brixeus commited on
Commit
74435e0
·
verified ·
1 Parent(s): c0ed14b

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ecffbb8582f34920a781cbd116b729624941349ab39f8451804e485c756ec0e
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29791a025ced8d299076a79346377bd78aed9f80b92c62bc9f6fbd9253cf2852
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25e6513eee0c8c44dc57d46eb9a823122f5e73d0a3ee2e30b1223701bb4fae14
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d403de80d714eb7e810a40b639c6f9fecc4dff7279304deda2241c8dc2573da3
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e8641384676c0c3ca843dcc47e3f6d9bd5a859182c78c26888d7b28bf27a1bf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926c539986362599115d4154ffc69906160c0ab960c9d9ae1b2884107080e0e2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.00984009840098401,
5
  "eval_steps": 9,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 7.22,
74
  "eval_steps_per_second": 0.905,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4.693768229879808e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.014760147601476014,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 7.22,
74
  "eval_steps_per_second": 0.905,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.011480114801148012,
79
+ "grad_norm": 0.23769880831241608,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 0.7161,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.013120131201312012,
86
+ "grad_norm": 0.323109894990921,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 0.7092,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.014760147601476014,
93
+ "grad_norm": 0.2681789696216583,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 0.5955,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.014760147601476014,
100
+ "eval_loss": 0.6832801699638367,
101
+ "eval_runtime": 426.9229,
102
+ "eval_samples_per_second": 7.217,
103
+ "eval_steps_per_second": 0.904,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 7.073707050663936e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null