VERSIL91 commited on
Commit
0662b7d
·
verified ·
1 Parent(s): 784ccc6

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 sha256:08a4aed87e4f6bf1d6f59f55e526fad111e5cd225c597f6857af1cbb3f2f25cd
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b42822e14943a4545a608e5e71794677342f072bf138f6e0fb8a3d3f27b3db
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869050f22cc5e09f2369016e11d40eb3dce21fe2c913ac1670d56c45842f7fc1
3
  size 13005114
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a158ae36756275e196e614bde6aebe4488cb7617b8032ca7d9ffbe09c9676d0
3
  size 13005114
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": 0.00013276190397165533,
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": 103.74,
38
  "eval_steps_per_second": 51.87,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 246322204508160.0,
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": 0.00026552380794331066,
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": 103.74,
38
  "eval_steps_per_second": 51.87,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.000199142855957483,
43
+ "grad_norm": 11.809197425842285,
44
+ "learning_rate": 3e-05,
45
+ "loss": 16.4297,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00026552380794331066,
50
+ "grad_norm": 10.205855369567871,
51
+ "learning_rate": 4e-05,
52
+ "loss": 12.7148,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00026552380794331066,
57
+ "eval_loss": 0.8961522579193115,
58
+ "eval_runtime": 250.7588,
59
+ "eval_samples_per_second": 101.181,
60
+ "eval_steps_per_second": 50.59,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 485180099788800.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null