kostiantynk-out commited on
Commit
f85db00
·
verified ·
1 Parent(s): 6c99f74

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 sha256:198fe6b37fb6b90d34e501ece4552622bbf82383bcbb72ee09c95986d19faec7
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbed8f364bb5b28c1116de344ea3371a9ebba57bbae59e4b34dad1167adf268c
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97e5782db96a96db370c9eacb604a1d642e1e8becd17d752a3c2dc3baa0aba33
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6f81b8e5caf7665d80abbd2f463c638e5734be3925d40a3257b86f5eee9824
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:290db72453c0549da48ac2c903de9d8ef739ca7e660c6a1235dab2d77509f626
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc527ae92339ea167c2945496cfde8562215165c21050204ee36547f80f22391
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": 0.00016650594218081157,
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": 31.523,
74
  "eval_steps_per_second": 15.763,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 300058398425088.0,
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": 0.0002497589132712174,
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": 31.523,
74
  "eval_steps_per_second": 15.763,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00019425693254428018,
79
+ "grad_norm": 4.960712909698486,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.8703,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00022200792290774876,
86
+ "grad_norm": 3.8892712593078613,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.3767,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002497589132712174,
93
+ "grad_norm": 3.7098920345306396,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.813,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002497589132712174,
100
+ "eval_loss": 1.7475117444992065,
101
+ "eval_runtime": 499.9676,
102
+ "eval_samples_per_second": 30.348,
103
+ "eval_steps_per_second": 15.175,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 450087597637632.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null