tuantmdev commited on
Commit
e627062
·
verified ·
1 Parent(s): abc4356

Training in progress, step 160, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef29c78cf1fc2aea8813e530e1ae3e93ab8e0527cb20bb4d6f6e8229e703784
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0d23e704cdea01490c820e42fdd840657f2957a1e9b292df4c1a538e62af1a
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5254969b5f8c46f3eb9b5eb37f1f1cda2cc29d31ef25a3827eb11e64134d5bb
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab216b0452c26a3e24efd82ee8e3ea1f46521a2a264e56103ede5421f7f1dee
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8c6245a88bb55b540f19788bcf53d1989864172e536f45d09b31f8665a109f4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d5a7d54c93ecd3f4e8fa6889b459b14554a16ac8e5c6ae5718291742bf3789
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
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": 0.018643853839954167,
5
  "eval_steps": 40,
6
- "global_step": 120,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,21 @@
60
  "eval_samples_per_second": 42.515,
61
  "eval_steps_per_second": 21.259,
62
  "step": 120
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 40,
@@ -79,7 +94,7 @@
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 7038466848718848.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.024858471786605555,
5
  "eval_steps": 40,
6
+ "global_step": 160,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 42.515,
61
  "eval_steps_per_second": 21.259,
62
  "step": 120
63
+ },
64
+ {
65
+ "epoch": 0.024858471786605555,
66
+ "grad_norm": 0.19861990213394165,
67
+ "learning_rate": 5.000000000000003e-06,
68
+ "loss": 0.0553,
69
+ "step": 160
70
+ },
71
+ {
72
+ "epoch": 0.024858471786605555,
73
+ "eval_loss": 0.04789276421070099,
74
+ "eval_runtime": 255.9177,
75
+ "eval_samples_per_second": 42.361,
76
+ "eval_steps_per_second": 21.183,
77
+ "step": 160
78
  }
79
  ],
80
  "logging_steps": 40,
 
94
  "attributes": {}
95
  }
96
  },
97
+ "total_flos": 9311165979820032.0,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null