VERSIL91 commited on
Commit
02eb12b
·
verified ·
1 Parent(s): dafd329

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:bc471c2b1eda8b927031a6d3e8cd3255b883eda2031191ea12480d6742156da5
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5227582055d82df26701de8cc1f636f78f000a8896b5dce4967328f6fb3731f
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ee57259179fe5b8df2c49c95a676c914979d67109aae916ab55d557d48ed9a1
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2c0b857d405ba1c2d49af505fec551cf81bd42011bb1e10321d9e33b2f157b
3
  size 41459700
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": 0.014035087719298246,
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": 21.359,
38
  "eval_steps_per_second": 10.679,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1394108836872192.0,
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": 0.028070175438596492,
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": 21.359,
38
  "eval_steps_per_second": 10.679,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.021052631578947368,
43
+ "grad_norm": 0.4889359772205353,
44
+ "learning_rate": 3e-05,
45
+ "loss": 0.4988,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.028070175438596492,
50
+ "grad_norm": 0.4712343215942383,
51
+ "learning_rate": 4e-05,
52
+ "loss": 0.4643,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.028070175438596492,
57
+ "eval_loss": 0.46725717186927795,
58
+ "eval_runtime": 12.5186,
59
+ "eval_samples_per_second": 19.172,
60
+ "eval_steps_per_second": 9.586,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2788217673744384.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null