tuanna08go commited on
Commit
213379c
·
verified ·
1 Parent(s): d77d4e3

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 sha256:849e21a01cf14e0cbd07cbe4393bf2ae259a951643f363000dbb669d82770ae8
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf5d0b76cc1c294d9b93d2adf150a4249df0c05abf194569df1f968f278e6d6
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63b77c287ba0e1a795979e4b0d611230092fd48716faa5a102869f4a67ff9ef8
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0487ad0bf0060e91fc475f1ad2c6dc8aabe9f249c5c0af7a55edfceed33b3969
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1b3534a3a901147bff8ade449bb26ab7a947aa86bbd008f725e62ec281c1e3a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b925f41b93ae978efc363ec176c67bd523156ae2461120bbde365bcfec0fe9
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": 0.0008551365751780164,
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": 1.8805,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9937675364597760.0,
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": 0.0012827048627670247,
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": 1.8805,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0009866960482823267,
72
+ "grad_norm": 3.7152276039123535,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9245,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0009866960482823267,
79
+ "eval_loss": 1.8017830848693848,
80
+ "eval_runtime": 2023.9174,
81
+ "eval_samples_per_second": 6.325,
82
+ "eval_steps_per_second": 3.163,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0011511453896627143,
87
+ "grad_norm": 3.436457633972168,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.626,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.490651304689664e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null