lesso01 commited on
Commit
057fa5c
1 Parent(s): b5a9184

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 sha256:91e7428d0087f5d49503759871fa5943a4baaf4d36e6f4d393900773f1306171
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec22674347964778e11c35e364acd86f3ae81232bef3d8373662659dc865bf9b
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d89dd02bd79f345bc7031d1aa5d72ab9c9e1abb6ed8310e30a63177d7d135332
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b73706219fc742e97b26cc61b2c10e8809f151905074103419e0c62b32fb836
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
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": 0.0022279985146676567,
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": 30.258,
74
  "eval_steps_per_second": 15.129,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 977249545224192.0,
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": 0.0033419977720014855,
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": 30.258,
74
  "eval_steps_per_second": 15.129,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0025993316004456,
79
+ "grad_norm": 1.7376594543457031,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6128,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0029706646862235424,
86
+ "grad_norm": 1.4749916791915894,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.1024,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0033419977720014855,
93
+ "grad_norm": 1.9655250310897827,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2391,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0033419977720014855,
100
+ "eval_loss": 0.22511792182922363,
101
+ "eval_runtime": 37.5364,
102
+ "eval_samples_per_second": 30.211,
103
+ "eval_steps_per_second": 15.105,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1465874317836288.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null