mamung commited on
Commit
2cda429
·
verified ·
1 Parent(s): aec04ad

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 sha256:9d652791bc2698526c64f894e7e5e113ef758f874a281b96e2952ca26f332efc
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51938a86b21da17a4ccef7bae1068387c4ca94c38d4d5c37ed121979b35931c8
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de4a6fd98bf834f254bf3b8a25ffe718bd85c4639c1ca2d5b32ef12cd745438f
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4fe83f24b7f7661dd68902f384101f822537fcce9754332361e66da67f6d17
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:884ce308a4b9046b63daa8471de316c7b3c332361554edb94ea15c1aef43590c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0498481dc13586eb056bf15062506f1ff8e314200eb2c09558f026d1062ec3a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
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": 0.005045682700141034,
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": 7.78,
132
  "eval_steps_per_second": 3.89,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 2.148510102234071e+17,
154
  "train_batch_size": 2,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0063071033751762925,
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": 7.78,
132
  "eval_steps_per_second": 3.89,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.00546615625848612,
137
+ "grad_norm": 0.9580327868461609,
138
+ "learning_rate": 0.00017343225094356855,
139
+ "loss": 1.3615,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.005886629816831206,
144
+ "grad_norm": 0.9180206656455994,
145
+ "learning_rate": 0.00016494480483301836,
146
+ "loss": 1.2992,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.0063071033751762925,
151
+ "grad_norm": 0.8730207681655884,
152
+ "learning_rate": 0.00015555702330196023,
153
+ "loss": 1.2218,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.0063071033751762925,
158
+ "eval_loss": 1.368905782699585,
159
+ "eval_runtime": 2719.9889,
160
+ "eval_samples_per_second": 8.836,
161
+ "eval_steps_per_second": 4.418,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 2.6856376277925888e+17,
183
  "train_batch_size": 2,
184
  "trial_name": null,
185
  "trial_params": null