VERSIL91 commited on
Commit
9c749d4
·
verified ·
1 Parent(s): 9734423

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:bf21a9c292310a04dfc090cb76b0886dbdb3563d41b5214f7bce41d487d807d9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f022736d972b798893af80478125fa818b793bf58f346595186a49d70f1bc67e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:794afdcd5691070cea940c5d8f911d719f1594c0ffc9370ebabab6ee76076253
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3ad76c0312338ae490137c32466c10ff8e4f844e5df827e3204536e1e34a95
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
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": 0.0007973355703025722,
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": 41.426,
74
  "eval_steps_per_second": 20.713,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4438954195550208.0,
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": 0.0011960033554538584,
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": 41.426,
74
  "eval_steps_per_second": 20.713,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0009302248320196676,
79
+ "grad_norm": 4.912286281585693,
80
+ "learning_rate": 7e-05,
81
+ "loss": 1.568,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.001063114093736763,
86
+ "grad_norm": 4.547962188720703,
87
+ "learning_rate": 8e-05,
88
+ "loss": 1.2934,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0011960033554538584,
93
+ "grad_norm": 2.319340467453003,
94
+ "learning_rate": 9e-05,
95
+ "loss": 1.1418,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0011960033554538584,
100
+ "eval_loss": 1.0305676460266113,
101
+ "eval_runtime": 306.6854,
102
+ "eval_samples_per_second": 41.326,
103
+ "eval_steps_per_second": 20.663,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6658431293325312.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null