duyphu commited on
Commit
3961f62
·
verified ·
1 Parent(s): 4512241

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 sha256:209c7f2bb1f0b990f36d30182fc28094ee136dba3c3c724b8b8f6c183ca218ed
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d72601fdc47120ba0a21293f05401c2170be5aa798f5ca14b8d005344bb112c
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab5a5893eba778947dd6752871f3decfce158efc321d1845287e17551f34028d
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1de62ab6fa9fade0448e6875150898ca9b81788053a9bdd6f2357010272a583
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a660fe1685e8a6b7a3af3fc232b2540a63f4d3847dc6daad940db92f4e5b7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d353d97d0b63c56a83db8404c27f273e2a2788441660a22b36acdc00febe2be4
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": 0.012070566388115135,
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": 12.6359,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 228094271029248.0,
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": 0.018105849582172703,
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": 12.6359,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.013927576601671309,
72
+ "grad_norm": 95.26651000976562,
73
+ "learning_rate": 5e-05,
74
+ "loss": 12.3584,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.013927576601671309,
79
+ "eval_loss": 3.173269271850586,
80
+ "eval_runtime": 18.1951,
81
+ "eval_samples_per_second": 49.849,
82
+ "eval_steps_per_second": 24.952,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.016248839368616527,
87
+ "grad_norm": 108.44436645507812,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 12.8901,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 344334620688384.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null