rizkyjun commited on
Commit
a8985d2
1 Parent(s): bc1882f

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 sha256:76a459e70707e9f9a3497330ba03b6326e00a0001b85f2ebe53fe9643f91e5cd
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69766648ba6587f424193aa61d2be2a77d88fc6665b6972e465baa4ae135b2ab
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eeb55be73bed4fc1687c1b6ce5766981e0c0d45e42f822b2bf85754ca015e865
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c127e0c55dae8694d9ed23c958bf86e2600a75ca0e7979232bd29eedb41cae16
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e2584adcfe5878130368943010052e98d7f9569785b451bb350577d373a1f2f
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3587699f49f930b2c0cd17b5071fff6f2cf9326eebadb8adb2db8be4db4ec081
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": 2.4054911136627197,
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": 30.668,
134
  "eval_steps_per_second": 3.837,
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": 2.625477585518592e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
1
  {
2
+ "best_metric": 2.3888440132141113,
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": 30.668,
134
  "eval_steps_per_second": 3.837,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 2.389,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 2.3888440132141113,
146
+ "eval_runtime": 204.475,
147
+ "eval_samples_per_second": 30.683,
148
+ "eval_steps_per_second": 3.839,
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": 2.917579599470592e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }