JacksonBrune commited on
Commit
04a4bbb
·
verified ·
1 Parent(s): 3994a51

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:482bb53673a262d01f33e53b5781e9de4734d65a1ba3992a01e36c4d0aa97e29
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1899e882c91382cc518fe94d562dc23c03dfeb04c92913a10f0610e9d1b99808
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ac80e4b93cce9fddca16e6c2ed8e3c38e4bf8e1be639f15e7d91c2545f25c5d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f121debc4e28086eb72aba13b2b7a0ec6dfb79590ffbf9be3f73b3b2a4829e
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:ad50d6cf06913bd0bd4258afcb318b70f1ccc0899d991e7012fdad252831c348
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.00511727078891258,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 19.452,
103
  "eval_steps_per_second": 9.739,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 3005541903237120.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005685856432125089,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 19.452,
103
  "eval_steps_per_second": 9.739,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005685856432125089,
108
+ "grad_norm": 1.452796459197998,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.8366,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
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": 3329215646662656.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null