philip-hightech commited on
Commit
f403be9
·
verified ·
1 Parent(s): 730f3a8

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:c54a2249fdc089fb454026607dce0400de266d4c9d43307ebd87559f0bf9d303
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac2eb8a5750a8dbe35b1dfe56ab1f5ae3dbd845afcad4ab5d9a91744075b4d6
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c01d872942ab89223d4c938b6469b983d4c7b87039f68ee34169c944738391f
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d0dcbd3465dfc75e88c5d3a027cf1d6400bf3e250d22eccdfa35164af87359
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c96db4829b9891657f1ce7f91387d734fa74eb83875cd8bbcf019a82c894512
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619af8b1ffeda21fd1f80d1c9c048863058d34f456129a40227423e9e8adcac1
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": 0.000688541087365271,
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": 40.081,
61
  "eval_steps_per_second": 20.042,
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": 1010022063538176.0,
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": 0.0008827449838016295,
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": 40.081,
61
  "eval_steps_per_second": 20.042,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0007061959870413037,
66
+ "grad_norm": 9.540621757507324,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 3.4454,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0008827449838016295,
73
+ "grad_norm": 8.860605239868164,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.6023,
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": 1294900081459200.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null