kostiantynk-out commited on
Commit
4640960
·
verified ·
1 Parent(s): 285f549

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 sha256:5e14b18df2c6b40498fd4c7f3ee63f1cfa38a047714131fc5ccdd4443bc2f41c
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c40eb520420fc1a019de3e613e5a68d84d788c6b1120d7b138b8bf24b8a51b1
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:072accb14366bf6a5f9b49f844febf1282052f5038bb058bd56df8a3ed81a228
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062f879ec4ce5a25e6d0bab0b38c4bd51bdc4e3fa94023ba94348a92490ca15f
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19f671f97d721dc915fd4d99adc75c236b138ac6507f128ca203a7f2700368aa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7908ee2973a878ea7824bdd2f61631c3215514837bf77a00521938e104a36012
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": 0.006369686823731167,
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": 26.068,
61
  "eval_steps_per_second": 13.034,
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": 7044340471824384.0,
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": 0.0081662651586297,
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": 26.068,
61
  "eval_steps_per_second": 13.034,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0065330121269037604,
66
+ "grad_norm": 3.450343132019043,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 9.819,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0081662651586297,
73
+ "grad_norm": 5.672661304473877,
74
+ "learning_rate": 0.0,
75
+ "loss": 9.3623,
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": 9080277024374784.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null