trenden commited on
Commit
eb3b4e3
·
verified ·
1 Parent(s): 3d88603

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 sha256:59d5f2b78f85d99ffa4c166854a078d79355fc2e88d240e2f8be1df6a5d09c16
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f49cd3906fd147acd3466bbb6a6a964fc1c1ba8245c0ca525d1481af503147
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a88f60fe0ea6cc5d81f16db177e21458990cde5803a8184d93e73b17fa8257ec
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb9f5d6f4872a5dd23064c9a9e71edbca78a36f255c2d1530cf86b2a2888fa8
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3483100185f9bb64a1baea7d0678dd8819a763e19d4dc3947a4c495c2a757eec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54088f61daf67ba3987886527d2520040d63916cf72a674a3a58d1cc4e57624a
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": 0.00995850622406639,
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": 20.069,
74
  "eval_steps_per_second": 10.035,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1793300335951872.0,
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": 0.014937759336099586,
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": 20.069,
74
  "eval_steps_per_second": 10.035,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.011618257261410789,
79
+ "grad_norm": 0.3038789629936218,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.343,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.013278008298755186,
86
+ "grad_norm": 0.29985228180885315,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.2773,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.014937759336099586,
93
+ "grad_norm": 0.38474905490875244,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.3235,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.014937759336099586,
100
+ "eval_loss": 0.2738620340824127,
101
+ "eval_runtime": 12.7069,
102
+ "eval_samples_per_second": 19.989,
103
+ "eval_steps_per_second": 9.995,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2711820020219904.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null