tuanna08go commited on
Commit
9546e38
·
verified ·
1 Parent(s): 64ddd20

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:a46b10021dbe1c382684bcf82e76d698022ccd34baa88a83a3c739a571f4ec40
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b8cca4b6f374fc4af89df1a074f81c749236c72f7f5a144f1cd932cfffc1cc
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:312a17bf1213b44e2037e9f6857009a9a6f5af46435581519c23b4ddbc07bb7a
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f8cd7dad2a479fd5be170fbd13c2b5cd9de5c8109e9264688e8c5b5c94ff27
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9e47077ccc9b4381fcae7598ddb39a02fc9c44e4adcd3603e5e91f4dcd57e9a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68febc57b83e4f949a52f064cd0caf38fbf252ef901cd41bf7ac2f17e73af454
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": 0.3317384370015949,
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": 59.455,
61
  "eval_steps_per_second": 7.432,
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": 1.974256476880896e+16,
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": 0.4253056884635832,
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": 59.455,
61
  "eval_steps_per_second": 7.432,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.34024455077086657,
66
+ "grad_norm": 0.5272931456565857,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 0.2039,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.34024455077086657,
73
+ "eval_loss": 0.1671234667301178,
74
+ "eval_runtime": 13.3113,
75
+ "eval_samples_per_second": 59.499,
76
+ "eval_steps_per_second": 7.437,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.4253056884635832,
81
+ "grad_norm": 0.4160679280757904,
82
+ "learning_rate": 0.0,
83
+ "loss": 0.1855,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.4253056884635832,
88
+ "eval_loss": 0.16490614414215088,
89
+ "eval_runtime": 13.3202,
90
+ "eval_samples_per_second": 59.459,
91
+ "eval_steps_per_second": 7.432,
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": 2.5310980472832e+16,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null