Nexspear commited on
Commit
286b8c4
·
verified ·
1 Parent(s): c3faea6

Training in progress, step 30, 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:c53254f7ea39fe8f31247ca88cb1caeabdacc9a6e1133aeda2a0e5a64a20f392
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f0c0d8d86cef26a072d97f98acadf4578aa0e3357fb39100083acb3e947626
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cfe9e8e0441d1088dc84ff17fd775ff5fe66a0f007e919d9ba407a9f990ffd0
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3822dcf377fc922f395e85094def75a146277d0f294be9f5d4b05f8fc85d4e95
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c620901f4f18db9d2766b73b498690238d01bc9e321c63a96cb81351dc958c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c0eeda3a62034479ea787479fb6c3516b246ee5930ba976a4814c1c12227b2
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": 0.046992481203007516,
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": 27.914,
112
  "eval_steps_per_second": 6.979,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 4967074313011200.0,
134
  "train_batch_size": 4,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05639097744360902,
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": 27.914,
112
  "eval_steps_per_second": 6.979,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.05075187969924812,
117
+ "grad_norm": 1.6344633102416992,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 1.609,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.05639097744360902,
124
+ "grad_norm": 1.6545953750610352,
125
+ "learning_rate": 5e-05,
126
+ "loss": 1.5911,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.05639097744360902,
131
+ "eval_loss": 1.6130125522613525,
132
+ "eval_runtime": 16.0529,
133
+ "eval_samples_per_second": 27.908,
134
+ "eval_steps_per_second": 6.977,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 5960489175613440.0,
156
  "train_batch_size": 4,
157
  "trial_name": null,
158
  "trial_params": null