jssky commited on
Commit
2ef6291
·
verified ·
1 Parent(s): 035a695

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8637d98b9e8f2383f1d8e7d249eb7d420976d90f9bc2f6ecaa78ffbbc3f5b73f
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e59777a7cfe1559f0102ac38de438f53c8906418bb638c69622963006726246
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42bfb32aeec4c8449802c213c5c94f8330903d85114eded22c94a2b4706e6403
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef36988a855c6f9724204fe3d2ed86883b08121f4790e72a65832823a9a3f09a
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.00022702334556736918,
5
  "eval_steps": 3,
6
- "global_step": 6,
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": 2.4,
74
  "eval_steps_per_second": 2.4,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4218776992088064.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00034053501835105374,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 2.4,
74
  "eval_steps_per_second": 2.4,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00026486056982859735,
79
+ "grad_norm": 4.4711103439331055,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.3662,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00030269779408982557,
86
+ "grad_norm": 3.5810935497283936,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.9538,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00034053501835105374,
93
+ "grad_norm": 3.5936524868011475,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.434,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00034053501835105374,
100
+ "eval_loss": 0.6861280202865601,
101
+ "eval_runtime": 2598.99,
102
+ "eval_samples_per_second": 2.141,
103
+ "eval_steps_per_second": 2.141,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6328165488132096.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null