Aivesa commited on
Commit
5fea149
·
verified ·
1 Parent(s): fdeaf61

Training in progress, step 9, 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:c38ffe4d14cd55c08f097f26421cabb564b9c6d4451a30379505487ed77218e4
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb4c50fce6fb3ef0e1ee2c02f352b528a6e87352552e2d9bdad3439caefb6b8
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35dfd5e31c0d5884b627d90dac2a01f1bfa5b1a8d86f8be7c6ec822f260a7bdb
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1f301da5a493c8102dfa3afdb6231ed4e7102065535f7b164d016dd6c2f988
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48d4efbdd6be505612a10c38990de33ca2143b4d80eaad8ab36f9c1966758683
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e080bbaaf7f398e3c31827b98141f7e6ea8bca33ad66752d1d4dadd3b7436a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.002551834130781499,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 28.036,
66
  "eval_steps_per_second": 14.018,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 98694636503040.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003827751196172249,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
65
  "eval_samples_per_second": 28.036,
66
  "eval_steps_per_second": 14.018,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0029771398192450825,
71
+ "grad_norm": 19.050405502319336,
72
+ "learning_rate": 0.00014,
73
+ "loss": 6.4988,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0034024455077086655,
78
+ "grad_norm": 21.619447708129883,
79
+ "learning_rate": 0.00016,
80
+ "loss": 6.3776,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.003827751196172249,
85
+ "grad_norm": 17.375764846801758,
86
+ "learning_rate": 0.00018,
87
+ "loss": 6.7369,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.003827751196172249,
92
+ "eval_loss": 1.5340806245803833,
93
+ "eval_runtime": 34.2694,
94
+ "eval_samples_per_second": 28.889,
95
+ "eval_steps_per_second": 14.444,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 149138561826816.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null