chauhoang commited on
Commit
c2d396c
·
verified ·
1 Parent(s): f4859d8

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 sha256:0f55a0c1beed4339bd5b16d5fa9b59b387099700fc903db09a84216f27e1738b
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca142807e3accd1d27573aceb6610b392f16e85d065ec0d80cfa5492f0d49c44
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f68ada2af2757d900d5db8b040ff86dc120a17a795910db83d8e88cf4874c97
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7fd17dee7ef53db22bdb91880d0d41ca1d1e7ca735bf68e98ab5266d83b5b8b
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3e2c18aa2ae28cac6de0a936cf187d80fe9ba4af7aaaf836168b5d337949c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153ac38337b7db7527868e522dddbcf1ec2ddfb83bf9056bffc1a383a4c77899
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": 0.01287128712871287,
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": 2.4506,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 812139530944512.0,
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": 0.019306930693069307,
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": 2.4506,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.01485148514851485,
72
+ "grad_norm": 0.6969410181045532,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.4852,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.01485148514851485,
79
+ "eval_loss": 2.4748666286468506,
80
+ "eval_runtime": 27.7477,
81
+ "eval_samples_per_second": 30.669,
82
+ "eval_steps_per_second": 15.353,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.017326732673267328,
87
+ "grad_norm": 0.5595166683197021,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.5691,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1227801495601152.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null