tuanna08go commited on
Commit
a487449
·
verified ·
1 Parent(s): f1a3bd2

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:c0daac258d6f82e34bb71758e589fe1ca14e64cf2278c83749f1dfa75b743afb
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872dd4f47e62f719300e488d925401e72d30977da694c8d0d7cc327547319197
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a3ecdd6a26d931a8ea793e06dd72e035f773c068b901cb717967af24efc4765
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f409829c59176cff79b07b00badc562b1e3e214e61883ee19627c92795b77eec
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:ee67e020b47ef6805a46d6409036170d131a1606006dd175c72aca6d167ace95
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b7a41fc5fd0d170e9504e4ce08b29cf3b4d308968a1cadf8a9b49c497426ea
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:694a539f11c8d87dcdc9a0523d10086c9a55d2b245bea58f425e64a8cd3022da
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
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": 0.0035588771742515236,
5
  "eval_steps": 10,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -75,6 +75,21 @@
75
  "eval_samples_per_second": 14.762,
76
  "eval_steps_per_second": 7.382,
77
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 10,
@@ -89,12 +104,12 @@
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
- "should_training_stop": false
93
  },
94
  "attributes": {}
95
  }
96
  },
97
- "total_flos": 8323039116656640.0,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004448596467814404,
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,
 
75
  "eval_samples_per_second": 14.762,
76
  "eval_steps_per_second": 7.382,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.004448596467814404,
81
+ "grad_norm": 1.345386266708374,
82
+ "learning_rate": 0.0,
83
+ "loss": 1.5898,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.004448596467814404,
88
+ "eval_loss": 1.5169124603271484,
89
+ "eval_runtime": 321.4289,
90
+ "eval_samples_per_second": 14.725,
91
+ "eval_steps_per_second": 7.364,
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": 1.0357559789617152e+16,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null