trenden commited on
Commit
3c3ea2d
·
verified ·
1 Parent(s): a3f6f75

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:e6e24f704c26b5d29144ef08b4974df88142f5c1f07a91faae3357e2659b251a
3
  size 16794864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e24eb6f2ee5d1e050a651951cf2de06a516ea9d76a737ff2803f6159b01761
3
  size 16794864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:524f8748f3015b4d39b8d303b9e773d06be2a0db712925a9275a47018189e032
3
  size 8671162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:239fb36e72e17a2fa7f04d31fc3ff5adb45cfc5137fc6775b8f3a9ea2d124b18
3
  size 8671162
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:830c0717e1a623f4428da5c6215b99cc10f0295b0807586eba37d260994f5fd2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88f1c8f29deec72fdb86411eef34c00d861bf676cb3ace988ec0111b482ed57
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": 0.018554861730597682,
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": 133.145,
46
  "eval_steps_per_second": 66.573,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 583355275935744.0,
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": 0.02783229259589652,
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": 133.145,
46
  "eval_steps_per_second": 66.573,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.021409455842997322,
51
+ "grad_norm": 8.210744857788086,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 6.1164,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.02783229259589652,
58
+ "eval_loss": 1.2978790998458862,
59
+ "eval_runtime": 4.4556,
60
+ "eval_samples_per_second": 132.417,
61
+ "eval_steps_per_second": 66.208,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 875032913903616.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null