VERSIL91 commited on
Commit
55901b6
·
verified ·
1 Parent(s): f01a596

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 sha256:362ff6189b4aab2c48a830576b3248698e84ece83f30b3e242259b68ae024e09
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5797f003860f432bed96e5b2820306a9ce460e109a23f4183e7eb22e8b2b1d8
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d41ece9ff0d9ff5952fbb312220c72ccab2a7885f16375594132a2e37bbfa18f
3
  size 3633466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc3ebaf1a419d6b676e9d55a8a337d2ad9166765edc426e241942c258eda16c
3
  size 3633466
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": 0.00037954715280331155,
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": 91.365,
38
  "eval_steps_per_second": 45.687,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 28291436642304.0,
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": 0.0007590943056066231,
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": 91.365,
38
  "eval_steps_per_second": 45.687,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0005693207292049674,
43
+ "grad_norm": 0.3894922137260437,
44
+ "learning_rate": 3e-05,
45
+ "loss": 2.9739,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0007590943056066231,
50
+ "grad_norm": 0.4525291323661804,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.6925,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0007590943056066231,
57
+ "eval_loss": 5.884451389312744,
58
+ "eval_runtime": 97.4136,
59
+ "eval_samples_per_second": 91.106,
60
+ "eval_steps_per_second": 45.558,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 58297505808384.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null