flytech commited on
Commit
101cfc2
·
1 Parent(s): e9102f8

Training in progress, step 1100, 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:f00956cad5b242d28d69ef7f923e91b71ba0e20a0414975ebf772dd8e9f57161
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5c897c76d3e8f27fc7136e672c3280ff050a7fcd4091363e23ea0750090dd4
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57a9fdefbec929aa5b96d3138d9e4e530cab3e268afb55db0aaf843cc8c9e4c9
3
  size 21689885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842b8c344b8c65bc1a13c4faa1194017d28fc956dd3a367e28f2301196ab2a2c
3
  size 21689885
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4907f2830ba6f2777cd22e1a2deb95c664e378deb1ca91ebe14c24ed9b4dbb72
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ddda47155dbb083b66c8282a99e7ea39e7cfeb4728de3763b68101fafe74fc
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1969c6d78c022e21e37f015f4d4c5f85f6638038ce809e096a3a6a48192ec9d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a93f99d4a6617303f18bd3ba2a9725dae8b6ebbcc6fee0956ed65621ae9dfb
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.7786666666666666,
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,
@@ -137,13 +137,26 @@
137
  "eval_samples_per_second": 1.779,
138
  "eval_steps_per_second": 0.223,
139
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  }
141
  ],
142
  "logging_steps": 100,
143
  "max_steps": 1686,
144
  "num_train_epochs": 3,
145
  "save_steps": 100,
146
- "total_flos": 3.674986443177984e+17,
147
  "trial_name": null,
148
  "trial_params": null
149
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.9564444444444444,
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,
 
137
  "eval_samples_per_second": 1.779,
138
  "eval_steps_per_second": 0.223,
139
  "step": 1000
140
+ },
141
+ {
142
+ "epoch": 1.96,
143
+ "learning_rate": 3.8760711931443636e-05,
144
+ "loss": 0.5561,
145
+ "step": 1100
146
+ },
147
+ {
148
+ "epoch": 1.96,
149
+ "eval_runtime": 1406.3866,
150
+ "eval_samples_per_second": 1.778,
151
+ "eval_steps_per_second": 0.223,
152
+ "step": 1100
153
  }
154
  ],
155
  "logging_steps": 100,
156
  "max_steps": 1686,
157
  "num_train_epochs": 3,
158
  "save_steps": 100,
159
+ "total_flos": 4.090239148621824e+17,
160
  "trial_name": null,
161
  "trial_params": null
162
  }