duyphu commited on
Commit
7905339
·
verified ·
1 Parent(s): e41bed5

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 sha256:499ebb1bfc3d4dd5529b09bbf97240ff65eb365d873e472b5de0fcd8507a7f9e
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03d5e8c34ab44b87a4cb440ca1c3b7f5ff7b8a484a119cbc3e3e8014d7776b4
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dbb2b7c49f7d9c7ea522d8de58bd705f8661e93b83d047d9e1fb4c719a9dc54
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03935a39f6f99141d751c2cd93a0571264a6c47b24246bcce451039b0ba194d
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c0a2f298542422c4f57b584e3c4258688b62f2945feca91d54575c701b5435
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec698543fc8efe1c42cfec18e55613892ce220f315dbecc631afb9ede0781a9
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": 0.0010436004214540164,
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": 0.0416,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 365056471597056.0,
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": 0.0015654006321810245,
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": 0.0416,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001204154332446942,
72
+ "grad_norm": 0.4202684760093689,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.0625,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001204154332446942,
79
+ "eval_loss": 0.058590423315763474,
80
+ "eval_runtime": 390.0396,
81
+ "eval_samples_per_second": 26.895,
82
+ "eval_steps_per_second": 13.447,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001404846721188099,
87
+ "grad_norm": 0.6236194372177124,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0789,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 552036615585792.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null