VERSIL91 commited on
Commit
9513def
·
verified ·
1 Parent(s): 1080cc3

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 sha256:8c7a24103b663f56a3404ac485129bbb94f00f1d39bb9ace00f908f26a64f2aa
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1942d86e038035720ad88b92081a41ae803d0a0703ff30194020af481d4e4339
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9685c7d0b0f5345a58782020655cb4f4c4b833e55e8de37222072d80c200c315
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83024fbd9a4a65a906300a0a7f8aae5552a62682265d4db6bcde00a85f528ad
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
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": 0.003656724945720489,
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": 41.406,
38
  "eval_steps_per_second": 20.703,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1479651398516736.0,
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": 0.007313449891440978,
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": 41.406,
38
  "eval_steps_per_second": 20.703,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.005485087418580734,
43
+ "grad_norm": 3.3355343341827393,
44
+ "learning_rate": 3e-05,
45
+ "loss": 2.5934,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.007313449891440978,
50
+ "grad_norm": 3.516296625137329,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.6304,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.007313449891440978,
57
+ "eval_loss": 2.4208180904388428,
58
+ "eval_runtime": 22.2861,
59
+ "eval_samples_per_second": 41.371,
60
+ "eval_steps_per_second": 20.686,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2959302797033472.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null