nat-hunt commited on
Commit
8c1f106
·
verified ·
1 Parent(s): 2300a4d

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 sha256:78ea7f155ee71fe00af988906c79c3ba9d0eab530bfba269a2fc202c1ec314b4
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb84dac1d0fe571f004c3539e2eda791e1e73c3d9972a4b110ea71d78dfdcfba
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f416dcbcd5bb0ae9858bd5e1dc079343ae7465b2dbbc8cfffff1fda04bf68697
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577b47c05f5c800ee0c4bfa76a518325c29dfc7decff3435e932871184b8d73a
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76f38dbecbc56a312e62ae20178cc7dcf74caef9c6efe912086661f87270aac7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07e4d9599cf29959d97584366c333a3a8bdb99588c142d3d9e8eba2ac6b556d
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": 0.023376623376623377,
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": 17.651,
103
  "eval_steps_per_second": 8.88,
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": 1455586380349440.0,
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": 0.025974025974025976,
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": 17.651,
103
  "eval_steps_per_second": 8.88,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.025974025974025976,
108
+ "grad_norm": 0.5720862150192261,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.542,
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": 1619596113346560.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null