kostiantynk-out commited on
Commit
b5aeef0
·
verified ·
1 Parent(s): 8f89bfb

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 sha256:7757c3b4521d1ba12b92eca69109685060fec758ffb28a0fcd5db263e3e6db87
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72708ab60810ebf07c8aaef20c89937cb54ea032d2d192429d2bbe5a494e13ca
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf113f18c6f0f85613b36de1dc59f3150d1059de6752dc1a0e7794143cca5c62
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317d0969f298a46df8ec65204a63f2b2a86e55095937f7ce63f95ab3eb97ac6a
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:b3df234e5aaf8c4946e213550320cfa641d06d78d6188e95560495eed9123ce4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08feb0b8dea6185f68f1482010f68eaf6c0392818bbf986a4c66ef478d1e367
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": 0.04192421392098898,
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": 29.401,
61
  "eval_steps_per_second": 14.701,
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": 6352122043957248.0,
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": 0.05374899220639613,
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": 29.401,
61
  "eval_steps_per_second": 14.701,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.042999193765116905,
66
+ "grad_norm": 3.074694871902466,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.9478,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.05374899220639613,
73
+ "grad_norm": 5.18685245513916,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.9982,
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": 8143746210201600.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null