ClarenceDan commited on
Commit
964e9d1
·
verified ·
1 Parent(s): 580f830

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 sha256:36266b168e6cfe639050fc6dcdc71f7e83546ecb2d6234e0f43e44231b722bbc
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e17ec0ce1db97b13f6f29bf895a87806fa4f0a94422779c9694dab62fe3cf5d
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a9cb8d7008ddf12a02a7473f50930dd37630c6a4b3c9c654a9830ff50dded0f
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf3d26dea06b4ef349b88333401ba92b0fd716bf7300a4d4e845d391d9ad0bda
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0732a4518c77e89f0b67b1a73557c53e87040e49f4fb885cf13aa6e0549b28a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163020c3a5e3deb0c9f202a04693b11d0b5de442bd4ef423bf0f0a2016603d4d
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": 0.0051557465091299675,
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": 20.019,
74
  "eval_steps_per_second": 10.009,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1710169792708608.0,
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": 0.007733619763694952,
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": 20.019,
74
  "eval_steps_per_second": 10.009,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006015037593984963,
79
+ "grad_norm": 0.30002692341804504,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.2206,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006874328678839957,
86
+ "grad_norm": 0.35041213035583496,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.3039,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.007733619763694952,
93
+ "grad_norm": 0.36330825090408325,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2723,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.007733619763694952,
100
+ "eval_loss": 1.3176864385604858,
101
+ "eval_runtime": 24.458,
102
+ "eval_samples_per_second": 20.034,
103
+ "eval_steps_per_second": 10.017,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2687409674256384.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null