adammandic87 commited on
Commit
8f44af0
·
verified ·
1 Parent(s): 6191b80

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2905b8f58588c4f845cb334f9193beb992f7033709a0ed2435ab461e5230a9be
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e02b16238cc9a689ef4cc394f791a2dde10563b7e28fa8f9970383ca6cff4a4
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:193df67499d433156045a2b796561e5c33969c748da54bb30be0baf8e0a9eae6
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a957c6254c6d2af630203438fa1cbc88ad140bf2a6b7a55c2cef042e09426ad
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41656c856e2a4df73637aab8ca1add18efc41bb01dff2d3e743b7b1678b8ca96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b1ba37de46bd55947921e981af81175de41ab0e33c654019eefd79b863b1a5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.002197291415774017,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 62.268,
46
  "eval_steps_per_second": 31.14,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 237843788070912.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0032959371236610255,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 62.268,
46
  "eval_steps_per_second": 31.14,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0025353362489700195,
51
+ "grad_norm": 0.6566107273101807,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 3.411,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0032959371236610255,
58
+ "eval_loss": 3.748792886734009,
59
+ "eval_runtime": 80.9379,
60
+ "eval_samples_per_second": 61.566,
61
+ "eval_steps_per_second": 30.789,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 360601872236544.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null