lesso01 commited on
Commit
dae73d9
·
verified ·
1 Parent(s): ba54ea4

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 sha256:4dcb5a8425529190f218572317dcab771f74f976f053a33bc71aca0e2946c5b5
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c0f65bde8c07d26d1535a0b941d0562d65fe4e28d8315b166b8ca0b71cd025
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0931811f456074fdea1af0f0b742b3acb54b9d1d29b3240aa140cc260e35a553
3
  size 847674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:addbf1c42cebe519872628fbe1a7fb82eebbb83f5ad647ca516ac8b81558f2fc
3
  size 847674
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f89ee07fe03d1a05ba9f35a1ae7e0f887e7de2494b1948e33f324c76bd30d853
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a5a857ed41b50df491280680008400b63a0cea9bbaf95bf767f775a18248db
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": 0.00029682765444313895,
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": 177.65,
74
  "eval_steps_per_second": 88.835,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 393351266304.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0004452414816647084,
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": 177.65,
74
  "eval_steps_per_second": 88.835,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0003462989301836621,
79
+ "grad_norm": 6.363209247589111,
80
+ "learning_rate": 0.00014,
81
+ "loss": 9.1041,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003957702059241853,
86
+ "grad_norm": 7.665739059448242,
87
+ "learning_rate": 0.00016,
88
+ "loss": 9.2728,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0004452414816647084,
93
+ "grad_norm": 7.9968414306640625,
94
+ "learning_rate": 0.00018,
95
+ "loss": 9.0876,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0004452414816647084,
100
+ "eval_loss": 8.97900104522705,
101
+ "eval_runtime": 47.6991,
102
+ "eval_samples_per_second": 178.431,
103
+ "eval_steps_per_second": 89.226,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 590026899456.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null