nathanialhunt commited on
Commit
3c8946e
·
verified ·
1 Parent(s): 5a2ee04

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:f96eb5d5cedd40354462127d376991bcf09e7965ceafe680577e5131d247a0db
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b48600bb723c435162209715a1653a0648d697bbb166ecf65a489a2ce62081
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:445bcb1c076bc6fa4a47c5e19425e65ab06cb23a1c9a43bc5f2cbe949dbcac33
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0be16bdf71475747a224b67ba5d619f02933af0298b651c09234eb55613f894
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e465eb0265e76c1c3121bcc183ba1f1604238c641718592811ee2b5b90c7fa47
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": 0.00021894214453830574,
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": 15.228,
74
  "eval_steps_per_second": 7.614,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1267309624688640.0,
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": 0.00032841321680745865,
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": 15.228,
74
  "eval_steps_per_second": 7.614,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002554325019613567,
79
+ "grad_norm": 1.9005385637283325,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9594,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00029192285938440767,
86
+ "grad_norm": 1.6968870162963867,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7966,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00032841321680745865,
93
+ "grad_norm": 0.9660829901695251,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7219,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00032841321680745865,
100
+ "eval_loss": 1.6114068031311035,
101
+ "eval_runtime": 751.3421,
102
+ "eval_samples_per_second": 15.358,
103
+ "eval_steps_per_second": 7.68,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1953769004728320.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null