shibajustfor commited on
Commit
c4c2565
·
verified ·
1 Parent(s): 5d821b0

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 sha256:49a1c918fcda2a975a96e4fc373262467e5584955e7e39b9e8623c783566cedb
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3b3bd4231582b1fa4d2d7e6e21400715365e206b9941ce4f35a208b5583120
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a4f4cf08eea244d4f0c41f098c906a75535ba3357b57f899ec840d15639ae1e
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7cc0ad3c8afd27f48fa469bdf474af7e15a3b9014e0006ee16b1e0707f96ca9
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
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": 0.00404040404040404,
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": 364.255,
46
  "eval_steps_per_second": 182.127,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 3219660865536.0,
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": 0.006060606060606061,
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": 364.255,
46
  "eval_steps_per_second": 182.127,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.004662004662004662,
51
+ "grad_norm": 0.2962060272693634,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 10.8256,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.006060606060606061,
58
+ "eval_loss": 10.80303955078125,
59
+ "eval_runtime": 7.4648,
60
+ "eval_samples_per_second": 363.037,
61
+ "eval_steps_per_second": 181.518,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 4942281965568.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null