duyphu commited on
Commit
6d36d5f
·
verified ·
1 Parent(s): ae75f94

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:bb3808db039136cd4caaccb1042ada32261ef3ae947df0a346a07922149fbb8c
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b22f2a9248cbd8231ee844533856891cd70ef94a266e270a27b984786e787c4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cc74c2f94acacd49d4250f2433ac3254bb9bee70c67c0bc9a4f9f4ba0c8302d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398faea48da3392c31c588a338d7198427c5fabee6eb306e639f57d1fcafb235
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8356e0eedb914506be9d6834a09dc3748c48d92697d3720f05ef898a38d1c12e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d894e21213c07cbd0cec0014f57efd5c4063573964a7d259b2cdbd9a265b45
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": 0.0005240482729082159,
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": 1.32,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6982105036750848.0,
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": 0.000786072409362324,
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": 1.32,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0006046710841248646,
72
+ "grad_norm": 1.0257610082626343,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.1806,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0006046710841248646,
79
+ "eval_loss": 1.1275124549865723,
80
+ "eval_runtime": 1879.839,
81
+ "eval_samples_per_second": 11.113,
82
+ "eval_steps_per_second": 5.556,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0007054495981456754,
87
+ "grad_norm": 0.6786960363388062,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.3336,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9941407833784320.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null