nathanialhunt commited on
Commit
843a05b
·
verified ·
1 Parent(s): 0bc44dd

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:f21abc531c54a76a7f1820033de20e4f711ee822032e6c6c1f41794dfbe215ac
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dedf8a7b37ff6871a083cfe6733c2f4a28803d8bd6f0c682e71376d38902c86b
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1706db7971e253407a89049199253b80883fd56ca07aace28c048e1c4f47987a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61a011c6234fadce6a79fe76652ad74ccbf08f5b48858ae151e48601235ca61
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
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": 0.0032804811372334607,
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": 32.983,
74
  "eval_steps_per_second": 16.513,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109757876240384.0,
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": 0.004920721705850191,
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": 32.983,
74
  "eval_steps_per_second": 16.513,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0038272279934390375,
79
+ "grad_norm": 5.284390926361084,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.6106,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004373974849644614,
86
+ "grad_norm": 3.671947956085205,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.8108,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004920721705850191,
93
+ "grad_norm": 3.879005193710327,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.8781,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004920721705850191,
100
+ "eval_loss": 3.004443407058716,
101
+ "eval_runtime": 23.4201,
102
+ "eval_samples_per_second": 32.92,
103
+ "eval_steps_per_second": 16.482,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664636814360576.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null