chauhoang commited on
Commit
ef08500
·
verified ·
1 Parent(s): ff12479

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 sha256:5f4588b774dceef1e19bee5dbd70dd6037aeb699f2b3e4222ff18c7641100068
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4a5e792b93d17ae648094dc2b143adb6a1d51109776ab9b576a4a7e17447d4
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffa1a9910a429b5bfd12e002d8ca0eceafa901f58ebe63c0d5a429c26257844f
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987c532242177d4b57d7b2257b56ec7e707e68bfb5cb5f6d5e1f1e43d840388d
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e557af93914c894de252ad5739c858bc8be67dba19068d91502dd049001e333e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da57a3a869ac100e03e854428cb96b9fe176c6ed5065d0878032c78bdd0f415e
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": 0.002832321141643291,
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": 3.8274,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2132126528962560.0,
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": 0.004248481712464936,
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": 3.8274,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0032680628557422587,
72
+ "grad_norm": 2.1029868125915527,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.572,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0032680628557422587,
79
+ "eval_loss": 3.6732211112976074,
80
+ "eval_runtime": 147.1822,
81
+ "eval_samples_per_second": 26.267,
82
+ "eval_steps_per_second": 13.133,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0038127399983659688,
87
+ "grad_norm": 3.5215439796447754,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.7833,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3198189793443840.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null