trenden commited on
Commit
33ca0f0
·
verified ·
1 Parent(s): 2a2b50e

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 sha256:66f989918e8e0b6096baccd096c01465d332b856890928ded20303b7628d5bf1
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24466fd2926d53a5f0dfa602e43541182302f7b70ee9f787ef9cdc5f9f93c7f
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d384874b8b7e146a78d52714a10b002ae7cb5969307d3a4d2c6d2a26f68b17
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439d4ab65c4a2581ccbcf03e7f95218c37fe5f15a584bc30dde29330fbed38b1
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:b08313bc423e4e749b1be6f1d16ebae8bf798fe463157da525e99306fd0b9592
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ce404e87fcfa8b39c59ce102013231e7cdc3750402766ab47e6fc98888814f
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": 0.14457831325301204,
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": 32.386,
74
  "eval_steps_per_second": 16.193,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 550772026638336.0,
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": 0.21686746987951808,
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": 32.386,
74
  "eval_steps_per_second": 16.193,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.1686746987951807,
79
+ "grad_norm": 3.184393882751465,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.6275,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.1927710843373494,
86
+ "grad_norm": 3.618189573287964,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.3245,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.21686746987951808,
93
+ "grad_norm": 3.3444736003875732,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.5488,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.21686746987951808,
100
+ "eval_loss": 1.3555703163146973,
101
+ "eval_runtime": 0.5451,
102
+ "eval_samples_per_second": 33.024,
103
+ "eval_steps_per_second": 16.512,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 826158039957504.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null