auxyus commited on
Commit
e7d6088
·
verified ·
1 Parent(s): 427f7b1

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:ed0d09a18456cb4a22bfb0c48d4042136a45b74511322ca20b7d4ed194d54c88
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680ddfa6814d59919c0076c072cf1f1d8730e7555e534a9e5de1c2ee1946f844
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:028d0eb2a8acfafbe84193b62459bd66f6c09756456c93383bef6df7acc0f8fb
3
  size 111412180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:291cf092537a9997910f645e28a0c0d4aac20e01556955bb7a3c2b551549b7f3
3
  size 111412180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aa02f64b1ce38774d3f28a7edd647b233b72e77d93204357b568e7977c5ef70
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70815b76403150f357476f8c7c6203eb49775afd453225f5b00784817bcbbc4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
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": 0.48484848484848486,
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": 11.076,
132
  "eval_steps_per_second": 1.418,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 6.102359434749542e+16,
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": 0.6060606060606061,
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": 11.076,
132
  "eval_steps_per_second": 1.418,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.5252525252525253,
137
+ "grad_norm": 0.0010147533612325788,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 0.0,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.5656565656565656,
144
+ "grad_norm": 0.0007608148152939975,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 0.0,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.6060606060606061,
151
+ "grad_norm": 0.0006441783043555915,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 0.0,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.6060606060606061,
158
+ "eval_loss": 1.3838871382176876e-05,
159
+ "eval_runtime": 11.276,
160
+ "eval_samples_per_second": 11.085,
161
+ "eval_steps_per_second": 1.419,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 7.627949293436928e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null