great0001 commited on
Commit
3c30461
·
verified ·
1 Parent(s): c84025e

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:deea8f1e783b773626984886ab029c610e4784a6ec84b96b790561fa610d868d
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191ae54d36d9ce8a5f940ddd3c309e0b725f42565aeffff8e5d7b1a34724fb9a
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd09ef20115ccdfeb57c443c2471cdad3bf98261f28f4cb6e7ff1a5a6cb336cb
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080e1f407236a53757482cbdd12ee27ced770ee5927ab2653200ef6bb9d152d7
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d5c51856a73f7bc59089afabbf3e78ff64adb1c34833e96c5b147cbb8666adf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b17ea9222f849df45fb42b477e3d57caefe1e563a3e7a364cbecb2349a17614
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": 0.0027649769585253456,
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": 18.096,
74
  "eval_steps_per_second": 9.048,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1848159869337600.0,
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": 0.004147465437788019,
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": 18.096,
74
  "eval_steps_per_second": 9.048,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0032258064516129032,
79
+ "grad_norm": 1.1867609024047852,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6008,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.003686635944700461,
86
+ "grad_norm": 1.3795751333236694,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7295,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004147465437788019,
93
+ "grad_norm": 1.678766131401062,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.6363,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004147465437788019,
100
+ "eval_loss": 1.4757215976715088,
101
+ "eval_runtime": 50.3951,
102
+ "eval_samples_per_second": 18.137,
103
+ "eval_steps_per_second": 9.068,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2745837520158720.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null