flytech commited on
Commit
2e2ce76
·
1 Parent(s): a4e84a0

Training in progress, step 700, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f57691dcd7e933b52c5d9a5166dd8caf267ed92a968a040b9f470eb982b7c27
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e91a1a8e96924bbcd73abc051fa8a13678036d9348c20a1683b969fccbecee
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec84ae944a4cc142d3f93478ccc0616a338cda7251f06ce0a53b35001b957960
3
  size 21689885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8aac4cb37632a2b687539076c10496a1fa1ed9950c97d1c4b6b8ea744855b90
3
  size 21689885
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:664719eaa329cdcebc74bdfaf903302609da1e0efb1bc47661be48112583bcc7
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b8f5c907aed8338712b8f177ba38001ec7dd83fd2543620cdd6e8cb262e4df
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1200aa065149a5c4bcf6d6753675764c297af325981700a57cc5d1430df50525
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02d5c23307ae8df91bb7174151c2ade133a92bd9c4c2b8d149ca1030193276b
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": 1.0666666666666667,
5
  "eval_steps": 100,
6
- "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -85,13 +85,26 @@
85
  "eval_samples_per_second": 1.783,
86
  "eval_steps_per_second": 0.223,
87
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  }
89
  ],
90
  "logging_steps": 100,
91
  "max_steps": 1686,
92
  "num_train_epochs": 3,
93
  "save_steps": 100,
94
- "total_flos": 2.013975621402624e+17,
95
  "trial_name": null,
96
  "trial_params": null
97
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.2444444444444445,
5
  "eval_steps": 100,
6
+ "global_step": 700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
85
  "eval_samples_per_second": 1.783,
86
  "eval_steps_per_second": 0.223,
87
  "step": 600
88
+ },
89
+ {
90
+ "epoch": 1.24,
91
+ "learning_rate": 0.0001,
92
+ "loss": 0.5692,
93
+ "step": 700
94
+ },
95
+ {
96
+ "epoch": 1.24,
97
+ "eval_runtime": 1404.1983,
98
+ "eval_samples_per_second": 1.78,
99
+ "eval_steps_per_second": 0.223,
100
+ "step": 700
101
  }
102
  ],
103
  "logging_steps": 100,
104
  "max_steps": 1686,
105
  "num_train_epochs": 3,
106
  "save_steps": 100,
107
+ "total_flos": 2.429228326846464e+17,
108
  "trial_name": null,
109
  "trial_params": null
110
  }