VERSIL91 commited on
Commit
bd55652
1 Parent(s): 98421f3

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:d1153cf0a68cac999393f59476a2d4e5de07a401bfbdd59484c08675c8c8a363
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e625728c72bf1abf930ba18ead72ec53fb0b1b6979c03b3acc4bf15867090ec
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947005a82f5ed46a60769bf0169e84d9e4759ab90e2842022b83faf1696a0e1e
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccfdbb123f59b9042212459ee836e6a3ff373fb8c40d7f49c137636f05baa188
3
  size 63974
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": 0.00813421453990849,
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": 176.773,
38
  "eval_steps_per_second": 88.599,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 197196349440.0,
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": 0.01626842907981698,
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": 176.773,
38
  "eval_steps_per_second": 88.599,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.012201321809862735,
43
+ "grad_norm": 0.05969623476266861,
44
+ "learning_rate": 3e-05,
45
+ "loss": 10.3912,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.01626842907981698,
50
+ "grad_norm": 0.06552771478891373,
51
+ "learning_rate": 4e-05,
52
+ "loss": 10.3887,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.01626842907981698,
57
+ "eval_loss": 10.389606475830078,
58
+ "eval_runtime": 1.7974,
59
+ "eval_samples_per_second": 230.892,
60
+ "eval_steps_per_second": 115.724,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 387927244800.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null