103
+ "eval_steps_per_second": 9.829,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2567524822548480.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null