duyphu commited on
Commit
212a2cc
·
verified ·
1 Parent(s): f9b1390

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 sha256:3f3cc1c31abb1395fff7fe0a73386bde4c4cc4c989ee354f9cdada39e83eef7b
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d739181fb85db551f2dbc994b358d6e0accaf90e6f090f0efa5246ef289cbd99
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e56b8d967290a40bb1fb0245d140fa2ade828c84a3e96db6bd20382587cc190e
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfcea14fcfb14850eb274d3bcf8e3bf45cea51d1ef16c90868d631147d3a6e95
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2375426862b4f13ce35577b98d89db2b13044a902b481f88885debcd45088cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7de898c197172b52a45968a35db678287a8ed888d349ae1c9fec1ef54776db7
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": 0.08300079808459697,
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": 1.613,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 829882028261376.0,
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": 0.12450119712689545,
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": 1.613,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.09577015163607343,
72
+ "grad_norm": 0.8338580131530762,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6784,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.09577015163607343,
79
+ "eval_loss": 1.6296522617340088,
80
+ "eval_runtime": 4.2233,
81
+ "eval_samples_per_second": 31.255,
82
+ "eval_steps_per_second": 15.628,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.11173184357541899,
87
+ "grad_norm": 0.9931209087371826,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6411,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1226782128734208.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null