ramdhanfirdaus commited on
Commit
1955a18
1 Parent(s): 7b5a043

Training in progress, step 1100, checkpoint

Browse files
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eb2155785c902b07f4c270e2c5661f075b5f97eec7119dc0af7a9020d2a0fd6
3
  size 50349441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3885f4e3e78a9742f5082bbba27e73fb0c203a9fd13ef579f9199ab68c4f161e
3
  size 50349441
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77d361f5aa6aa86bc28600464f80e71b075c93630c0492a348c2b160ae9bd377
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a40b2af77334cbb2abe1c91fc12c19101f537fed1041335bf9a8fbca457094
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:367394aed610ff7068eaf27da3eb89a6cd4769f26c2abeadffb65a7a6d3952cd
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4887eda634f542d0c8496ee30ab1130b0b9a4766dc9d31a2130fdb8d2444505
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6349676847457886,
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": 43.509,
148
  "eval_steps_per_second": 5.444,
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": 5.962359246697267e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }
 
1
  {
2
+ "best_metric": 1.6135053634643555,
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": 43.509,
148
  "eval_steps_per_second": 5.444,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 1.6273,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 1.6135053634643555,
160
+ "eval_runtime": 144.1005,
161
+ "eval_samples_per_second": 43.539,
162
+ "eval_steps_per_second": 5.448,
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": 6.557572892531098e+16,
171
  "trial_name": null,
172
  "trial_params": null
173
  }