adammandic87 commited on
Commit
3ebca02
·
verified ·
1 Parent(s): 708f05c

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 sha256:1a44dcbb937536752e0d3c044e2501fac798adee2416be723d316532c94c498e
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef83d5e6f9063518e54065b3530f580cddf45f57fd88b305935a88019ed902e
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab5dbfc1ef67ec230f0f3910b23b3542a49e15754d543e255c91f62ef4d4563
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a77e7dc4dde4dfa319809e0df85ff1f69bb8cf79e6cbd5599954362e4e33e8c
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01d0903aa420d18f253df95cd1ed6a8bc8082a9eea91eb682a120fc88792e0ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e4abb5d8f838d7298d0da53d751603c0e159cddd8e50398726666cfef25317
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": 0.003247924936845904,
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": 7.336,
103
  "eval_steps_per_second": 3.671,
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": 5135049645096960.0,
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": 0.003608805485384338,
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": 7.336,
103
  "eval_steps_per_second": 3.671,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.003608805485384338,
108
+ "grad_norm": 4.158239364624023,
109
+ "learning_rate": 0.0002,
110
+ "loss": 5.7451,
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": 5705610716774400.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null