Best000 commited on
Commit
33e0a6e
·
verified ·
1 Parent(s): 456fa4e

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 sha256:4a20c701da19dd85897596c11089ac3e89c2eee9e383cacfaf23e1a0bfbda933
3
  size 66103768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8134ea2a3eaa5cb8a90c61742125c2c2e16b8333660eceb4e0ac4bc87a9b3d4b
3
  size 66103768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddaf1fa0ccd194d9e43a22129be39d9bf61746e8f45dc55f236e1a00725fc086
3
  size 33939412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1da99327cd43626fd48e502e3477d741dae74d16bd42f85353a9f99068c0d9f
3
  size 33939412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0550373e8ab2cc5a61fc1c48c9e340c7375bbacfdfbd51c10d044332f8177330
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": 0.0051557465091299675,
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": 18.538,
74
  "eval_steps_per_second": 9.269,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1368370882646016.0,
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": 0.007733619763694952,
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": 18.538,
74
  "eval_steps_per_second": 9.269,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006015037593984963,
79
+ "grad_norm": 1.2088669538497925,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.0819,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006874328678839957,
86
+ "grad_norm": 1.3356318473815918,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.2304,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.007733619763694952,
93
+ "grad_norm": 1.5668182373046875,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.0227,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.007733619763694952,
100
+ "eval_loss": 0.9346973299980164,
101
+ "eval_runtime": 26.4204,
102
+ "eval_samples_per_second": 18.546,
103
+ "eval_steps_per_second": 9.273,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2088566084038656.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null