phungkhaccuong commited on
Commit
914995b
·
verified ·
1 Parent(s): f32e9c2

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 sha256:7bbea78e1ad7b03886c63d0303a73cc62ff2144543fc87afb5f154fa2a28b89b
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd37880839e6f1a0fcc287be5dda6a422e887523ad68a253a27a2278b7352cad
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d97a2223a4798de92b7ff7835008e4d945f4ef00e4116adfc1384a3c094c368
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc31eb0ca7439971533b46eeb7ccb7e28d94e9f474d786b46c3637434e3cb69
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acd0be13f0ec7941600ed6c6a8548ae99c85efa3317ee073f3d6c665dedd1743
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc320ba6ece3516819691f442cfa1d1723dc2597d5a5228cb7f81ca049b95933
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": 0.011120615911035072,
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": 0.4865,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 131169388068864.0,
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": 0.016680923866552608,
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": 0.4865,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.01283147989734816,
72
+ "grad_norm": 0.8162946105003357,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4356,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.01283147989734816,
79
+ "eval_loss": 0.5716511607170105,
80
+ "eval_runtime": 18.8325,
81
+ "eval_samples_per_second": 52.303,
82
+ "eval_steps_per_second": 26.178,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014970059880239521,
87
+ "grad_norm": 0.6465003490447998,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.3828,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 198040056496128.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null