shibajustfor commited on
Commit
d51d025
·
verified ·
1 Parent(s): 5efc746

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 sha256:58b58dda6c58f4ef3c72407522f8fdc9d3fe61a97e5b52add68d80370add3dcf
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57aa272d219c3bfad02cc054413da166b2748764f3c1ae21e3a1b4fe40217a1
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4641db41f001dc1dc2c0ae43a5cc546510da3447f30e7b404dc8784ce5e6e0ba
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52811d42a1c79c55e44b5faf017533ac770468d02875a7a0f26bdd834d06069e
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:d8b29aef03c991f6bab85ca61524ae5fbc2dacc16323d80f5f5b89b12d9af90c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60dca62740fd71d403885d743187d4b5ea21a6f98b8b6d677eff3898e78e7e5c
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": 0.022190611664295874,
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": 28.79,
61
  "eval_steps_per_second": 14.395,
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": 6677805857243136.0,
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": 0.02844950213371266,
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": 28.79,
61
  "eval_steps_per_second": 14.395,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.02275960170697013,
66
+ "grad_norm": 5.738654136657715,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 5.6701,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.02844950213371266,
73
+ "grad_norm": 5.592751979827881,
74
+ "learning_rate": 0.0,
75
+ "loss": 5.0778,
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": 8591567291940864.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null