duyphu commited on
Commit
2daaf8c
·
verified ·
1 Parent(s): 5e6bf0f

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 sha256:5b250f3f86e9fc4188517cc5c1c93eed89c0e7db7704f66861fc5b241becbe2a
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8edb840461ccb7be6861578ee4ff4b38f0116225b852c53a08eff610e8ee21e0
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54fa12cc9eec219b1c4b82fb4e3a3c1f1af8f96339bf6dafc1dcd484b6afdce9
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7dd04586ffdddb56f092c98de106b9b854da264941a0256e96eb554208ce67
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:728673b92976f39bdf8edc770560e4ef6b61c1c501931d83ff4d3bf638d48bfb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64e0d7db9f8b3e2f5a82311e462e9f3e1bbcea539743f12a28f5144cf6ceb93
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": 0.0028156811782542777,
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": 1.366,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1782577253842944.0,
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": 0.004223521767381416,
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": 1.366,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.003248862897985705,
72
+ "grad_norm": 4.017838001251221,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5395,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.003248862897985705,
79
+ "eval_loss": 0.6098601222038269,
80
+ "eval_runtime": 186.9724,
81
+ "eval_samples_per_second": 20.795,
82
+ "eval_steps_per_second": 10.397,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.003790340047649989,
87
+ "grad_norm": 4.869180202484131,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.4914,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2691006046666752.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null