phungkhaccuong commited on
Commit
0c38344
·
verified ·
1 Parent(s): e67431a

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:a5ce53bc19aa2ffcccb7a9b173c05a537da712849d267f09462933807e603d5d
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9fc57c48be99f68456439a491ddeb8ee43af8698865365485aea0b6e4b318e9
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1805c2c56b2ea13cc05c382d8da945aa35d9c8e3c78170118f920d015cb97c08
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e04d4a972cfc116140a1a335b6c5e1ab3c7c79cc671281cc873369ce5b08622
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": 0.002191642256548585,
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": 0.0003,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4234706153373696.0,
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": 0.0032874633848228776,
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": 0.0003,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.00252881798832529,
72
+ "grad_norm": 0.0014348478289321065,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.0001,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.00252881798832529,
79
+ "eval_loss": 7.054233719827607e-05,
80
+ "eval_runtime": 290.7879,
81
+ "eval_samples_per_second": 17.177,
82
+ "eval_steps_per_second": 8.59,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002950287653046172,
87
+ "grad_norm": 0.0006044543697498739,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0001,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6352059230060544.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null