daniel40 commited on
Commit
16bcfdf
·
verified ·
1 Parent(s): 1ccf3d6

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 sha256:4bb35316923cffdd6430e32a1aab2a40a8077beef0b9ad2514f2be533622a5e3
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fafdb241a1486e726d50e788f8badd306f4069713e80b149b815cdf656a6958
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9195ec733d540aa7a58dbdb3cad929cc316406e7c6d3628d88b280def1668785
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cbf58af552a0253385e4e18f24d2433414bd6de8d550968c8a25e9bfb7db54
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da2f3736139f86eb2e423375789bde32fa05e4661b3cd2bee766195f97ade183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72db1ca300703148b11f6c9ce555ec1a4f9c50722bf07f81b60e9a09bb963e32
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
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": 0.03346203346203346,
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": 57.806,
61
  "eval_steps_per_second": 28.962,
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": 1982385063198720.0,
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": 0.0429000429000429,
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": 57.806,
61
  "eval_steps_per_second": 28.962,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.03432003432003432,
66
+ "grad_norm": 2.279877185821533,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 2.6689,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0429000429000429,
73
+ "grad_norm": 2.2998838424682617,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.6421,
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": 2533047580753920.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null