kostiantynk commited on
Commit
160311b
·
verified ·
1 Parent(s): 7e0f7f0

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 sha256:6ddd91eb01044148105edb1719f30143179e1203b0ff7a29588185bf59494253
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54722a74ea64bbfeac0b0838c511129565367b648603f547c401522dba1b24e9
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eb1000b1aa71a917dfb1855d9269803bf4fcf0d77d9fb72fc606bd303d10d14
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c230aa914d3ceca0a8001fded80b5ccac90d739fcf4bcb7fe5049b9102553a7e
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e27cd19f974f785eff0dd466312f3df9cf7c31c05e4df06e9fa559050f360be
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a14a16007d1242716f4ca0ef3e774a2a2fb5bb35e61cd0b0a58afdd92059628
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": 0.0013718506793299037,
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": 20.691,
46
  "eval_steps_per_second": 10.346,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 3349006302314496.0,
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": 0.0020577760189948555,
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": 20.691,
46
  "eval_steps_per_second": 10.346,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0015829046299960427,
51
+ "grad_norm": 0.646447479724884,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 1.1103,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0020577760189948555,
58
+ "eval_loss": 0.5264923572540283,
59
+ "eval_runtime": 192.9002,
60
+ "eval_samples_per_second": 20.684,
61
+ "eval_steps_per_second": 10.342,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 5023509453471744.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null