JacksonBrune commited on
Commit
c187bc4
·
verified ·
1 Parent(s): 5783985

Training in progress, step 50, 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:f542c798903bb90d8832b08ec3ad86ea6114e32121adb98e581c21a60db5d6a3
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b049f83d5fac6cb399a0e7b6782b28ac055d84b2444654d1b72f42fa9e378b5
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:527a96f9506e323cb1c72dde7d05b8204cfbc1953ac9ebb883a3933e2d32436c
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3352633c3e903fe4e5dfb1c3131959f708ec9166fb9987ead5561d4eaf583b33
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e8c059d2b21d8c06ed6e950bd954f79aab3e5bef600b979a0c76c28d552e078
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c517c0990eb87a714937cb546365d0a8a53a36ba53d26da819b16dc52fccc8b3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.02222538823194187,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 47.375,
61
  "eval_steps_per_second": 23.72,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1791747878289408.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.028494087476848555,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 47.375,
61
  "eval_steps_per_second": 23.72,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.022795269981478843,
66
+ "grad_norm": 0.15403081476688385,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.0953,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.028494087476848555,
73
+ "grad_norm": 0.3279174864292145,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.1058,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 2261980353134592.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null