tensor24 commited on
Commit
62a342a
1 Parent(s): 08b6893

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:e11f73b9843d6d2dc8001383fe8163a77cee93fd1bd2da34d90ac78d5af99819
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ec54c60773a764d5465f9fea421e4da459e8c8c2d9948f7544e21229cbf924
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28215c46caf65eeee8df1df83266c4c9fcea6c2b979e2ad4da5d50c84bec6ee7
3
  size 25986148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3225c651180dc4c9b22485a13d425d3caaa78282678d622863b642c8e9b85a3
3
  size 25986148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e3316d2cf3807eae9dbf9a639db4bf3b211c11598d00a94e92fb77034b1be1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23d8c54930bcfa400a42faf2dd8310c9fa2fc3255471da30515ca920d46e8eb
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": 0.000387409200968523,
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": 6.454,
74
  "eval_steps_per_second": 3.227,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1235242526441472.0,
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": 0.0005811138014527845,
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": 6.454,
74
  "eval_steps_per_second": 3.227,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0004519774011299435,
79
+ "grad_norm": Infinity,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.5575,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.000516545601291364,
86
+ "grad_norm": Infinity,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.3466,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0005811138014527845,
93
+ "grad_norm": 1.7445339669456749e+19,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.9283,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0005811138014527845,
100
+ "eval_loss": 2.8495190143585205,
101
+ "eval_runtime": 1013.3024,
102
+ "eval_samples_per_second": 6.436,
103
+ "eval_steps_per_second": 3.218,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1852863789662208.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null