robiulawaldev commited on
Commit
9045e97
·
verified ·
1 Parent(s): 9cbb038

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:fa2ab53143a30f51c80d7761d59feac2e20eca0ae0b9b2b9528e9e59840eb935
3
  size 130583912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b796f0338f3a1f9351164e75805fd71514580eaa447004ca79fc2b65db6d5176
3
  size 130583912
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ddfb5e1737be553298fd1f7661b467e09fc0480c55fdaf2729acfd2a33fe2d
3
  size 66578772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7704dbf9b3ba6280fd6908f1f782809c8397cec0e6de4a0b643bf0797a121f1
3
  size 66578772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3cb51c865de749e1c981ae84c7a4541c12d5f3faba169695b5eaed850549ba2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd4b82ee0b29621eaa6123f17c5514ef4bd498e3b74eb2f61e7321c2fc0fa73
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
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": 0.001684410564277539,
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": 21.169,
61
  "eval_steps_per_second": 10.586,
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": 6300480557285376.0,
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": 0.0021595007234327425,
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": 21.169,
61
  "eval_steps_per_second": 10.586,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.001727600578746194,
66
+ "grad_norm": 1.7444703578948975,
67
+ "learning_rate": 0.0002,
68
+ "loss": 4.1676,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0021595007234327425,
73
+ "grad_norm": 1.4239596128463745,
74
+ "learning_rate": 0.0002,
75
+ "loss": 3.9287,
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": 8059705647955968.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null