rizkyjun commited on
Commit
3f4fd57
1 Parent(s): d66f92f

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 sha256:57aa977d45153c3463856e66c16fa1e99ea23131f33ce947df37af305ee5fc8b
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c5f0dbf90ce0773bf366132a2914c1c76cc6844b8bd1dd3d373932871fc8f5f
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:567942077b5bc24670bbaddccc3f562685ebc30536aab685800929dcc359ee21
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ff097348929f737de5e1f3683a008f91e1ba74accb6599c925eb581c325f4b
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d66b1a8c16da8ebf7970425c7c306a82ffa223990ce4f0cb56084c069e08e81
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:741013df0f2c38258d3aad4259e56feb3245d57324e1c9624b55abdc9cee37a6
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": 2.4826207160949707,
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": 30.688,
134
  "eval_steps_per_second": 3.84,
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": 2.562316410028032e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
1
  {
2
+ "best_metric": 2.463895559310913,
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": 30.688,
134
  "eval_steps_per_second": 3.84,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 2.4724,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 2.463895559310913,
146
+ "eval_runtime": 204.6362,
147
+ "eval_samples_per_second": 30.659,
148
+ "eval_steps_per_second": 3.836,
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": 2.84738668720128e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }