nblinh63 commited on
Commit
1d2cf88
·
verified ·
1 Parent(s): f30527c

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:a7a83d396ad160e5e5a044d1ae3213fc66af111c83fa37b6938ff157d177e7a0
3
  size 30322120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f0e2d5872d4903fdd2a95629229c4d4a30143f7d4bab766c94f345f841f718
3
  size 30322120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16376afc1fddc46799352e11feea556e6952677516c7af585a46b72b988610a9
3
  size 15768084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b80dff48d49f6dfcab93cdd75e2d929b806eb1378ffda9cb85917ac6aceb6b
3
  size 15768084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d712c77120c67ed91988aaa635519cafd55c1a8cf6c5bd9894cf262d7fd97eb6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84a5cf2454179937316496e4212e2e56502a7858df2afe7855b38d36059da33
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": 0.0008721881019006433,
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": 2.216,
74
  "eval_steps_per_second": 1.109,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 372738871001088.0,
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": 0.0013082821528509648,
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": 2.216,
74
  "eval_steps_per_second": 1.109,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0010175527855507504,
79
+ "grad_norm": 6.6997294425964355,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.3049,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0011629174692008577,
86
+ "grad_norm": 16.76756477355957,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.7391,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013082821528509648,
93
+ "grad_norm": 9.461111068725586,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.1305,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013082821528509648,
100
+ "eval_loss": 2.8077025413513184,
101
+ "eval_runtime": 1305.1255,
102
+ "eval_samples_per_second": 2.22,
103
+ "eval_steps_per_second": 1.11,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 559108306501632.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null