duyphu commited on
Commit
83cab1a
·
verified ·
1 Parent(s): 88cd990

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 sha256:98d42b398dedd16cdbe49fc38eec633ba6b8430558b39349a121535d8d3be3e0
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479752a47fcba6c581ed2eb83fdaa07cb1b83c984bcd43c796ca49c632b0bb72
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eff7abd10735a21fccd369da38eb4819fbf58dce49959e4716717f15c150d83
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2da540c1c2028fb9515359b35166cb776730dfbe6d595841383f3fb98ec8e53
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:e12c942777fc09da747a25dca358fd03e95c6fe8144e84ff7e6e840e4cf92c8a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0a559ace6df90c8d5082d12929ddc5b820a5e6f1a55cc76503570b04996d09
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": 0.01491681009753299,
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": 1.2361,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2191527593902080.0,
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": 0.022375215146299483,
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": 1.2361,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.01721170395869191,
72
+ "grad_norm": 2.637056350708008,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.2209,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.01721170395869191,
79
+ "eval_loss": 1.190410852432251,
80
+ "eval_runtime": 36.0048,
81
+ "eval_samples_per_second": 20.386,
82
+ "eval_steps_per_second": 10.193,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.020080321285140562,
87
+ "grad_norm": 2.392871379852295,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.2144,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3409042923847680.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null