robiulawaldev commited on
Commit
fc926b6
·
verified ·
1 Parent(s): 807f7f9

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09cd71d593251741cccc7701ec9e223e84e8d9dcd240c7777b7e3461ed2d2524
3
  size 682685984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a5d0f01b77802e68db4f9d611f70edab43a9232ce53e82b68060805f1fcf13
3
  size 682685984
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4f86960f918313f8b9dfbbf8ef758f4588efe47fb179e4fe2de276428ee074f
3
  size 85498196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45bf7311db649b1b18934ddb295f4935f1fa9cbd95b36f8a6cd8f49375867b41
3
  size 85498196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1de830288606b38e6cfca5b625f3b4e9a64b2aee6f091f612490c0af98ad6b5b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f33eab43f94c54c28d44f815245195ca47f5bccffb6fd58d916729befff7f8a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed58e5b5053e09a44cd1fe67ab0f07cc790b003abec6db1f957ea4f926e4423
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
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": 0.04912280701754386,
5
  "eval_steps": 14,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,28 @@
45
  "eval_samples_per_second": 72.834,
46
  "eval_steps_per_second": 18.209,
47
  "step": 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +86,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1849904741744640.0,
68
  "train_batch_size": 4,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.07368421052631578,
5
  "eval_steps": 14,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 72.834,
46
  "eval_steps_per_second": 18.209,
47
  "step": 28
48
+ },
49
+ {
50
+ "epoch": 0.05263157894736842,
51
+ "grad_norm": 2.7136929035186768,
52
+ "learning_rate": 0.0002,
53
+ "loss": 3.0622,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.07017543859649122,
58
+ "grad_norm": 2.9015309810638428,
59
+ "learning_rate": 0.0002,
60
+ "loss": 3.1672,
61
+ "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.07368421052631578,
65
+ "eval_loss": 1.512506127357483,
66
+ "eval_runtime": 3.2972,
67
+ "eval_samples_per_second": 72.789,
68
+ "eval_steps_per_second": 18.197,
69
+ "step": 42
70
  }
71
  ],
72
  "logging_steps": 10,
 
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 2774857112616960.0,
90
  "train_batch_size": 4,
91
  "trial_name": null,
92
  "trial_params": null