VERSIL91 commited on
Commit
ce45990
·
verified ·
1 Parent(s): c2e6faf

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:dbc76c85fd2ea6d51cea5b9f28ec3fd5afc84207260296eda8ea2098b9e46712
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69d808bea7bcdca77b1cf72a8e4fb089e3a2a7e04f22e30f46c45a02c2543d3
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eae0b8e8276b01cb2f653c1975afb9172283eb0bbfa6206347234f2f6ce41ad
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cc66c92607a98f12b8533e9d2380401b61beb0593a87784b467205c177aa91
3
  size 41119636
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": 0.001527154719862556,
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": 28.495,
38
  "eval_steps_per_second": 14.247,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1977387508039680.0,
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": 0.003054309439725112,
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": 28.495,
38
  "eval_steps_per_second": 14.247,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.002290732079793834,
43
+ "grad_norm": 0.2686094641685486,
44
+ "learning_rate": 3e-05,
45
+ "loss": 0.6843,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.003054309439725112,
50
+ "grad_norm": 0.22620728611946106,
51
+ "learning_rate": 4e-05,
52
+ "loss": 0.5546,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.003054309439725112,
57
+ "eval_loss": 0.6147086024284363,
58
+ "eval_runtime": 77.7071,
59
+ "eval_samples_per_second": 28.389,
60
+ "eval_steps_per_second": 14.194,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3995970589163520.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null