ramdhanfirdaus commited on
Commit
3a4cd28
1 Parent(s): bfb0667

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16ccbf888575fd54835b10d90064294290267ea6384ad30f87220a12415c534f
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a59a74d1956a4024e58d1e672829ede9dba9aad64784b5d69f2485e8fe32551
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ed034173cc0172be756e411854a7fca2caa854b2c1dff5be0db43bb6584955
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f72acf25274a664019f70e5655fa4e34b139771772abde791dab35fb24c2f1
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5877e96d88bc486eb083b9ffdaed482a8ee342de0d30ce8efc7818182ef17f26
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cb585a748a6df427c7d10de4790a4f273c745429b7f17704596f5b448d6d2ce
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6701653003692627,
3
- "best_model_checkpoint": "./outputs/checkpoint-900",
4
- "epoch": 0.6557377049180327,
5
  "eval_steps": 100,
6
- "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -133,13 +133,27 @@
133
  "eval_samples_per_second": 43.796,
134
  "eval_steps_per_second": 5.48,
135
  "step": 900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 100,
139
  "max_steps": 4116,
140
  "num_train_epochs": 3,
141
  "save_steps": 100,
142
- "total_flos": 5.365348992702874e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
1
  {
2
+ "best_metric": 1.6471772193908691,
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,
 
133
  "eval_samples_per_second": 43.796,
134
  "eval_steps_per_second": 5.48,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 1.6592,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 1.6471772193908691,
146
+ "eval_runtime": 143.2508,
147
+ "eval_samples_per_second": 43.797,
148
+ "eval_steps_per_second": 5.48,
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": 5.961752561722982e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }