VERSIL91 commited on
Commit
689f996
1 Parent(s): c9dad50

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0449953e256667ee14724b9a713e9f0179e96c7f9d8c1177ab78228c3d08e753
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f84907a3ca78e1ca01664111c24d04e1ec08410037648dea945b43856465b22
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09d6d61337632c4e2440902b1f5fe3430f89adeda695ef7b5d373ac1ed92b04
3
  size 20632762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bdd9e1e48f38bbd25ae301adfd54e5c56ce8b9b28222bc11cac6889acec4fa
3
  size 20632762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.0006876544536370474,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 71.797,
38
  "eval_steps_per_second": 35.906,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 391582234705920.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0013753089072740948,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 71.797,
38
  "eval_steps_per_second": 35.906,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0010314816804555711,
43
+ "grad_norm": 15.039040565490723,
44
+ "learning_rate": 3e-05,
45
+ "loss": 6.1838,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0013753089072740948,
50
+ "grad_norm": 10.66008186340332,
51
+ "learning_rate": 4e-05,
52
+ "loss": 4.5854,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0013753089072740948,
57
+ "eval_loss": 5.231777191162109,
58
+ "eval_runtime": 111.1543,
59
+ "eval_samples_per_second": 44.074,
60
+ "eval_steps_per_second": 22.041,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 795401414246400.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null