tuanna08go commited on
Commit
82a8e3b
·
verified ·
1 Parent(s): 59a7e7c

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 sha256:2cda9f1f5120389e25f34d4bead67255b2f0f66997979e23e4c929ed6c2eee02
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65932fa0f736bb86a99853117536a74b60ded3d59bd0e4cf9a244f36117fba77
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7337898e244a6fd6d9c42b28a6810c8c64f5822c5418ad7bd57a9daaf7da59a7
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f503a247dfe227ac5d0f77f5e178daec7793b68b28ed2333b7ffc0dfd26ccfaf
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65aa5c0b92d89456129ebd9520dd0ffb8ac2f18cbdc8beceb40b593a4a4bf305
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f097e45e4d5555c24ef9a3d1fad3bc5fe160ab0efdcf7ffb092ad49e28ce61cc
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": 0.013353591987844807,
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": 19.886,
61
  "eval_steps_per_second": 2.486,
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": 1.029889327104e+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": 0.017119989728006164,
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": 19.886,
61
  "eval_steps_per_second": 2.486,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.01369599178240493,
66
+ "grad_norm": 0.21196746826171875,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 0.0596,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.01369599178240493,
73
+ "eval_loss": 0.058330558240413666,
74
+ "eval_runtime": 992.6916,
75
+ "eval_samples_per_second": 19.821,
76
+ "eval_steps_per_second": 2.478,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.017119989728006164,
81
+ "grad_norm": 0.10265098512172699,
82
+ "learning_rate": 0.0,
83
+ "loss": 0.0563,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.017119989728006164,
88
+ "eval_loss": 0.057584770023822784,
89
+ "eval_runtime": 991.2861,
90
+ "eval_samples_per_second": 19.849,
91
+ "eval_steps_per_second": 2.482,
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": 1.3199061616164864e+17,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null