chauhoang commited on
Commit
fc0c371
·
verified ·
1 Parent(s): 0e6a299

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 sha256:4f467e1c4adca3a515f20c7a20358d008bee5f0c0afc391064a7d8b5342f2752
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465aa0e6592abf061075a7325916b9ecefc8319eb63546b50a4895c4b2c73b0a
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a6920078d1c4075a91533e556532f37fd035f0c8af3aa0327892d8571de1f8a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eebdc7fe1c9b1749572e1c818b0db8fe3799ed040845c660077ee46b8f256e0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5803672b70de78596eaeb18d3a249ac6e5bb05bc00cd70eddb4f24e2d04b1873
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e029eb4948e78d3baec5a28b1d457b35bd248ab09130b2c52006c8708c222df
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": 0.017799075817217184,
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": 0.601,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6288518443696128.0,
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": 0.026698613725825774,
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": 0.601,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.020537395173712135,
72
+ "grad_norm": 0.9632827639579773,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.609,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.020537395173712135,
79
+ "eval_loss": 0.622657060623169,
80
+ "eval_runtime": 50.7462,
81
+ "eval_samples_per_second": 12.119,
82
+ "eval_steps_per_second": 6.069,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.023960294369330823,
87
+ "grad_norm": 0.5321747660636902,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5539,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9247821240729600.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null