duyphu commited on
Commit
218a481
·
verified ·
1 Parent(s): bf36fd1

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ea225bc7cd779fac9cc9b41f07d0b86436c10a794dd46fe060e53ed137dd42f
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e279d22cf2e4188912641cf0b768cc864df9bd61cf1762ebd34634ab28f4765c
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:538403e5d6e61d307b9cdb985d05c083984df1049d6057c77fd80e01273caaae
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0c667c7c1cc3cccc4f358115ca1782e08deeae8312e30f0e797b77e4dc92b4
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55bb59e79ad5fd2694553ccebf289da4173c21393a2a030c807225f775413eff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9c793d071e896d1051385592c277f6c68b0546d5f22bd7f54f2f1d99273487
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.027253668763102725,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 5.038,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2643747573596160.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.040880503144654086,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 5.038,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.031446540880503145,
72
+ "grad_norm": 10.36804485321045,
73
+ "learning_rate": 5e-05,
74
+ "loss": 4.4984,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.031446540880503145,
79
+ "eval_loss": 4.253625869750977,
80
+ "eval_runtime": 22.3864,
81
+ "eval_samples_per_second": 17.957,
82
+ "eval_steps_per_second": 8.979,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03668763102725367,
87
+ "grad_norm": 9.573823928833008,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 4.0202,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4017800588820480.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null