ardaspear commited on
Commit
c80ed8d
·
verified ·
1 Parent(s): 4dca11a

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f7750ecd057873cb9d5219aaa02f321b6d7fbd275ba8bd6423cd1c422a1d5f6
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ca2f6171dc7730ecf8c08fbc975040570ae9017ca86af36aec82bf0683c124
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c2114e917b04734ecf6d6c29e2dec4f37e3e775e81af5b53e52453122fa4372
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4f0e8dad369bc7bb59d5e7f497c51f10df0b55006fce373720fb706b727122
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
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": 0.23893805309734514,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 36.213,
103
  "eval_steps_per_second": 4.574,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 7347907728506880.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3185840707964602,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 36.213,
103
  "eval_steps_per_second": 4.574,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.26548672566371684,
108
+ "grad_norm": NaN,
109
+ "learning_rate": 8.83022221559489e-05,
110
+ "loss": 0.0,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.2920353982300885,
115
+ "grad_norm": NaN,
116
+ "learning_rate": 8.473291852294987e-05,
117
+ "loss": 0.0,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.3185840707964602,
122
+ "grad_norm": NaN,
123
+ "learning_rate": 8.07830737662829e-05,
124
+ "loss": 0.0,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.3185840707964602,
129
+ "eval_loss": NaN,
130
+ "eval_runtime": 5.252,
131
+ "eval_samples_per_second": 36.177,
132
+ "eval_steps_per_second": 4.57,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 9797210304675840.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null