adammandic87 commited on
Commit
526e441
·
verified ·
1 Parent(s): f3ecada

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 sha256:2e6d7a99ffb8d50be36e8c91323327ffb3bc4da2fc6fddc055413af2d2c734e0
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f30e84edb5b48e5b1148e667840944d0a82c8be9c7c61a8c9fd243dd4d67b73
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0c0598d0cd1c6fa9c6273b1d4246076aa26e2fac4e442940c983b2d9a9b629d
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e839fd8a0c0887b941caa2afd4820eab5b8dc8375a2f82132c3f83e4dc0117
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e45466b2402edf839cb626cb699c4790782548a29dbd01cb24e18c7a1e498d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02cbecb1241da1dcf720ca1cdcbc95d2d83980810133627d4fd945fcf4ef3576
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": 0.00010109306880646995,
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": 49.377,
74
  "eval_steps_per_second": 24.689,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 235493287526400.0,
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": 0.00015163960320970494,
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": 49.377,
74
  "eval_steps_per_second": 24.689,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00011794191360754829,
79
+ "grad_norm": 0.4844641089439392,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6189,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00013479075840862662,
86
+ "grad_norm": 0.5195013284683228,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7658,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00015163960320970494,
93
+ "grad_norm": 0.5042082071304321,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.4831,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00015163960320970494,
100
+ "eval_loss": 1.7677805423736572,
101
+ "eval_runtime": 504.9623,
102
+ "eval_samples_per_second": 49.489,
103
+ "eval_steps_per_second": 24.744,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 357949797040128.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null