tuanna08go commited on
Commit
1040748
·
verified ·
1 Parent(s): 550483f

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 sha256:405ca5b743b4bb86487f26ec115316d05a119ff47b6109c59297064547ae4c9b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4d4deb49aa8333893ed3fae6cbf6ac86fb0da41b737e45e7c73fd504f59138
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db5ce6dcd1939eef79d2ff2883d6d9e8f61cd4401b2ca2605a316c54438420f4
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7adac44b78985ede53d4e11c45ccacfee7eda00a62fe3f87d2f7ee1d274bf1ee
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:a47fca3639d80e70dbf3c3184796f71da8605d334ca66b7e8450dbc7a8e3c251
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df4452b6ca42236c2bcd52b5df9f8e63ebc61625217e8356d9a4e2cc7327676
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": 0.009670820159940488,
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": 7.5632,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4819847447838720.0,
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": 0.01450623023991073,
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": 7.5632,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.011158638646085177,
72
+ "grad_norm": 21.01249122619629,
73
+ "learning_rate": 5e-05,
74
+ "loss": 7.2472,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.011158638646085177,
79
+ "eval_loss": 1.7419497966766357,
80
+ "eval_runtime": 108.0936,
81
+ "eval_samples_per_second": 10.472,
82
+ "eval_steps_per_second": 5.236,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.01301841175376604,
87
+ "grad_norm": 31.042816162109375,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.7182,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7273587966738432.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null