willtensora commited on
Commit
0305a0c
·
verified ·
1 Parent(s): ab32a8d

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:b02ad53180ac0fe58d891871ec94ac80636749fee518b2df968f2f04dcf3520e
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fae5f02256d435fea2df6685f86120b96c2eb7360bbd101c64e8558d6388cdd
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:369292b2fbf20955c9fc2c4f90e6f2788a89d8a803689545acdf1f04dde02d25
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee462f9d51986c0c067381a416b7613f00ef45b035e21395d44e99797217fc5
3
  size 41119636
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:540e1f4a6df791c7d5746e5016ad4b3dbbc7b05cb1c90e581731b22022e11a95
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137d39878de2043bea8c79a280777ce70b18802cd3392122a7b38d5dd0ee940c
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dddaadce4f873230225f40917d486d2a2d55acac8daf2d725aab16fe680bcf0
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa4c9f7c4790f7217bed19143f47de9e4d492ca89587a48fa0690e8407d9727
3
  size 14512
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": 0.003043625295908015,
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": 59.587,
103
  "eval_steps_per_second": 14.909,
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": 2972467375112192.0,
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": 0.0033818058843422386,
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": 59.587,
103
  "eval_steps_per_second": 14.909,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0033818058843422386,
108
+ "grad_norm": 1.1577800512313843,
109
+ "learning_rate": 0.0002,
110
+ "loss": 4.8454,
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": 3298217223520256.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null