kostiantynk1205 commited on
Commit
9844abe
·
verified ·
1 Parent(s): ca091f7

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 sha256:94d00346d3a197412a3ff051533b9259c555c7a4092888dc816ecc2ecef71fe9
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89d30a7d380dc400f687eef809077f33636c6a368f3c019d199bbe0a13f0122
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02f4a92f6fc5f86c27d9937be0454d6d16622f058dfd1dfb8c4cb10be7f9daa4
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb52382192d5a3812a1bd8b9ae5981c94fb31cd73f6cecbe6089c7e49784d68a
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70afda1cbfc0e8bb209365463c9845e7e0bb3405bef03c4f98bf21a7ac3cb2d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98928e1126863039d68d24c31d1f4b445df92b7d2d85fd2e0a5ab706a5eed5d3
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": 0.001217646507852259,
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": 20.72,
61
  "eval_steps_per_second": 10.36,
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": 1.058676538343424e+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": 0.001561085266477255,
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": 20.72,
61
  "eval_steps_per_second": 10.36,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.001248868213181804,
66
+ "grad_norm": 1.9232873916625977,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 2.9176,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.001561085266477255,
73
+ "grad_norm": 1.8639222383499146,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.3282,
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": 1.3477766699679744e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null