ardaspear commited on
Commit
5bf23b4
·
verified ·
1 Parent(s): 87d5d70

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f5bc0b5ca26d966bff3b30712be13dd89dc7308d73aaf9aab9d44ae316b2c4e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a4a5888d0eb9edb735edf1836a19a959b1ba8681885f9aa21198c19709da23
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:963b0ef9edd916189186a9e637cfa0c20df02d242efdf89b8c33ef6562fe4142
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d003c8d3ec225855b33dde2ea80eeb4f521574e37dab0bf55687c6326b82d05
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
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": 0.0016834166624581251,
5
  "eval_steps": 5,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -111,6 +111,28 @@
111
  "eval_samples_per_second": 13.634,
112
  "eval_steps_per_second": 1.705,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 3.884422465270579e+16,
134
  "train_batch_size": 8,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0020200999949497502,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
111
  "eval_samples_per_second": 13.634,
112
  "eval_steps_per_second": 1.705,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.001818089995454775,
117
+ "grad_norm": NaN,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 0.0,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.0020200999949497502,
124
+ "grad_norm": NaN,
125
+ "learning_rate": 5e-05,
126
+ "loss": 0.0,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.0020200999949497502,
131
+ "eval_loss": NaN,
132
+ "eval_runtime": 1833.8204,
133
+ "eval_samples_per_second": 13.639,
134
+ "eval_steps_per_second": 1.705,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 4.638679254643507e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null