duyphu commited on
Commit
75cea94
·
verified ·
1 Parent(s): 91e9fff

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:c7954c145a00413b26fc50edb90180878d630ab2d26433950eb0004c30764774
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dee11cdef5f41a89f36ed393cfeb898b8f8e41ea71a87a44728307b8216e5b8
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ce983545b75d9c335c6d8ddf5c0faec56582dd947787a8cf060452c1f7a019a
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:048e31d49f912495b59d7838bc551a1055ff1ef6c87f4b59d005facc8214e6fc
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab88c76e1a200c7f5fc1bfd392b2b60a4878104da3f6a35d2813aaaa7c1e3d68
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea02351e4f1449e24d2b179ecb6369a16ac5f33053c1ced26f2e6c56b7d9c09c
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": 0.0005776333694354189,
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": 2.4069,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4244442879885312.0,
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": 0.0008664500541531284,
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": 2.4069,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0006665000416562525,
72
+ "grad_norm": 5.183065891265869,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.5257,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0006665000416562525,
79
+ "eval_loss": 0.4758754074573517,
80
+ "eval_runtime": 1094.0337,
81
+ "eval_samples_per_second": 17.324,
82
+ "eval_steps_per_second": 8.662,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0007775833819322947,
87
+ "grad_norm": 5.683261394500732,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.9673,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6407476270596096.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null