duyphu commited on
Commit
988a037
·
verified ·
1 Parent(s): abdd1b4

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 sha256:040a5e9a1139967d63e8780736b9e02ba4505f07efc590995875aa207f1b310d
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6df4a5d55ecc8c3adcbadcb2349717a837821cb6cec4ad04b157f5f626e67e
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a9788a292cb1c6a3cd380e4403312823977981d4ed056afb4b25c3e4597942c
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4fa3cc6a191c31ba5233bd2e0cf17bcf9f5c85eaeed8bbd22acf9442cfcf9d
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65aff41284df3bb03394cbdcf4e3b2890e7e5a16910233362baef91ee578828c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7458535a598eff19c9f56e9c654a6f3d6525c5476aca0e0ac50d69d1e2572b95
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": 0.0016081893952280073,
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": 2.2323,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9268793368903680.0,
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": 0.0024122840928420108,
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": 2.2323,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0018556031483400084,
72
+ "grad_norm": 4.070034027099609,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.468,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0018556031483400084,
79
+ "eval_loss": 2.291248083114624,
80
+ "eval_runtime": 970.6296,
81
+ "eval_samples_per_second": 7.014,
82
+ "eval_steps_per_second": 3.507,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.00216487033973001,
87
+ "grad_norm": 3.880756378173828,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.3391,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.395096733876224e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null