auxyus commited on
Commit
7506e3c
·
verified ·
1 Parent(s): 5219b34

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:b82d984d7fd25d8600e1e50b767e1c8478b7d318de5fcc17f0afbebee0ee7b6a
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f18c08f0653b6251959d2184bbd8b3e9cc50c3fcdb458ecf29239ddd27579c
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1dbb4902484c101346f2589997409531c23e3462cd45071513218bd8dd76984
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f49775c121a9c46537ac77247db2f9f039282ffb38986db55a2a31df4b67402
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:abd5e2ef111422d96f5dcdd7879c0a0bac563960736e5a17c4ad2052531c82be
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.01273209549071618,
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": 7.522,
74
  "eval_steps_per_second": 0.941,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4.680537529437389e+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": 0.01909814323607427,
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": 7.522,
74
  "eval_steps_per_second": 0.941,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.014854111405835544,
79
+ "grad_norm": 0.46977323293685913,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 0.3508,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.016976127320954906,
86
+ "grad_norm": 0.33589252829551697,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 0.3184,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.01909814323607427,
93
+ "grad_norm": 0.31081634759902954,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 0.3063,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.01909814323607427,
100
+ "eval_loss": 0.288199245929718,
101
+ "eval_runtime": 316.9259,
102
+ "eval_samples_per_second": 7.513,
103
+ "eval_steps_per_second": 0.94,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6.987844762258637e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null