duyphu commited on
Commit
7872535
·
verified ·
1 Parent(s): fcd2019

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 sha256:078f8df3f7ca18a3fa6ebaa10607d5bda344924159deaddb14da8aae9d186bbf
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c261491424d59651698e4ffaa279cead67a5165db5fefa8438e560f78d05d71
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2adf99ce872bc70728298ec5b8dbc33311b574bdb6dac830d9d02ac93488bed
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934acad99c4942d90dff089cfd053b054480fb7ced5892875617cbf1093f7812
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:fb4384732486a1e2c8068a2293eb37a46b0e67a2c9448bfd1b2dec067d664d24
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d931e87ae8e5c24bad8f1bd3279b4bf6247e2199db3be6b9b713b3cbbb94217
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": 0.0007022709010000608,
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": 1.6707,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8347339865456640.0,
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": 0.0010534063515000912,
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": 1.6707,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0008103125780769932,
72
+ "grad_norm": 0.6931402087211609,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.7328,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0008103125780769932,
79
+ "eval_loss": 1.6576857566833496,
80
+ "eval_runtime": 1652.751,
81
+ "eval_samples_per_second": 9.432,
82
+ "eval_steps_per_second": 4.716,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0009453646744231588,
87
+ "grad_norm": 0.855765163898468,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.7545,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2582087894761472e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null