nblinh63 commited on
Commit
65c856b
·
verified ·
1 Parent(s): 690450f

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 sha256:85ec2da4273051c575b27bc0e03421574e5b95872f1cf6e5f8cfdd65db2b9a77
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b34f85b7fdacbb73b13dd82169b72fbd6bd206bf9613c4d3e6006af65e53498
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe77937d17f666bcedb63ca2b56b2df75371283b4dc13ae27851d131b803cb92
3
  size 132798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6093149b03bc60da6834b81778fa9627be49c2fa83b27d98c83cd3b23635d3
3
  size 132798
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:059e301c18065b1c9a75f81e66def92b497540651351d8bc02434f165c0917ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab09cd63e6991a21a903bb7e435be9cb2e1639d45bb694e85a79f19ec18d10be
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": 0.014519056261343012,
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": 67.821,
74
  "eval_steps_per_second": 33.91,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 44920995840.0,
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": 0.021778584392014518,
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": 67.821,
74
  "eval_steps_per_second": 33.91,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.01693889897156685,
79
+ "grad_norm": 4.074832439422607,
80
+ "learning_rate": 0.00014,
81
+ "loss": 44.1527,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.019358741681790685,
86
+ "grad_norm": 3.816525936126709,
87
+ "learning_rate": 0.00016,
88
+ "loss": 44.3855,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.021778584392014518,
93
+ "grad_norm": 3.581460475921631,
94
+ "learning_rate": 0.00018,
95
+ "loss": 44.1724,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.021778584392014518,
100
+ "eval_loss": 11.039490699768066,
101
+ "eval_runtime": 2.5528,
102
+ "eval_samples_per_second": 68.16,
103
+ "eval_steps_per_second": 34.08,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 67381493760.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null