tuanna08go commited on
Commit
f5b3daf
·
verified ·
1 Parent(s): 6c69e06

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:b4f41a8a07730aa86d35650ecc0b48fcbdcdf924fee8814ae0069c3dafa7c54c
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d48c778c36c572f41f58cea18e1dfef9df39062f0424b9598d079e62b8924d2
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4f71baa216eb514be883774b91f9e16b26df71ad0b5b0a517ca2401099d855
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6643566f7a06cc8e128aad4fe1083e4cc24f9a43fdf6d2e1524e0c66e9d020
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75d4ec2316e6378a5eff98df663b9ae7cfb4eb449454873234e07815bdcd6ca8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed83ae277942571648c3be90a9bb9a69ce40097aaed95a14cbf28423e425874
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.023682113173175454,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,36 @@
60
  "eval_samples_per_second": 20.037,
61
  "eval_steps_per_second": 2.505,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +104,12 @@
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": 1.030263969719255e+17,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.030361683555353146,
5
  "eval_steps": 10,
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": 20.037,
61
  "eval_steps_per_second": 2.505,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.024289346844282515,
66
+ "grad_norm": 0.4046275317668915,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 0.9362,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.024289346844282515,
73
+ "eval_loss": 0.9117223620414734,
74
+ "eval_runtime": 552.2012,
75
+ "eval_samples_per_second": 20.092,
76
+ "eval_steps_per_second": 2.512,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.030361683555353146,
81
+ "grad_norm": 0.37605157494544983,
82
+ "learning_rate": 0.0,
83
+ "loss": 0.9095,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.030361683555353146,
88
+ "eval_loss": 0.9005217552185059,
89
+ "eval_runtime": 552.7944,
90
+ "eval_samples_per_second": 20.071,
91
+ "eval_steps_per_second": 2.509,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 1.321104037726126e+17,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null