nathanialhunt commited on
Commit
a6e24af
·
verified ·
1 Parent(s): ca8c175

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:db484006509d32d7adaec262e245adba6ca8c09ff86895b44aac5a5bb91f4b83
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd04dddb6d005a1564187b0234613045376444d842a067d8b26fb78907578f36
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48b66c95962faee0850e0b759d28666b6a645bc8c893239168a9ea4708c13bf8
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ed4f247397a1327e11f48168704ce6c2e2a27702a50f814acca79b699430b1
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bd5a71c8d3679fb05142c2af980b4724a5b0e253b0cdc6272eb4e02445ac458
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ee757ee38972c71c71244d96c67f901bdf22f0776daf15866f8ab7a70cf9f4
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": 0.00557361820715281,
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": 26.901,
74
  "eval_steps_per_second": 13.45,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 537604630511616.0,
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": 0.008360427310729215,
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": 26.901,
74
  "eval_steps_per_second": 13.45,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006502554575011612,
79
+ "grad_norm": 0.3915104269981384,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.4111,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0074314909428704135,
86
+ "grad_norm": 0.3610092103481293,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.362,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.008360427310729215,
93
+ "grad_norm": 0.43476492166519165,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.4626,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.008360427310729215,
100
+ "eval_loss": 0.384464293718338,
101
+ "eval_runtime": 16.859,
102
+ "eval_samples_per_second": 26.929,
103
+ "eval_steps_per_second": 13.465,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 800155729133568.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null