tuanna08go commited on
Commit
1d97e7b
·
verified ·
1 Parent(s): 3ecea13

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 sha256:6785a7aad216f597a97cd617b028142e4da1e93c0c7e8a8486723bbc45984ade
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb658c1e128ae211c4a80a703805f71d272e2c8ced9c73a70148c0f532e9b16b
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd5dd1dbdf0f6c8bd47dcf43086a167454b465934a17a8c6fbfb327d6a63b69
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbeca8010759600245cc5b750e78d3f72140f139cc64b3b357c82d9b497c7c3
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:107a2111e838867c3feac9e98b4e198826002bd6fc18625eae8ef120b76d9b4b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539f6fec05424d4999d48d5e57223c607bec5f3cd6f24e3fe3db842c0cd3c8b6
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": 0.0023953199133999723,
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": 9.5732,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2753860133191680.0,
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": 0.0035929798700999587,
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": 9.5732,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0027638306693076606,
72
+ "grad_norm": 3.964927911758423,
73
+ "learning_rate": 5e-05,
74
+ "loss": 9.1613,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0027638306693076606,
79
+ "eval_loss": 2.22302508354187,
80
+ "eval_runtime": 268.9169,
81
+ "eval_samples_per_second": 16.998,
82
+ "eval_steps_per_second": 8.501,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0032244691141922704,
87
+ "grad_norm": 3.796499013900757,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 7.9359,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4222585537560576.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null