Nexspear commited on
Commit
1db0547
·
verified ·
1 Parent(s): e87da0a

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:a68903b0479938ce67f6aac0f75f1a49ee7d04b91257953b48817dee63171347
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d076f90642c4653a4d5d2fff1a3d43d725dc92f8502a80c48c2da71cd77818
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:856a78b39b3a4c8d22049977b73ee8bebd79f4adb639638fd4d72dfc1bbc02a8
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385d05485e929a6c25aef9287332814c8b517524358bc89393fb36a1e0f3b049
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9b614e76ea213bd606a3fa03078615ee2354596b18cb2b0f1976286da0079ee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a463d5feac318c09783e529b68d2719872f249d90beddb2b474a4acc955e8e79
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": 0.17560975609756097,
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": 35.566,
74
  "eval_steps_per_second": 4.523,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 6004412094873600.0,
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": 0.2634146341463415,
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": 35.566,
74
  "eval_steps_per_second": 4.523,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.2048780487804878,
79
+ "grad_norm": 0.3672405481338501,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 3.1769,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.23414634146341465,
86
+ "grad_norm": 0.3140566647052765,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 2.8991,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.2634146341463415,
93
+ "grad_norm": 0.23150236904621124,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 2.7151,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.2634146341463415,
100
+ "eval_loss": 3.1205644607543945,
101
+ "eval_runtime": 4.8858,
102
+ "eval_samples_per_second": 35.409,
103
+ "eval_steps_per_second": 4.503,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 9126706384207872.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null