robiual-awal commited on
Commit
8a61e6e
·
verified ·
1 Parent(s): 13a1ef8

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 sha256:8752d9152bc3805979f91cac1858c0ef97cf60c042113bb02e29a7770e0bd2c7
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cc8260d1228e5890e864858d510713e5d3e7ddfba88912a710f4e494612a4e
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29bf5e986d49824eb8b9a3288e2c2f77c8c59f7f4d880efa327579a5b78b524d
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4169835a61be0ed9c4f0c37c039dd76fc94ef7434b3c70ffad4588d1f473f8
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c17c52bd8ef844b04cd44e7f1ec97aa686b196d5b59be84905cabc36870028c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52aa87102828bf8cab533c138f772c48c494ebc2b940fefe592ecc57aeb95a28
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": 0.0004107608818720164,
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": 15.136,
61
  "eval_steps_per_second": 7.568,
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": 1.519787666571264e+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": 0.0005266165152205338,
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": 15.136,
61
  "eval_steps_per_second": 7.568,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0004212932121764271,
66
+ "grad_norm": 1.2472842931747437,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 5.9418,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0005266165152205338,
73
+ "grad_norm": 1.7747693061828613,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.1515,
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": 1.963059069321216e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null