VERSIL91 commited on
Commit
0d1afc8
·
verified ·
1 Parent(s): ebd51fb

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 sha256:5f979e4cde4eaa6b73c68760d2083b4813c55e6ca18b21f07312d730cc78171b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36caa77a2b7b69d83120178df3b2b1061f744cd493392c9fa98210090aba08a4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3a8b7079894336bfe68c6e3194b6d714159744e80291d6bc3675d19ade78161
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5440e4ec072f6aeee27822fa65907c2bbe3913b5a250c17acef4207f7a69cda2
3
  size 43122580
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": 0.003170514217774695,
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": 20.291,
38
  "eval_steps_per_second": 10.155,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1479651398516736.0,
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": 0.00634102843554939,
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": 20.291,
38
  "eval_steps_per_second": 10.155,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.004755771326662043,
43
+ "grad_norm": 9.65805435180664,
44
+ "learning_rate": 3e-05,
45
+ "loss": 4.8463,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00634102843554939,
50
+ "grad_norm": 11.565286636352539,
51
+ "learning_rate": 4e-05,
52
+ "loss": 5.1627,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00634102843554939,
57
+ "eval_loss": 5.065210819244385,
58
+ "eval_runtime": 51.8197,
59
+ "eval_samples_per_second": 20.513,
60
+ "eval_steps_per_second": 10.266,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2959302797033472.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null