tuanna08go commited on
Commit
f466fab
·
verified ·
1 Parent(s): cba312d

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 sha256:8d7d3ea1e097e035a423006a65fb5ea733859c16d8b4a7b16d9f525decd73f6a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6642daef3b69a0fff5cfc38c7ef35a8428615c39e2728488da2fa8721dc2900
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3df3ded4d29b49102fae0ae3a449a5024f7ca0c73636f8769ee21e020273c29c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41fc74d7290320475151a142672865f8d3068fbb3acd892a910ba83f5c866fa
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b65f1a0fab783030b9678af169570889794fb3146a39ba3945282029a965db4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f4d6bb4cc4e74c35f6a1360afa90540250a2e67956fb6d4004e4c1936bf578
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": 0.0004546408337413443,
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": 2.3363,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6935865930547200.0,
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": 0.0006819612506120165,
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": 2.3363,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005245855773938589,
72
+ "grad_norm": 5.118088245391846,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.4692,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005245855773938589,
79
+ "eval_loss": 2.5201780796051025,
80
+ "eval_runtime": 3211.5638,
81
+ "eval_samples_per_second": 7.498,
82
+ "eval_steps_per_second": 3.749,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.000612016506959502,
87
+ "grad_norm": 6.5606513023376465,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.5892,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.0265081577209856e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null