SystemAdmin123 commited on
Commit
f351a9d
·
verified ·
1 Parent(s): 3f8a119

Training in progress, step 80, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07f20642645957edae2ce7c265e225e4b56cff6574adf38e81ae104351b0a523
3
  size 250490408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93dd86ff9c49f760a44ffb114f71868da216852fceb842d16f972a0466408fef
3
  size 250490408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb92f5e9d43c62bfc8384c770c60b8f905fc63e20919d6d54f8f08372119a898
3
  size 255265850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a01640571f9afbe7ca0e574211f839e88c711a2bbef5f651160659d39e5b8e
3
  size 255265850
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed64e0e27f410ed20158985bfa09c9103bc78ccd30e02605475adc9ee8711d22
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f762cf91540bcf7946b28532c1cf75c965f79b51d1fb88cba12058ec09b36cc8
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef152eb96e063e261cf4df880cb4e01fe8cf9df29ac68b58ffc75651778615d7
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb084d5318e7452dd167fa6706b2ed07ba51a72e3318c2203b535306ebccc99
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5258a10d326b43bb322f9f7412c08a5d462c4dd53d2018b15d95caea3824d34f
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": 5.0,
5
  "eval_steps": 40,
6
- "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -65,6 +65,28 @@
65
  "learning_rate": 0.00019863613034027224,
66
  "loss": 4.7735,
67
  "step": 60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 10,
@@ -84,7 +106,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 3885935078932480.0,
88
  "train_batch_size": 32,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 6.666666666666667,
5
  "eval_steps": 40,
6
+ "global_step": 80,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
65
  "learning_rate": 0.00019863613034027224,
66
  "loss": 4.7735,
67
  "step": 60
68
+ },
69
+ {
70
+ "epoch": 5.833333333333333,
71
+ "grad_norm": 4.59375,
72
+ "learning_rate": 0.00019757963826274357,
73
+ "loss": 4.6862,
74
+ "step": 70
75
+ },
76
+ {
77
+ "epoch": 6.666666666666667,
78
+ "grad_norm": 4.3125,
79
+ "learning_rate": 0.00019622680003092503,
80
+ "loss": 4.4865,
81
+ "step": 80
82
+ },
83
+ {
84
+ "epoch": 6.666666666666667,
85
+ "eval_loss": 3.095829725265503,
86
+ "eval_runtime": 10.2886,
87
+ "eval_samples_per_second": 145.89,
88
+ "eval_steps_per_second": 2.333,
89
+ "step": 80
90
  }
91
  ],
92
  "logging_steps": 10,
 
106
  "attributes": {}
107
  }
108
  },
109
+ "total_flos": 5198666264477696.0,
110
  "train_batch_size": 32,
111
  "trial_name": null,
112
  "trial_params": null