chauhoang commited on
Commit
464bee7
·
verified ·
1 Parent(s): f5b8f33

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:c4c56770f6c64e1be90e7670833a3f9ddd34cfc596b549eca7ba11a3dfdb3a3f
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed1d45474cab4980753f156dcad1e1a5e2711a0e628eeec58ac74e365a9e9a8
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d10f92e571f702b9428bb57db14a340d45ba629d264942fd5daf892d1426382
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90af40dae5ecdfe2da9383ae97bd71e41228c5a1fbdd6a70561bc286c4d9277d
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c7b895dbd817964db8ab0bbb7f84f180d00f39e68a0bd2e127356ac525d7c30
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa539f6e4688557e287ce87d8b179dfd55b8cad2483d5ba29fc9d6b605bb4a7
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": 0.06611570247933884,
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": 1.6945,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1712833357676544.0,
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": 0.09917355371900827,
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": 1.6945,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.07628734901462174,
72
+ "grad_norm": 0.6166580319404602,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.8622,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.07628734901462174,
79
+ "eval_loss": 1.7218282222747803,
80
+ "eval_runtime": 10.3009,
81
+ "eval_samples_per_second": 16.115,
82
+ "eval_steps_per_second": 8.058,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.08900190718372536,
87
+ "grad_norm": 0.7534248232841492,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.818,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2562998819880960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null