ramdhanfirdaus commited on
Commit
87edcea
1 Parent(s): d95c73e

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 sha256:251f0d23e7cc7ff7b02b7f89375964c7785569584b8c7171f1241c1d0e2a663a
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e204a04da8c9218f2ba802f46425f9cd1e86d82835c73818cb8d5f5a39d3c8f
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3cea6b935081f89ad900a908bab0539f9e0331029e1a7be684cc13797049c52
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d140a5f804ad0468ab4100e5ea3900351fccc4d82232b90034d288e642e94fd2
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:c9252c51de1df31c7fa9db77b24072fda5aaa497928e7fedd7c0f01cfbd17906
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ba1d0fda7cecda3732f983458a042256076da8cddf865f2c4b33829d7dcdd1
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cf3d71e92538f8852c28d0ab56db4f9cd9e4b98c0e807cde568075961dd5196
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a5b6d164040e04936ade41907e85a9b8d18c7eec435aae9acf42177d440544
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7926479578018188,
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": 43.711,
134
  "eval_steps_per_second": 5.469,
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": 5.359923998077747e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
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,
 
133
  "eval_samples_per_second": 43.711,
134
  "eval_steps_per_second": 5.469,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 1.7803,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 1.7669757604599,
146
+ "eval_runtime": 143.5614,
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
  }