chauhoang commited on
Commit
64b7d5f
·
verified ·
1 Parent(s): 79a9223

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:f849720b59429fb9018de22ae36ff1365137f47c5091d999503d1e99409a3b60
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b376b4e023f5d02eaa8a33082a0363eb6e4bb7a1e0aef97f5632511708b89c4
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3f6d499f0d9ee7ee109094c4f3ae3afd406a5d72b9ab75f31c3d921e968a998
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:601c8cf9a0f6e80f286e928eaf41a6f7c230c99935867c713c7349721fd60342
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:063b198d14bfbd9c72942387bd8f823def8669e53a6e5658d6f8ffcc145487c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f433ed62c38200cb99bd4ea92305aacec81b1a38d1e001768339ab1f472e6821
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": 0.045454545454545456,
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": 3.3777,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5627837474144256.0,
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": 0.06818181818181818,
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": 3.3777,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.05244755244755245,
72
+ "grad_norm": 1.3302963972091675,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.3628,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.05244755244755245,
79
+ "eval_loss": 3.413740873336792,
80
+ "eval_runtime": 17.7307,
81
+ "eval_samples_per_second": 13.592,
82
+ "eval_steps_per_second": 6.824,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.06118881118881119,
87
+ "grad_norm": 1.3246403932571411,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.3863,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 8133662918836224.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null