leixa commited on
Commit
1bad219
·
verified ·
1 Parent(s): 85d549e

Training in progress, step 39, 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:fd81b5143a2851467ee237e4b1aae743ef67cbb140678d87678837d18724d0c1
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f382ad7236c3f538fc7e8cfcd9b3a2cbf0999c16e45297a65fe281ba98224f1
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c6a6f648698cd3455ec070fd03d54c2ca5075daafcf8d88087dcffc0390d2fd
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe210eaefd96a7e614ea3ab2b776d290e5bf396533231f95eb4cd8b729fbef52
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74b86d52620cc1ca6c6ad3d1937f9ecd5813650698788b10f41a3d7f093677d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8167a96dc4a0b700271fb769c80662658cb5db8db82c0d6060f5e230fd90b238
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.01644788866044599,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "eval_samples_per_second": 13.031,
67
  "eval_steps_per_second": 6.516,
68
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9061707439669248.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.024671832990668986,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "eval_samples_per_second": 13.031,
67
  "eval_steps_per_second": 6.516,
68
  "step": 26
69
+ },
70
+ {
71
+ "epoch": 0.018978333069745373,
72
+ "grad_norm": 0.3070535957813263,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6121,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.022141388581369603,
79
+ "grad_norm": 0.3568773567676544,
80
+ "learning_rate": 3.086582838174551e-05,
81
+ "loss": 0.574,
82
+ "step": 35
83
+ },
84
+ {
85
+ "epoch": 0.024671832990668986,
86
+ "eval_loss": 0.5655958652496338,
87
+ "eval_runtime": 51.1891,
88
+ "eval_samples_per_second": 13.011,
89
+ "eval_steps_per_second": 6.505,
90
+ "step": 39
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3592561159503872e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null