robiulawaldev commited on
Commit
903d278
·
verified ·
1 Parent(s): 2f1df4c

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 sha256:4dd0e1153674bcd55996847a8807c34e63010d48590a3e637a0ebc2c711f1720
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce0c3606224ddf9ade3d302f813514dd743b3c0ee6e4f1c76cd6ae48f32d07c
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cbe8a1a6b357a69cc5269a67c718a96d161becd852e8d720989999f1ea09312
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0eae8cd57cb831eab8cb9b2e7a414983c46f66696e464de1e63a6be97f1e04
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecd5dda6211db43329456f947b9bdb53d4ac05d8872017cb96bef25db1267364
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc3b30bde5659cc182ea9d1f3531a67232f428baf59f2705e59e9c0e5ef8898
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
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": 0.00012795810848386865,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 37.231,
46
  "eval_steps_per_second": 18.616,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 716275031998464.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.000191937162725803,
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,
 
45
  "eval_samples_per_second": 37.231,
46
  "eval_steps_per_second": 18.616,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.00014764397132754076,
51
+ "grad_norm": 3.2244198322296143,
52
+ "learning_rate": 0.0002,
53
+ "loss": 0.7387,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.000191937162725803,
58
+ "eval_loss": 0.6604138612747192,
59
+ "eval_runtime": 1150.8851,
60
+ "eval_samples_per_second": 37.17,
61
+ "eval_steps_per_second": 18.585,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1080695662313472.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null