ramdhanfirdaus commited on
Commit
45de4ff
1 Parent(s): 01d50fb

Training in progress, step 1100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e204a04da8c9218f2ba802f46425f9cd1e86d82835c73818cb8d5f5a39d3c8f
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cefae802cfbecd2725077d9393d82fe538f1becaea47fc1680c97e3fc9caeb6
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d140a5f804ad0468ab4100e5ea3900351fccc4d82232b90034d288e642e94fd2
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b462c18b2bbaf5e3948040483b0c1fd7977c05e7964e4bedfe341e0a854c79
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ba1d0fda7cecda3732f983458a042256076da8cddf865f2c4b33829d7dcdd1
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a715695621b29a5bc3a047f2409a8533344cff46a1200fae816a8ba63da770
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a5b6d164040e04936ade41907e85a9b8d18c7eec435aae9acf42177d440544
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed812891698c785c43e6b058c6acf6649c2fbbcf6509f75e58beb0e45a7d710
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7669757604599,
3
- "best_model_checkpoint": "./outputs/checkpoint-1000",
4
- "epoch": 0.7285974499089253,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -147,13 +147,27 @@
147
  "eval_samples_per_second": 43.703,
148
  "eval_steps_per_second": 5.468,
149
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 100,
153
  "max_steps": 4116,
154
  "num_train_epochs": 3,
155
  "save_steps": 100,
156
- "total_flos": 5.955808807482163e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }
 
1
  {
2
+ "best_metric": 1.7429991960525513,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1100",
4
+ "epoch": 0.8014571948998178,
5
  "eval_steps": 100,
6
+ "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
147
  "eval_samples_per_second": 43.703,
148
  "eval_steps_per_second": 5.468,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 1.76,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 1.7429991960525513,
160
+ "eval_runtime": 143.4985,
161
+ "eval_samples_per_second": 43.722,
162
+ "eval_steps_per_second": 5.47,
163
+ "step": 1100
164
  }
165
  ],
166
  "logging_steps": 100,
167
  "max_steps": 4116,
168
  "num_train_epochs": 3,
169
  "save_steps": 100,
170
+ "total_flos": 6.550064066907341e+16,
171
  "trial_name": null,
172
  "trial_params": null
173
  }