kk-aivio commited on
Commit
37c14d0
·
verified ·
1 Parent(s): 605741a

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:ed867fe682a35665d9cd6bd40bf9332f9d8f70f903761f1e4f0e31633bcb480f
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28c3769d952a080f7d79b5bc5cd7e3f246a262a96874e9ac0163cd91ff34667
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7560292d3777baa584fe0425bd64ed3bff3f81ad2752b43361255ee6af613f00
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b95534f26d17f6ef1c42c5dc9318b52996f3159b0b3f61f474a25603012e7e
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b15136f5d879e4ff194d1576a3a9b5574ef7137f2137749ff8ef2fca741d6220
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b2104cac213e0d4ed7e45b077b91787aea0d9685672f8b88dc986bc44c1185
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": 0.00011184587638234512,
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": 28.9,
74
  "eval_steps_per_second": 14.45,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 475092464173056.0,
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": 0.00016776881457351768,
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": 28.9,
74
  "eval_steps_per_second": 14.45,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00013048685577940266,
79
+ "grad_norm": 0.8296093940734863,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.2445,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00014912783517646017,
86
+ "grad_norm": 0.748724102973938,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.1062,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00016776881457351768,
93
+ "grad_norm": 0.8164461255073547,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.1827,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00016776881457351768,
100
+ "eval_loss": 2.2403993606567383,
101
+ "eval_runtime": 781.9116,
102
+ "eval_samples_per_second": 28.888,
103
+ "eval_steps_per_second": 14.444,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 737643562795008.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null