chauhoang commited on
Commit
ad0a625
·
verified ·
1 Parent(s): 9fc6123

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 sha256:4f070452bd24cff69a78f0ac2756480a665c8c2aacdff9b3bcd7c9b1700fdf45
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3dfdf8c3ccb05d8cb8514811f3ee2176d88cd792b2e50791abd9d580ecf65b
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da9dac7d925bd1fe70721927bb0f6e127ace59e8cd20d3f571d2662255001aea
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5203a94a71b1b6b59a0fbd5c729acbbc3289cd46c0a7bf4b33487fae3ba68924
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68bd8c8e0925b342f12eb7af7f76dfd02dcd4f16cb8570a361136dfd35216850
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbee6f84100698b0431eb48ba6934e5b0162eed4307a92814544f14034fe8b20
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": 0.010612244897959184,
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": 3.1387,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9057657012879360.0,
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": 0.015918367346938776,
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": 3.1387,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.012244897959183673,
72
+ "grad_norm": 2.512467861175537,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.2341,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.012244897959183673,
79
+ "eval_loss": 0.763218879699707,
80
+ "eval_runtime": 100.7949,
81
+ "eval_samples_per_second": 10.239,
82
+ "eval_steps_per_second": 5.119,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014285714285714285,
87
+ "grad_norm": 2.0444631576538086,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.1349,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.397874625609728e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null