shibajustfor commited on
Commit
b5ed404
·
verified ·
1 Parent(s): 32fe6fd

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 sha256:9d0010793aabe842e6850840ad4f56ec74b7294a3d02e633810f7ae3aeeac551
3
  size 161714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a138088615910a0c8d925769e1b5e1544c5fc487d00bb685dfd6df9127fc2404
3
  size 161714
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:960af0ca667cd744e875a0caf5f7cc4d2169b9aa4c3a22597bfb45838756b39d
3
  size 64750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51d79a972cc128975132ed330d84044d75a8eab2c849be4b537001176fdc81b
3
  size 64750
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e993de387eaf1c76836fe66cd1e5dad0a9ea203c11a45d9654a843d94d4d08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.0018542621284789703,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 473.481,
46
  "eval_steps_per_second": 236.741,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 38561163264.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0027813931927184554,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 473.481,
46
  "eval_steps_per_second": 236.741,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0021395332251680425,
51
+ "grad_norm": 0.5226926207542419,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 6.8229,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0027813931927184554,
58
+ "eval_loss": 6.807439804077148,
59
+ "eval_runtime": 12.4673,
60
+ "eval_samples_per_second": 473.558,
61
+ "eval_steps_per_second": 236.779,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 59324866560.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null