tarabukinivan commited on
Commit
69ea815
·
verified ·
1 Parent(s): 480f0dc

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d1e01116430185c2d853ee4465a93e686e5d57f6455a95de16c5dd0e2f81ae7
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eed38712468fc0f87f6b2923be23a26a399a36d737d9c3ec3f71d904be7424a
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b57b840371c90d5e4d001961522bf0330e6d24583041465d969a99b6968a4227
3
  size 239892858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf1441568dbde055a78842681a69d89d357f08e49823ce04eee45027b42cbf15
3
  size 239892858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45c8827f349044224c7f432996e313bccb81b889418433d17cdff84bd2044472
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d45af57d691377fa169679cd3d91e6c22a68044bebb251e6cdde561e066a989
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0020063450662720856,
5
  "eval_steps": 13,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -130,6 +130,27 @@
130
  "eval_samples_per_second": 19.514,
131
  "eval_steps_per_second": 9.758,
132
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
133
  }
134
  ],
135
  "logging_steps": 3,
@@ -144,12 +165,12 @@
144
  "should_evaluate": false,
145
  "should_log": false,
146
  "should_save": true,
147
- "should_training_stop": false
148
  },
149
  "attributes": {}
150
  }
151
  },
152
- "total_flos": 5548743227080704.0,
153
  "train_batch_size": 2,
154
  "trial_name": null,
155
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0025079313328401067,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
130
  "eval_samples_per_second": 19.514,
131
  "eval_steps_per_second": 9.758,
132
  "step": 39
133
+ },
134
+ {
135
+ "epoch": 0.0021066623195856895,
136
+ "grad_norm": 0.2568337917327881,
137
+ "learning_rate": 1.9098300562505266e-05,
138
+ "loss": 1.2448,
139
+ "step": 42
140
+ },
141
+ {
142
+ "epoch": 0.002257138199556096,
143
+ "grad_norm": 0.25470566749572754,
144
+ "learning_rate": 7.612046748871327e-06,
145
+ "loss": 1.0677,
146
+ "step": 45
147
+ },
148
+ {
149
+ "epoch": 0.0024076140795265028,
150
+ "grad_norm": 0.22263048589229584,
151
+ "learning_rate": 1.231165940486234e-06,
152
+ "loss": 1.1793,
153
+ "step": 48
154
  }
155
  ],
156
  "logging_steps": 3,
 
165
  "should_evaluate": false,
166
  "should_log": false,
167
  "should_save": true,
168
+ "should_training_stop": true
169
  },
170
  "attributes": {}
171
  }
172
  },
173
+ "total_flos": 7030705703878656.0,
174
  "train_batch_size": 2,
175
  "trial_name": null,
176
  "trial_params": null