lesso commited on
Commit
2aa8f3e
1 Parent(s): 3c09bd8

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:c4c6bb934a487e0bf0601fd224380c03ac2c0908fce3bd697d7a589d8505844a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b97ac5ebef64bd50840c2ffa86b792ae28cb985a21b7ecded20513ae724768
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:519c4e0f8aaa133a54be4b7ffe0c982104341c51ad45e8055d3195783edc889c
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2807781351b0d0fc8e02a04076ccfdd74f3b6876e9780ed49ba5454f43c3a80
3
  size 168037178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbad8ba2c5033686167702b52f4d733e73fc51970594ffd4d36a57cb85a15e30
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a81cc94bb9784a99b66a3847a12e5edc941dafcbd050831d68c21b46d0ac7a
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": 0.016216216216216217,
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": 3.259,
74
  "eval_steps_per_second": 3.259,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2034520672960512.0,
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": 0.024324324324324326,
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": 3.259,
74
  "eval_steps_per_second": 3.259,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.01891891891891892,
79
+ "grad_norm": 0.24453988671302795,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.0364,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.021621621621621623,
86
+ "grad_norm": 0.3633563816547394,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.0773,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.024324324324324326,
93
+ "grad_norm": 0.29696428775787354,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.3294,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.024324324324324326,
100
+ "eval_loss": 2.1837782859802246,
101
+ "eval_runtime": 24.0965,
102
+ "eval_samples_per_second": 3.237,
103
+ "eval_steps_per_second": 3.237,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3098020115644416.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null