tensor24 commited on
Commit
3597c0e
·
verified ·
1 Parent(s): c094d3c

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 sha256:27f774f184c8184fa3623bf32dfec2c943f975ea15e8ef31323df32716261743
3
  size 100697728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceea2947f2011935e2309ec0412e7fddb9ffd58d44e708442cabca335b0608cc
3
  size 100697728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1faca3e00d5dc62a81114ff201b4f127b10271954f6c4c22635066f7458884d
3
  size 51418196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a760c325711fbeda9babc47e99e674fc98eead4c04623cdd7932500d11de05b
3
  size 51418196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c357bfafab62ab14f0d4c4d9570ed28194b02613077cfb4fb793b2cb8e259cc2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e994a115df52a991dd7a9d53157f302db87da7ae8692af36a0bc6445e90cb1
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": 0.004378762999452655,
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": 3.247,
74
  "eval_steps_per_second": 1.626,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4421019620081664.0,
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": 0.006568144499178982,
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": 3.247,
74
  "eval_steps_per_second": 1.626,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.005108556832694764,
79
+ "grad_norm": 32.43141174316406,
80
+ "learning_rate": 0.00014,
81
+ "loss": 33.8516,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0058383506659368724,
86
+ "grad_norm": 41.67256546020508,
87
+ "learning_rate": 0.00016,
88
+ "loss": 30.5001,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006568144499178982,
93
+ "grad_norm": 44.105892181396484,
94
+ "learning_rate": 0.00018,
95
+ "loss": 22.1419,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006568144499178982,
100
+ "eval_loss": 4.630993843078613,
101
+ "eval_runtime": 177.6493,
102
+ "eval_samples_per_second": 3.248,
103
+ "eval_steps_per_second": 1.627,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6631529430122496.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null