trenden commited on
Commit
8166396
·
verified ·
1 Parent(s): 101e628

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 sha256:24f393f5deeb9908dfb8fda8cee3a5e4b8727e53eead295333e9a056f3363e56
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242cf82c9c76177c13f1ca91c1d0a1f5f85b4fad33a44fff50c330302bffb8e3
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e94842d71e4cf7da1fb045dd0e5f0bae6a7b1b0c00a452853ac3d0f0ba90bd66
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6a8a36dc01a965f10485c9693f23037bf3c6abc90910873cf81c9bb33df9c7
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:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea4a6c63434c27a483922b729f3295cf32c5e237d07366009f63d639620f157
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": 0.012951969778737183,
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": 30.791,
74
  "eval_steps_per_second": 15.474,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1051601871568896.0,
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": 0.019427954668105773,
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": 30.791,
74
  "eval_steps_per_second": 15.474,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.015110631408526714,
79
+ "grad_norm": 21.00330352783203,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.8624,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.017269293038316244,
86
+ "grad_norm": 23.177852630615234,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.7309,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.019427954668105773,
93
+ "grad_norm": 16.235668182373047,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.2404,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.019427954668105773,
100
+ "eval_loss": 1.0453327894210815,
101
+ "eval_runtime": 6.3324,
102
+ "eval_samples_per_second": 30.794,
103
+ "eval_steps_per_second": 15.476,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1577402807353344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null