filipesantoscv11 commited on
Commit
016c389
·
verified ·
1 Parent(s): ac0be35

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00c928ab20eb5994ffd2ba76b396607d3d2bee863be0efaea515b9a5e9529d88
3
  size 9864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e1404f9dc7c06b5024a239df730998bb0a5f1ef981f8fd1673f218494eeb5b
3
  size 9864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab5907298412f541a413810119656cc8bb70bb86dac17bc1a686b824b6be9be9
3
  size 27002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daaffbbe217e104436c7e922f40add640986078ee9419ca4a2e51a0754331c75
3
  size 27002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
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": 0.0032512395350727465,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 6.545084971874738e-05,
74
  "loss": 46.0,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 797921771520.0,
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": 0.00487685930260912,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 6.545084971874738e-05,
74
  "loss": 46.0,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.003413801511826384,
79
+ "grad_norm": 1.9497951143421233e-05,
80
+ "learning_rate": 4.2178276747988446e-05,
81
+ "loss": 46.0,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.003901487442087296,
86
+ "grad_norm": 3.0179426175891422e-05,
87
+ "learning_rate": 2.061073738537635e-05,
88
+ "loss": 46.0,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.003901487442087296,
93
+ "eval_loss": 11.5,
94
+ "eval_runtime": 15.9219,
95
+ "eval_samples_per_second": 162.732,
96
+ "eval_steps_per_second": 81.397,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.0043891733723482075,
101
+ "grad_norm": 2.72399811365176e-05,
102
+ "learning_rate": 5.449673790581611e-06,
103
+ "loss": 46.0,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.00487685930260912,
108
+ "grad_norm": 1.3301386388775427e-05,
109
+ "learning_rate": 0.0,
110
+ "loss": 46.0,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1196882657280.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null