ardaspear commited on
Commit
01ebb94
·
verified ·
1 Parent(s): 5b7718a

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a277460a0d360dd0a064d98263b5619098075640af04e651d7c0fdacb88227a
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18576dc1f9c92550d56ed38e62e4d75fece379b10517d92c74cfe6a6c67ee48c
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cbdd66c6c3a197379177729dba1edc0ccd0bb0d489d550ebadc2d82083746de
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17783c70dd0fe8b0e2fe9cdc558d7b872eeb2c95aba98374b81d204959a70d04
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75e787713c79490033aa63cbc5d7cee2bdf0359133f3625950f4f0d7d6e61f24
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2388a3f3387eb7fcab3d95cc6f7d549ec4545ab04c891b3624bae11c9e8cf700
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.10449927431059507,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 35.539,
74
  "eval_steps_per_second": 4.534,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 5764235611078656.0,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1567489114658926,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 35.539,
74
  "eval_steps_per_second": 4.534,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.12191582002902758,
79
+ "grad_norm": 0.5673230886459351,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 0.9585,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.13933236574746008,
86
+ "grad_norm": 0.47465190291404724,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 0.8755,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.1567489114658926,
93
+ "grad_norm": 0.5033220052719116,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 0.788,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.1567489114658926,
100
+ "eval_loss": 0.743035078048706,
101
+ "eval_runtime": 8.1945,
102
+ "eval_samples_per_second": 35.389,
103
+ "eval_steps_per_second": 4.515,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 8646353416617984.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null