Aivesa commited on
Commit
211c9aa
·
verified ·
1 Parent(s): 638d843

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 sha256:3ff8cd258115ced586009f202041f2702591f5c9b2ad090e9727ae49660fc80e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bab68235b5cf79bb8bdbd21dff8168ceb96b2de12f660c1c568912711d374b
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:011999d79480fba443e1ebd1be232bf3e87ec4b876486c0bf23fe23074e11718
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0aaf802f087992b6afe6cd186331187a7a94bbbe39eec0e06dd779b3baf1f47
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e10e7e084e9d9c969a8d9c919cc8f1ecdc23be93922140c6c36dc329b7d816c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0e1e671455c353fa99a1d12b6e48bbd12137e1c5f529ac1c3f24d8e1df3f99
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": 0.001894537417113988,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 20.016,
66
  "eval_steps_per_second": 10.008,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 1139236669489152.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002841806125670982,
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,
 
65
  "eval_samples_per_second": 20.016,
66
  "eval_steps_per_second": 10.008,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0022102936532996525,
71
+ "grad_norm": 9.589306831359863,
72
+ "learning_rate": 0.00014,
73
+ "loss": 4.2976,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0025260498894853173,
78
+ "grad_norm": 8.981024742126465,
79
+ "learning_rate": 0.00016,
80
+ "loss": 5.1871,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.002841806125670982,
85
+ "grad_norm": 7.4614644050598145,
86
+ "learning_rate": 0.00018,
87
+ "loss": 4.3596,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.002841806125670982,
92
+ "eval_loss": 1.0006051063537598,
93
+ "eval_runtime": 67.0363,
94
+ "eval_samples_per_second": 19.9,
95
+ "eval_steps_per_second": 9.95,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1752671799214080.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null