nadejdatarabukina commited on
Commit
a90713e
·
verified ·
1 Parent(s): 243385f

Training in progress, step 25, 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:cb1a87bf1d9b088fc0b8a1225a257a0bcf29fd066f5efeb430aafda9f7257dea
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7127dda397e9356ca1546d6030191b8cdfeb02ec3f1d4d11ab21774f56f8c3
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8f65dcd49ae8ab84935771910d3039e7f87354e1b0bf11e71aa8402fc0bffb2
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620f423ed912efd598fefbb379274e595a832758bb09bf21c6554f543efc7285
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db16b66d924db35ca922619ae5315c9bf623173b1f35fa14ec5ea6c1ca8bb24
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
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": 0.03368421052631579,
5
  "eval_steps": 7,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,28 @@
73
  "learning_rate": 8.954715367323468e-05,
74
  "loss": 1.2657,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +109,12 @@
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": 1.26955844272128e+16,
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": 0.042105263157894736,
5
  "eval_steps": 7,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 8.954715367323468e-05,
74
  "loss": 1.2657,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.03536842105263158,
79
+ "grad_norm": 1.9340174198150635,
80
+ "learning_rate": 3.308693936411421e-05,
81
+ "loss": 1.0206,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.03536842105263158,
86
+ "eval_loss": 1.2012845277786255,
87
+ "eval_runtime": 50.6968,
88
+ "eval_samples_per_second": 4.931,
89
+ "eval_steps_per_second": 2.466,
90
+ "step": 21
91
+ },
92
+ {
93
+ "epoch": 0.04042105263157895,
94
+ "grad_norm": 2.1337223052978516,
95
+ "learning_rate": 2.1852399266194314e-06,
96
+ "loss": 0.9806,
97
+ "step": 24
98
  }
99
  ],
100
  "logging_steps": 3,
 
109
  "should_evaluate": false,
110
  "should_log": false,
111
  "should_save": true,
112
+ "should_training_stop": true
113
  },
114
  "attributes": {}
115
  }
116
  },
117
+ "total_flos": 1.5869480534016e+16,
118
  "train_batch_size": 2,
119
  "trial_name": null,
120
  "trial_params": null