JacksonBrune commited on
Commit
9354f6a
·
verified ·
1 Parent(s): 3fafed2

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 sha256:65fdeeb997565e02fe879339b579d22ad41432ec208d5ffad0c87266a7d7e59a
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f68ee1040528611f65bb2c02d13458e13111499e9f904f623b313f6bc281950
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ee8e438250bf64cb654a2767c8e6e16b1d445564ae1e40152c9f8cf673428d1
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab6bdf38046bfd82af94294d94de42aba72166bf53454e1f48e97c367fc068e
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": 34.218,
74
  "eval_steps_per_second": 17.112,
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": 34.218,
74
  "eval_steps_per_second": 17.112,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0005334654295349325,
79
+ "grad_norm": 4.507593631744385,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.9796,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0006096747766113513,
86
+ "grad_norm": 3.349161148071289,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.7286,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006858841236877703,
93
+ "grad_norm": 2.6401185989379883,
94
+ "learning_rate": 0.00018,
95
+ "loss": 8.0305,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006858841236877703,
100
+ "eval_loss": 1.5174860954284668,
101
+ "eval_runtime": 161.4623,
102
+ "eval_samples_per_second": 34.219,
103
+ "eval_steps_per_second": 17.112,
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