Best000 commited on
Commit
d18814c
·
verified ·
1 Parent(s): 50b892e

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 sha256:0d6b8fab42bc853a461760d7325db5b04f1804e6cecb81b29166857645de5165
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55c0c45cf896e4dcd8989e4cf82302f0b35cfadf4058f46efd78340bff5c255
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:116497bbd470b7f703dbaaa6fb28327851eb9a7df7b29bc70f3fc3a6ea0b4728
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb1f05cdda60058b2b3378b55492ff47b561d52cbc7994e8b5da9fb1a12966d
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
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": 0.20168067226890757,
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": 62.906,
74
  "eval_steps_per_second": 33.872,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 52637139468288.0,
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": 0.3025210084033613,
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": 62.906,
74
  "eval_steps_per_second": 33.872,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.23529411764705882,
79
+ "grad_norm": 23.43442153930664,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.9591,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.2689075630252101,
86
+ "grad_norm": 19.78339195251465,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.6446,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.3025210084033613,
93
+ "grad_norm": 21.895431518554688,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.0876,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.3025210084033613,
100
+ "eval_loss": 0.5609821081161499,
101
+ "eval_runtime": 0.2125,
102
+ "eval_samples_per_second": 61.172,
103
+ "eval_steps_per_second": 32.939,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 78955709202432.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null