lesso commited on
Commit
41d3054
1 Parent(s): 0a0209a

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 sha256:3558277e560a59b9badeb6bac2729bade34c78b8b20452984d4887b54497dbb4
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e685f9de10ae8e0042d030f3ef5d1d4e12cf5a4bcdcba2b413625675f94305e
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc8054f5f2102f9bf053d9fe6c4659c0c0ba6ab9b32c5e930f053d851021ce4
3
  size 160172858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f786fd3f840ceea0e074566724939613c3aa157fa9eab561d6aae45dc993c2
3
  size 160172858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3483100185f9bb64a1baea7d0678dd8819a763e19d4dc3947a4c495c2a757eec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54088f61daf67ba3987886527d2520040d63916cf72a674a3a58d1cc4e57624a
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": 0.00064246707356248,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 10.649,
74
  "eval_steps_per_second": 10.649,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1669451464310784.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009637006103437199,
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,
 
73
  "eval_samples_per_second": 10.649,
74
  "eval_steps_per_second": 10.649,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0007495449191562266,
79
+ "grad_norm": 0.36104100942611694,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.9956,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0008566227647499732,
86
+ "grad_norm": 0.4580983519554138,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.0359,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0009637006103437199,
93
+ "grad_norm": 0.5145609974861145,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.8883,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0009637006103437199,
100
+ "eval_loss": 0.8663086295127869,
101
+ "eval_runtime": 184.9839,
102
+ "eval_samples_per_second": 10.633,
103
+ "eval_steps_per_second": 10.633,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2524536360665088.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null