mamung commited on
Commit
3690522
·
verified ·
1 Parent(s): c7ec7d9

Training in progress, step 27, 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:ca0db966ae65eb1b520e8f3ae3d456f9d4e91465f627cd1c82756b33b1b419f1
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee6d9d0b5a8afcedb89539ad37cd488a112dd096dc8ec8a1408dc33257e0ffb
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36dade300cc644e90cbf7ee1611e18edf52418503670d90c67cd8931c193f11d
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de6466228a4c823355a5571fc6096d3547d5e26e72afa5a7c8b15b678b07de2
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c7e8c0f7bb988751ccd9907b573ddb354edc6c4d1478341caae7f6c4a40c442
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4d249624bc8de793916f023beebfa62202a9083f1d5be34ff57cd42f702095
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
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": 0.002522841350070517,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 8.986,
74
  "eval_steps_per_second": 4.493,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1.0742550511170355e+17,
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": 0.0037842620251057756,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 8.986,
74
  "eval_steps_per_second": 4.493,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.002943314908415603,
79
+ "grad_norm": 1.5759952068328857,
80
+ "learning_rate": 0.0001999229036240723,
81
+ "loss": 1.4326,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.003363788466760689,
86
+ "grad_norm": 1.0148948431015015,
87
+ "learning_rate": 0.00019876883405951377,
88
+ "loss": 1.5209,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.0037842620251057756,
93
+ "grad_norm": 1.0281277894973755,
94
+ "learning_rate": 0.00019624552364536473,
95
+ "loss": 1.3521,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.0037842620251057756,
100
+ "eval_loss": 1.3808079957962036,
101
+ "eval_runtime": 2674.464,
102
+ "eval_samples_per_second": 8.986,
103
+ "eval_steps_per_second": 4.493,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1.6113825766755533e+17,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null