havinash-ai commited on
Commit
6a8fcd8
·
verified ·
1 Parent(s): 5d30821

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:568112dc6153382343d80b7d81678c37063adceacfea127c1556b43f9cfdb91c
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eddcff16639c34faec54d6f79996d31eb29148b00ce4270de190c9343d2a334d
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ca392f4080fc89704c052166689f31ef1ad892efdd7df50a65c140a8a1925b3
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acdc37abb3e79e9a77666b3506b322f5a9790576595a9ba3d16290881c3d1a13
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d87e31e70bd00544a171f1f4d95a75e20cac3097ae8bfe86653f57d1d07c450
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1094888e690d760f5dc6beb93863816b44facd96c60f74f3826e1336734dec25
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.003912520064205458,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 86.293,
61
  "eval_steps_per_second": 43.146,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 684282813087744.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005016051364365971,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 86.293,
61
  "eval_steps_per_second": 43.146,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0040128410914927765,
66
+ "grad_norm": 22.51584815979004,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 5.7603,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.005016051364365971,
73
+ "grad_norm": 20.262388229370117,
74
+ "learning_rate": 0.0,
75
+ "loss": 5.777,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 877285657804800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null