VERSIL91 commited on
Commit
4023296
·
verified ·
1 Parent(s): 9f09f2b

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 sha256:4270f17b1081e5f0be63fdf5f3c82414e2e251a40f4c988e3e940eebd4635457
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297c28cd81c3f094bfe8e24b41c53ce900e5b16af8f1712fc03325af3de8e246
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:228ecdda8c635eb34647ec9c0266784102f779db62ff527fd876f7d4ee201bd8
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:903c9d71119c38a75cceb1007f915477bd189159e9bd4195c8e54e905f2fb180
3
  size 19859140
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": 0.002749613335624678,
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": 68.44,
38
  "eval_steps_per_second": 34.248,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 364835540828160.0,
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": 0.005499226671249356,
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": 68.44,
38
  "eval_steps_per_second": 34.248,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0041244200034370165,
43
+ "grad_norm": 3.226841688156128,
44
+ "learning_rate": 3e-05,
45
+ "loss": 3.9862,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.005499226671249356,
50
+ "grad_norm": 3.114522933959961,
51
+ "learning_rate": 4e-05,
52
+ "loss": 3.95,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.005499226671249356,
57
+ "eval_loss": 3.8232789039611816,
58
+ "eval_runtime": 18.0219,
59
+ "eval_samples_per_second": 67.973,
60
+ "eval_steps_per_second": 34.014,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 762100907507712.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null