VERSIL91 commited on
Commit
b1ab698
·
verified ·
1 Parent(s): d29a2e9

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 sha256:7a23ec44dce95f7e94b8b15108e29a485c2ddd36f6e6f8fa8fd3c84c74882999
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464c231937ed9650f5633d1beae025a7b23f2a7f73d575d987ccb02c27b90348
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c00176e1ae39938d4993ecb3c0a1d71d911b29f5e72b54605e35fa3d1e46e23
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:481df3f4f8d40e1ffe3c718685d375b7f53567d27b1c1e7adfb4a1371bdaa4c9
3
  size 8075796
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": 0.013588110403397028,
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": 112.726,
38
  "eval_steps_per_second": 56.363,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 86314277928960.0,
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": 0.027176220806794056,
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": 112.726,
38
  "eval_steps_per_second": 56.363,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.02038216560509554,
43
+ "grad_norm": 0.8504584431648254,
44
+ "learning_rate": 3e-05,
45
+ "loss": 1.5389,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.027176220806794056,
50
+ "grad_norm": 0.7962632179260254,
51
+ "learning_rate": 4e-05,
52
+ "loss": 1.4063,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.027176220806794056,
57
+ "eval_loss": 1.4501497745513916,
58
+ "eval_runtime": 2.235,
59
+ "eval_samples_per_second": 110.961,
60
+ "eval_steps_per_second": 55.48,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 163038080532480.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null