lesso commited on
Commit
5247761
·
verified ·
1 Parent(s): f5587e8

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:cd21c4cb7f0b1d7e59e8e84be9d26898adc050c0bc37dffdd8b496dfbf20ac0e
3
  size 871457448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12eef8a71b1aad6cbf63c4f8e2fcc2d0275303149bb1e308b5ed7ca5b8431c19
3
  size 871457448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6779481cc12c5a2877c3e9a0d29835b757306c39a7d8bf52d6144fa8346d6d51
3
  size 443280340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc3ff12ebb80d7c737bfea0e489434bb49c641e49bff36183da9c00da893381
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:f5316a70172d657b3da900291c1d26d5b488abfc5df7d3d2ad0bedc3db9123ea
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21391e35c09de08ac3b86b89e77a3bc7010d7fe77e83103079e0b4a52ba825d5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.339023232460022,
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": 8.474,
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": 1.339023232460022,
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": 8.474,
46
  "eval_steps_per_second": 0.265,
47
  "step": 100
48
+ },
49
+ {
50
+ "epoch": 0.00810307106393323,
51
+ "grad_norm": 1.2007815837860107,
52
+ "learning_rate": 0.000206,
53
+ "loss": 1.2725,
54
+ "step": 150
55
+ },
56
+ {
57
+ "epoch": 0.00810307106393323,
58
+ "eval_loss": 1.3696740865707397,
59
+ "eval_runtime": 1839.133,
60
+ "eval_samples_per_second": 8.476,
61
+ "eval_steps_per_second": 0.265,
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