VERSIL91 commited on
Commit
d4f88d7
·
verified ·
1 Parent(s): ce9d34c

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 sha256:8a4dfb054152e1ea8569efe0ccb66551229be07183a68b8cc769bb05d22667f6
3
  size 161714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1007d3ac10bc2f1e68995fdcf0ba0bc6a00d63c0cbe7ac450b3bab6e9a8eef
3
  size 161714
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c42154281edf1afb43d56436a5c8be2b8160db219836411b0961192b18a3f4c
3
  size 64750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a758d28d9b59699867bc582ef5a235a30fb78b2af7862821c03457e3b466326e
3
  size 64750
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": 0.006988425420397466,
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": 868.155,
38
  "eval_steps_per_second": 434.077,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 10546642944.0,
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": 0.013976850840794933,
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": 868.155,
38
  "eval_steps_per_second": 434.077,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0104826381305962,
43
+ "grad_norm": 1.0225493907928467,
44
+ "learning_rate": 3e-05,
45
+ "loss": 6.9895,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.013976850840794933,
50
+ "grad_norm": 0.9295715093612671,
51
+ "learning_rate": 4e-05,
52
+ "loss": 6.9829,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.013976850840794933,
57
+ "eval_loss": 6.967185020446777,
58
+ "eval_runtime": 0.5617,
59
+ "eval_samples_per_second": 858.171,
60
+ "eval_steps_per_second": 429.085,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 21093285888.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null