dixedus commited on
Commit
8d10fc9
·
verified ·
1 Parent(s): 977be66

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:835d8c293a3ab814d700a9b4d9d9e841f19a6b42c9d8381b29e50c84dd003810
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532c8f8fb60354d82421e3a54d4af2f9a7ddfb4a76433b67f4b9f6a9faeef294
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:198fb543ee87040e226fc933590516e6b42493081c99e76c1a61cfaa92767bd2
3
  size 111142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef7de346dde7e25d2ed0a8556dd17b50afe140e235626a75e8706592fe1517c
3
  size 111142
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf4e7354a68005cdfb2691b9035fcbb8fd675630130003c737e6dc7ca2b633b3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d3ee372ae94cc4acaaf33960502a09e062f2e33912cab4e750581e6e7dd390
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.013165112452002194,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 386.987,
74
  "eval_steps_per_second": 48.394,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2719727222784.0,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.019747668678003292,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 386.987,
74
  "eval_steps_per_second": 48.394,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.015359297860669226,
79
+ "grad_norm": 0.03578553721308708,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 10.3645,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.01755348326933626,
86
+ "grad_norm": 0.03931654617190361,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 10.3648,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.019747668678003292,
93
+ "grad_norm": 0.045229654759168625,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 10.3649,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.019747668678003292,
100
+ "eval_loss": 10.361788749694824,
101
+ "eval_runtime": 5.9151,
102
+ "eval_samples_per_second": 389.344,
103
+ "eval_steps_per_second": 48.689,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3896532271104.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null