VERSIL91 commited on
Commit
a3cdb28
1 Parent(s): a055e2c

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:d15c69df656052a8042e2c9eafd81f0bf030b591791944af5128196dfb7b334d
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe53d1182f7b1305a438833b8f8065671c2cb01eddfa9582bbbf364e8b694742
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f57dae0e4c70c2557518e17bd4c470f1a407fabd157de98687fa5736061dbf27
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef5a4bf1abddc0440d1182ab2f147bb38b638bfc9db84639f2f94da6ccc216e
3
  size 41459700
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": 0.0005597243357646359,
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": 33.467,
74
  "eval_steps_per_second": 16.735,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 5968528457859072.0,
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": 0.0008395865036469539,
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": 33.467,
74
  "eval_steps_per_second": 16.735,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0006530117250587419,
79
+ "grad_norm": 3.2998745441436768,
80
+ "learning_rate": 7e-05,
81
+ "loss": 5.9918,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0007462991143528479,
86
+ "grad_norm": 3.2680015563964844,
87
+ "learning_rate": 8e-05,
88
+ "loss": 6.1079,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0008395865036469539,
93
+ "grad_norm": 4.798489570617676,
94
+ "learning_rate": 9e-05,
95
+ "loss": 5.3533,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0008395865036469539,
100
+ "eval_loss": 4.777524471282959,
101
+ "eval_runtime": 539.4964,
102
+ "eval_samples_per_second": 33.466,
103
+ "eval_steps_per_second": 16.734,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 9148839241973760.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null