adammandic87 commited on
Commit
c853bc9
·
verified ·
1 Parent(s): 6cd741c

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:d9f669241c53eaa4fb2e42fe8f653ce32487f9d4e365c8a8d44e81375da2ef00
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fee8c5fced4dab1bd65ea1de724f9a5cf5294627cd4efd2e87849d35c048e32
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe8561ceff1699750581ddc2ca781f54a73fc8534017b8e87ccb774b0ccfc03d
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32605ffa2277c6a10ae26b936de9234e4ed79ade9011173d0e24186a0368fae1
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f88f964ad87577ca1e97998fb85b6f51001376ab9ef4339f8dfdda15c840d119
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871f3f67e05823016dc8caa40ed97d5df9a85df2277a4171af37ea6a888e3518
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": 0.00045725608245851356,
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": 33.896,
74
  "eval_steps_per_second": 16.951,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 596669695524864.0,
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": 0.0006858841236877703,
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": 33.896,
74
  "eval_steps_per_second": 16.951,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0005334654295349325,
79
+ "grad_norm": 4.542642116546631,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.9806,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0006096747766113513,
86
+ "grad_norm": 3.3268468379974365,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.7394,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006858841236877703,
93
+ "grad_norm": 2.629209518432617,
94
+ "learning_rate": 0.00018,
95
+ "loss": 8.0235,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006858841236877703,
100
+ "eval_loss": 1.5179685354232788,
101
+ "eval_runtime": 162.9814,
102
+ "eval_samples_per_second": 33.9,
103
+ "eval_steps_per_second": 16.953,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 872055708844032.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null