phungkhaccuong commited on
Commit
0439c5f
·
verified ·
1 Parent(s): 66abf08

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:e8111cdfbce577f7422dc382bce938298ca721d8ac39dd861aacda27d7af324b
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732447f7a216b396be5f41de85247e60cb06a64070869c006c6d2b2ee6acc44f
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ffbc622ae51ff880912a197a2d9a613b76d69ef951594a6a49653686b3b6ddd
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10de69c1c6c0061ad3513d01f346875a2cf95b7b0d2384bf9758c1aed069f3d8
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd22f880dee0ce5dd119d25bee848382100f6e82be8be8743029639a01ab3da1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20cca61cca9e36aa1b69bdd6504a4e706175493008486e1ea5616609f9f32455
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": 0.02952029520295203,
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": 1.2401,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2091100240084992.0,
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": 0.04428044280442804,
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": 1.2401,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03406187908032927,
72
+ "grad_norm": 0.4039708971977234,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.2597,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03406187908032927,
79
+ "eval_loss": 1.2096537351608276,
80
+ "eval_runtime": 20.0923,
81
+ "eval_samples_per_second": 18.465,
82
+ "eval_steps_per_second": 9.257,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.039738858927050806,
87
+ "grad_norm": 0.41507863998413086,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.2934,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3102370028322816.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null