nat-hunt commited on
Commit
f258b95
·
verified ·
1 Parent(s): d4904ba

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:a547f6d82b9914a2070fa15f316a33b77ebad499db8f75f95886bc941ffb2362
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f65eb43a0b1ea0c2a27cff59ecb9d2f37e93b0748ea436193c219f7a922cf7
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73b58a3570a03b11a453808ed280da21f3df57ef7cc0c1636c7a265987ed6e3d
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84566f88637918dec770a228cd1f1be29123804c2c51c45c3cead469522f1ca
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d05d926a13e2b0db86e596e2ee777dcc8276585d379e27b6ca55897b2ce7fe
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": 0.006012024048096192,
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": 10.995,
74
  "eval_steps_per_second": 5.511,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3799469166428160.0,
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": 0.009018036072144289,
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": 10.995,
74
  "eval_steps_per_second": 5.511,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0070140280561122245,
79
+ "grad_norm": 0.6545887589454651,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.4233,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.008016032064128256,
86
+ "grad_norm": 0.740976870059967,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.9087,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.009018036072144289,
93
+ "grad_norm": 1.0389176607131958,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.6896,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.009018036072144289,
100
+ "eval_loss": 1.3327574729919434,
101
+ "eval_runtime": 38.2711,
102
+ "eval_samples_per_second": 11.0,
103
+ "eval_steps_per_second": 5.513,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5699203749642240.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null