phungkhaccuong commited on
Commit
b8b990a
·
verified ·
1 Parent(s): 2ca23a1

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 sha256:2a336b21b4e8e7f7551bbc3f01e7b14ac025b00b6a9c8bdc8171a6026b8b02ac
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82ee30d3e6133ff5dbc8447ca053df6726b6248296309ae92137e68982d6fd1
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6628ccd6a892c31934180115579600e85fe71b6fe3791161f9a2ee364d5af05
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b53b56f168fe155f7105deddc1dcecec2a18fac132b9042507ae77c3341448
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad1deb19dfc06efe6bedbf0434079d14d5dbfdf0a49f0d422ad00ca8a5d0b31
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c92eaf57053cbecdaa0579160167ea852314d5e01fbc4749b533abb666c0771
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": 0.02234156820622986,
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": 2.2547,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4808867045179392.0,
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": 0.03351235230934479,
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": 2.2547,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02577873254564984,
72
+ "grad_norm": 1.3723353147506714,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.2388,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02577873254564984,
79
+ "eval_loss": 2.2458176612854004,
80
+ "eval_runtime": 60.4579,
81
+ "eval_samples_per_second": 8.105,
82
+ "eval_steps_per_second": 4.052,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03007518796992481,
87
+ "grad_norm": 1.2066928148269653,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.3131,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7213300567769088.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null