tuanna08go commited on
Commit
51c75cb
·
verified ·
1 Parent(s): 76a5fbb

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 sha256:421df45b71d63d41d9151f33085175882b64dfe14c9dd6038cbe60098946a62f
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1807764b23bf76e80febd2d547f6e5b7fef15330de7075a424a87523966cce5
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d08c1b4bdd07fe1eedc03634213b7a210f91095825225b0fa65cb0f98e9d1b8c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7437003c5bae6203de0788ac3c06312a707671f74bd830aae756c655a0e953a1
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eba564523b8e7170117124c450887f82a78e23aad68f44ac77face0466e16e2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1725e7293373c9cc3826b6840eeb6bb1ffadc4138562c0593100d93aa07a3e1
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": 0.026375855947248287,
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": 4.3569,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9070066142281728.0,
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": 0.03956378392087243,
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": 4.3569,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03043367993913264,
72
+ "grad_norm": 7.597216606140137,
73
+ "learning_rate": 5e-05,
74
+ "loss": 4.9156,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03043367993913264,
79
+ "eval_loss": 1.136177897453308,
80
+ "eval_runtime": 73.88,
81
+ "eval_samples_per_second": 5.617,
82
+ "eval_steps_per_second": 2.815,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03550595992898808,
87
+ "grad_norm": 8.975362777709961,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 4.4263,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.358319084109824e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null