chauhoang commited on
Commit
a8ae3c1
·
verified ·
1 Parent(s): 07104c3

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07efcb239bf95861e2c3de9937de52f1cc63d97c2f77276ae04c2db6554c8a6d
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faaadf9e6a6e868d5b06ad2e7b05d876d4e1ad16a4786d4104667584ade5ca1f
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc666f53956dd14fd9275bd9c4991c19c98d6436f3348a3ccf170757a88bf73b
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0f24dde2377d3541f5f9ec8e717e510d15d7109c86b2e1ae130019cdc9c804
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d559250c31842a46cac390738afd0fa9c8572aef1ec90ad52af762fd9a38e34e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4eb4ee6bfd962037d021325b66a4604d2e5a6e602e87db44e707e81f5bb20cd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.01224105461393597,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 3.6147,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8574990035189760.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.018361581920903956,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 3.6147,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.014124293785310734,
72
+ "grad_norm": 1.2738316059112549,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.7694,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.014124293785310734,
79
+ "eval_loss": 3.6177690029144287,
80
+ "eval_runtime": 95.6706,
81
+ "eval_samples_per_second": 9.355,
82
+ "eval_steps_per_second": 4.683,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.01647834274952919,
87
+ "grad_norm": 1.5537434816360474,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.6585,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.286248505278464e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null