Nexspear commited on
Commit
9729a1e
·
verified ·
1 Parent(s): 1ebd904

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 sha256:37d18a82c3d76e317c375e8ce7148bcaadcbf107910ab35f1ce0e6d564ff158a
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cb0414b1c9b2a60887b5b43f58e8185969e299164c315cac6220389eb98e7f
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47213a62fa9c69f5f69eec1acd34b9c6ae3c097151b14c86c8a3f84ed7fff05f
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c535d24c8f78df51f3b609038c504bd274057ac2942269306dbf56fbad98dac9
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38b203c487a223bbc58ff68bdb5abcc1dc73df8232401ff6f5ebb4ec48efbf8d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f8d91445b23c7a2b71c10f72fc68a8d50c4ad52ee6befbb53c1732cd7664d4
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": 0.01754693805930865,
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": 458.24,
112
  "eval_steps_per_second": 57.28,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 2844541845504.0,
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": 0.02105632567117038,
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": 458.24,
112
  "eval_steps_per_second": 57.28,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.018950693104053343,
117
+ "grad_norm": 0.12474418431520462,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 10.3719,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.02105632567117038,
124
+ "grad_norm": 0.1344069540500641,
125
+ "learning_rate": 5e-05,
126
+ "loss": 10.3664,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.02105632567117038,
131
+ "eval_loss": 10.365849494934082,
132
+ "eval_runtime": 5.3008,
133
+ "eval_samples_per_second": 452.766,
134
+ "eval_steps_per_second": 56.596,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 3430182813696.0,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null