kostiantynk commited on
Commit
ff979a2
·
verified ·
1 Parent(s): c36456b

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 sha256:54722a74ea64bbfeac0b0838c511129565367b648603f547c401522dba1b24e9
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd27dc748edc757810bc5060578363b3540be9025283e02593a072aa046c284a
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c230aa914d3ceca0a8001fded80b5ccac90d739fcf4bcb7fe5049b9102553a7e
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d387ccd8d2a0f3fdbca0817cf85b2ae3b8c30a0415dd7b82fa3e4bbe81cd77bb
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a14a16007d1242716f4ca0ef3e774a2a2fb5bb35e61cd0b0a58afdd92059628
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf714fe91136fdfdfeaf594809718c37a9cba1de5dfc5056f77452c5d121cc4
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": 0.0020577760189948555,
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": 20.684,
61
  "eval_steps_per_second": 10.342,
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": 5023509453471744.0,
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": 0.002638174383326738,
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": 20.684,
61
  "eval_steps_per_second": 10.342,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.00211053950666139,
66
+ "grad_norm": 0.6791512966156006,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.0986,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.002638174383326738,
73
+ "grad_norm": 0.6163003444671631,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.0075,
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": 6534646443540480.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null