chauhoang commited on
Commit
09d8fd5
·
verified ·
1 Parent(s): dac261b

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 sha256:0bab1b93f49f0b98112ceebeff08153399251ad154d30a00583c4b1de743678d
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db76a4af169edbd8b02f4417924c2330959a17eac8e884e93288de14b75d7428
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c89caa81679974bc6b1450f9de1605fda1dad6afba117f79671547817afeb32a
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9047b064d422f8b6f1daee0998b36b7761fd0f4d00686496d3edc5052e9fe16
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4789694b0dfbba236adc1e0423cccff54c291754e75185fa5ae6a3664fb3ce4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6684d632e0ed9894b7d3581195993fbfd0a1de05dcd5960c38ed169d3e9d554
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": 0.010692987867571458,
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": 0.6215,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 625418340139008.0,
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": 0.016039481801357187,
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": 0.6215,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.012338062924120914,
72
+ "grad_norm": 1.4033981561660767,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5869,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.012338062924120914,
79
+ "eval_loss": 0.6099783182144165,
80
+ "eval_runtime": 27.1649,
81
+ "eval_samples_per_second": 37.696,
82
+ "eval_steps_per_second": 18.848,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014394406744807731,
87
+ "grad_norm": 1.5280038118362427,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5931,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 938127510208512.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null