kostiantynk1205 commited on
Commit
fe5477c
·
verified ·
1 Parent(s): 26f1645

Training in progress, step 50, 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:b6e6aee215e5301fdc5ce3754b1f2ea164d935004d6f9db9464ead89550f7f2c
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771c6f642e9ee5e5a483374cff2e1ecd26b87ecc55d7b1aa3b08adf4f6f83739
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f318c7631eda1f27274991b77b251da888eea4192344e7aa1b303094523052c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63869a710c0c6b01e084e1464a10ba459ffe6bf9743d53f2cd8bdb966e17f0ff
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:bbbabebe5b0848c856d841f6dbe8db82bb44f990eb1381f0226471bd7fa38a4c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f848446bb5c83fa78e983d11b42684960c897132ad0ce85bc64c6efdd504b41c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.09523809523809523,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 18.302,
61
  "eval_steps_per_second": 9.204,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.3188855289085952e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1221001221001221,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 18.302,
61
  "eval_steps_per_second": 9.204,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.09768009768009768,
66
+ "grad_norm": 4.531153202056885,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 3.7785,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.1221001221001221,
73
+ "grad_norm": 4.782752990722656,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.7577,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.7044733247356928e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null