VERSIL91 commited on
Commit
726c20e
·
verified ·
1 Parent(s): 8ddd586

Training in progress, step 5, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:852f32d993d8f78581c21ff1d69a9245c36324aec4ff09e716567a3f63792460
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe27b9df1c235ec73e2f1a175199985e364f1ef095c0541ebd6ea54df3f8b76
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c7bf08c012dcb4271e229031c21938551160e679b7c39fe950b3a695a03162b
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d60e27a5523814f104aa2f6b92497b61931b68d7a2ce1d30722925a3bf7192a
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0288028802880288,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 14.003,
60
  "eval_steps_per_second": 7.002,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 2337138695208960.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.036003600360036005,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 14.003,
60
  "eval_steps_per_second": 7.002,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.036003600360036005,
65
+ "grad_norm": 4.515499114990234,
66
+ "learning_rate": 5e-05,
67
+ "loss": 13.5987,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 2870170327449600.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null