dixedus commited on
Commit
6aec7e0
·
verified ·
1 Parent(s): 7a7d354

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fb6e92b847cf069f61d954f2c73559f06a873755d269f18388e998349ee3a37
3
  size 34793120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3490212461544586d69e95fe1e80fe7f5e2f9e0d34533c9a3dedc22b8fe54a
3
  size 34793120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25524a940d660c6b3f36d6c72bf633c5c996ae0d20843da6300d559f4388ccb4
3
  size 18132116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca9618063d1b54b36b7416f9cf454d8a8f7f5c9f43b28fc00252cb8b1dd2601
3
  size 18132116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:482085b98b98d266f913defe3d97147ee62eb55d360c7ba645ca30b8c48b48fe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b950c9eb0145b7f442f50792da98376361b51cf8743ae05f4d082235883412a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
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": 0.508833922261484,
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,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 39.809,
132
  "eval_steps_per_second": 4.976,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 4576827376926720.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.6360424028268551,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 39.809,
132
  "eval_steps_per_second": 4.976,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.5512367491166078,
137
+ "grad_norm": 0.06360410153865814,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 2.5429,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.5936395759717314,
144
+ "grad_norm": 0.07501388341188431,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 2.5588,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.6360424028268551,
151
+ "grad_norm": 0.06902483105659485,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 2.5453,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.6360424028268551,
158
+ "eval_loss": 2.3756144046783447,
159
+ "eval_runtime": 2.9987,
160
+ "eval_samples_per_second": 40.017,
161
+ "eval_steps_per_second": 5.002,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 5721034221158400.0,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null