chauhoang commited on
Commit
f9f6a11
·
verified ·
1 Parent(s): 79f1588

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 sha256:026bcb141bbd9c2dacda3d05278a8a0a59f4da5842f584bb1ed176d2fae6f3f8
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2e5cc55d408ae0e17a2c97c6c75a7b57de7ccee99bbc9c1982b8f24a69a504
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8b3012336bbc59237b4804077c8cb2b56a46e57f25653858b6ca3a12ef9c078
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb466183eaaad20a2d2b1809d98ae453a8754d39944ff04366d7f43d5641b49a
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35678f2e164dea4ebbafdb4df13644ad3b9d103a7e957de1eef9bc9540a6bd78
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab423bf67e2c5e85eb32f5af0f6128c31e26227abaf51e1b653a551268fea34f
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": 0.0012249272699433472,
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": 1.6659,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5225019001012224.0,
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": 0.0018373909049150207,
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": 1.6659,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0014133776191654005,
72
+ "grad_norm": 1.39825439453125,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.7729,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0014133776191654005,
79
+ "eval_loss": 1.7357591390609741,
80
+ "eval_runtime": 668.5358,
81
+ "eval_samples_per_second": 13.37,
82
+ "eval_steps_per_second": 6.685,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0016489405556929673,
87
+ "grad_norm": 1.4528638124465942,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.7096,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7953126267027456.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null