tuanna08go commited on
Commit
e5c4fcc
·
verified ·
1 Parent(s): ab4b90f

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:d491b3645ea5684ae9b55f454d022425dc48c87500babba9ed0dd46116207f00
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d9ec29969f808c6440894ea017504e12e1a4143c086d918020a7b62424fdb5
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:846cb220930a00172b131504817db4123a3175645bdf99d7538df8e3c6cfda35
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c845979d0fcf955ba9fb363fd6613664ddab9c0de3a5221b4c7e92e55c2388
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
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": 0.006117287218398918,
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": 1.2073,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4272226987671552.0,
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": 0.009175930827598376,
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": 1.2073,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0070584083289218285,
72
+ "grad_norm": 4.847468376159668,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.9374,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0070584083289218285,
79
+ "eval_loss": 1.0444806814193726,
80
+ "eval_runtime": 131.4278,
81
+ "eval_samples_per_second": 13.62,
82
+ "eval_steps_per_second": 6.81,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.008234809717075466,
87
+ "grad_norm": 2.204052209854126,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0669,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6408340481507328.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null