lesso commited on
Commit
6851752
·
verified ·
1 Parent(s): ae2bf49

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:157721e82bf15671ad9675f39c52a69e6fc7cfe6e9015ac95cbb8b07f2b3bea3
3
  size 871457448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01abd88bea61466afacc2064bd943b194ccce1b809b929cf8b12087953416884
3
  size 871457448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:574432611cc8141a41e7ef0ebfb1dbc7dd2f5aeefff73915bd4bac718e7a525e
3
  size 443280340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4123f635592dbc7dcd7af93c89a8fd6b3042e4ed04132266169639dd76e9fce9
3
  size 443280340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8307217e06e1987ccd435274b9aac0d79f8d820155ca98c15e5e38f16a87c83f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ca51295357a6d600fd0c726212784b1970da6cf307dff1168b6e51a8a8255f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c690d6f2396e52ee620192e6153c703ba870cd541fd4dd25642b8aee51276dfa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf23606550b94276a6908d6c21e49c1f83625cfca51cf2aaf23007a5bba6f9ae
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.3310236930847168,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.005402047375955487,
5
  "eval_steps": 50,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 8.451,
46
  "eval_steps_per_second": 0.265,
47
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 50,
@@ -59,7 +74,7 @@
59
  "early_stopping_threshold": 0.0
60
  },
61
  "attributes": {
62
- "early_stopping_patience_counter": 0
63
  }
64
  },
65
  "TrainerControl": {
@@ -73,7 +88,7 @@
73
  "attributes": {}
74
  }
75
  },
76
- "total_flos": 8.63610951696384e+16,
77
  "train_batch_size": 4,
78
  "trial_name": null,
79
  "trial_params": null
 
1
  {
2
  "best_metric": 1.3310236930847168,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.00810307106393323,
5
  "eval_steps": 50,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 8.451,
46
  "eval_steps_per_second": 0.265,
47
  "step": 100
48
+ },
49
+ {
50
+ "epoch": 0.00810307106393323,
51
+ "grad_norm": 1.0529603958129883,
52
+ "learning_rate": 0.000201,
53
+ "loss": 1.2689,
54
+ "step": 150
55
+ },
56
+ {
57
+ "epoch": 0.00810307106393323,
58
+ "eval_loss": 1.3370928764343262,
59
+ "eval_runtime": 1845.2096,
60
+ "eval_samples_per_second": 8.448,
61
+ "eval_steps_per_second": 0.264,
62
+ "step": 150
63
  }
64
  ],
65
  "logging_steps": 50,
 
74
  "early_stopping_threshold": 0.0
75
  },
76
  "attributes": {
77
+ "early_stopping_patience_counter": 1
78
  }
79
  },
80
  "TrainerControl": {
 
88
  "attributes": {}
89
  }
90
  },
91
+ "total_flos": 1.295416427544576e+17,
92
  "train_batch_size": 4,
93
  "trial_name": null,
94
  "trial_params": null