Best000 commited on
Commit
df0d9be
·
verified ·
1 Parent(s): ad14012

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 sha256:8df6b9e419e43ff5e1486102d9b21378e4c77a400525138ea18776fd8676cea2
3
  size 327040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b66b111a0b1abfa1c70d2742dbbce83d9963b0bb5024a02f015bb9f528012e
3
  size 327040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39eaa641ec0dd9d0d7ee85ed7357cb3b7a9fda6684164880dce1101ee0fe501a
3
  size 739258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658a21e87b472274b51128294045aa60ac45ea31d180172e261a19b4b2d650ac
3
  size 739258
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
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": 0.008605234851201148,
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": 72.706,
74
  "eval_steps_per_second": 36.353,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1470582226944.0,
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": 0.012907852276801721,
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": 72.706,
74
  "eval_steps_per_second": 36.353,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.010039440659734672,
79
+ "grad_norm": 0.1335136592388153,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.9258,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.011473646468268197,
86
+ "grad_norm": 0.11691147834062576,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.9326,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.012907852276801721,
93
+ "grad_norm": 0.16463994979858398,
94
+ "learning_rate": 0.00018,
95
+ "loss": 11.9372,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.012907852276801721,
100
+ "eval_loss": 11.944936752319336,
101
+ "eval_runtime": 3.9428,
102
+ "eval_samples_per_second": 74.567,
103
+ "eval_steps_per_second": 37.283,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2221517832192.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null