Nexspear commited on
Commit
9ae243a
·
verified ·
1 Parent(s): d58c586

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 sha256:088a68e66e552a6976c32f9b20f2ace92ad9ba2a29eb6bc282047ad6fa6b6f63
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e204fc319f37ca92a83df076ee7b55ede9ac3e0d7f7fe6d5e38c2ac6ecb2ee0
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7646b166ec03eeac2bbd06339911963ad75c4a191bbe8de095d6f8aeea4b6e35
3
  size 197158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed1f714420aa41b6aeae7718ea7244c8f8beae5b12cbacfe870b59b27623bf3
3
  size 197158
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
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": 0.36496350364963503,
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": 183.04,
112
  "eval_steps_per_second": 23.875,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 120520704000.0,
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": 0.43795620437956206,
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": 183.04,
112
  "eval_steps_per_second": 23.875,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.39416058394160586,
117
+ "grad_norm": 0.4930538833141327,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 11.8967,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.43795620437956206,
124
+ "grad_norm": 0.5465889573097229,
125
+ "learning_rate": 5e-05,
126
+ "loss": 11.8926,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.43795620437956206,
131
+ "eval_loss": 11.884086608886719,
132
+ "eval_runtime": 0.5974,
133
+ "eval_samples_per_second": 192.507,
134
+ "eval_steps_per_second": 25.11,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 144624844800.0,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null