shibajustfor commited on
Commit
673db40
·
verified ·
1 Parent(s): 97f2320

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 sha256:7db0c78b515d03ce7747d3f413b8b602ea499250b54972ee27826bcad6cbf5d3
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593cd1ed846f24dad729d487ad8493b2f721069b8f8844f0cf6deffba9a7bf71
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d91a3af138e8b42ec3a5825b756356312204754660e598d2f0d1650425089ac
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa341073c06cf3d6901c13e28f64dd8b9f647ea999bc6d47d7b60704be3d60f1
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bf85c58cca5aae7d759797e66cb053a57988fcfe19dedb65a2573f97c517485
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5680ac895463613d91eeb9054dc06bc19db700daeaf5c42ff7984ab49692a6
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": 0.012313521193464362,
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": 18.22,
61
  "eval_steps_per_second": 9.11,
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": 1.242743039852544e+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": 0.015786565632646618,
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": 18.22,
61
  "eval_steps_per_second": 9.11,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.012629252506117294,
66
+ "grad_norm": 2.400541305541992,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 4.1369,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.015786565632646618,
73
+ "grad_norm": 2.254683494567871,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.8398,
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": 1.591027713441792e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null