tuanna08go commited on
Commit
b2313a3
·
verified ·
1 Parent(s): 9dd6e91

Training in progress, step 50, 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:dbe3220fcc5f5412981604379deab23869b19a9532fe5fcb7169b99c7b75cff1
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa30eabf550678160c52ca967d4007a4a565fc0d23578450e8506819466549a
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b9b5d423b980203d505ca2b1e20b9b5f49cd5d55359155f7072fb14af385807
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea27678d3803a47f605ab0060e6269a785087dd8f63feab30ea45966f271284
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1315906b24c353ffb372fa61e423b6374fc83ec7776f1c3a47263ba225c105f0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068f2703b19f5ad779c77ee3cd618018e7b034ba6ce7b07b7cd363426cc2a99d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.0296043267862226,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,36 @@
60
  "eval_samples_per_second": 170.569,
61
  "eval_steps_per_second": 21.333,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +104,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 2959455736037376.0,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0379542651105418,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 170.569,
61
  "eval_steps_per_second": 21.333,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.030363412088433437,
66
+ "grad_norm": 0.3088821470737457,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 2.5504,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.030363412088433437,
73
+ "eval_loss": 2.807931900024414,
74
+ "eval_runtime": 52.0481,
75
+ "eval_samples_per_second": 170.515,
76
+ "eval_steps_per_second": 21.326,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.0379542651105418,
81
+ "grad_norm": 0.34101369976997375,
82
+ "learning_rate": 0.0,
83
+ "loss": 2.5387,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.0379542651105418,
88
+ "eval_loss": 2.800560474395752,
89
+ "eval_runtime": 51.8735,
90
+ "eval_samples_per_second": 171.089,
91
+ "eval_steps_per_second": 21.398,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 3806484202782720.0,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null