ClarenceDan commited on
Commit
b3f6ce6
·
verified ·
1 Parent(s): b759ecc

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:c5113a2e653b1a6db3c79911f05fb53cc2a43dcd98dadaa765d34d841f4d9e45
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f3816166db092ce32461101c0a9f684c851f7a1b0a49078ac37f16a7ef601a
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e669d5550458eb7d05f6c5a85beab84793c642eeccfe098573dd641926a594b4
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac5b878963166560b0c0bb1d787397540c1f3995a9144e0415df6247992d6f8
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
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": 0.0036036036036036037,
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": 160.025,
74
  "eval_steps_per_second": 80.126,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 492177457152.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005405405405405406,
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": 160.025,
74
  "eval_steps_per_second": 80.126,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004204204204204204,
79
+ "grad_norm": 0.10223779827356339,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.8398,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004804804804804805,
86
+ "grad_norm": 0.1232127845287323,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.8399,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.005405405405405406,
93
+ "grad_norm": 0.13759197294712067,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.8265,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.005405405405405406,
100
+ "eval_loss": 10.837149620056152,
101
+ "eval_runtime": 4.3583,
102
+ "eval_samples_per_second": 160.844,
103
+ "eval_steps_per_second": 80.537,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 738266185728.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null