kostiantynk-out commited on
Commit
b8c1800
·
verified ·
1 Parent(s): 6cd854c

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:c1bb6581d17652f455662f249ac91e05b6d013823347fde3e6cd7b1044acd611
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc72206104232e6314c5bbf95d8a4c1994992410640d0744a2042af03eb9f68
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbb872a21d8b5b11bc1475f938f44135fec7797927bf4c73df4821167d4985aa
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3eaaeccf4a6040c6caa7f35cc97acddf6e5846a43073ffce45b0cec5e8b09f8
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:830c0717e1a623f4428da5c6215b99cc10f0295b0807586eba37d260994f5fd2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ef78f97fdbf4f4d79c928df14622d2a5bd7bccc0a4be9d07392ee5bbaea2cc
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": 0.00020824295010845987,
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": 37.703,
74
  "eval_steps_per_second": 18.851,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 669273056870400.0,
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": 0.0003123644251626898,
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": 37.703,
74
  "eval_steps_per_second": 18.851,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00024295010845986985,
79
+ "grad_norm": 2.251619338989258,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.9577,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00027765726681127983,
86
+ "grad_norm": 2.264468193054199,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.5139,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003123644251626898,
93
+ "grad_norm": 4.589754104614258,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.1324,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003123644251626898,
100
+ "eval_loss": 1.2194496393203735,
101
+ "eval_runtime": 324.2447,
102
+ "eval_samples_per_second": 37.416,
103
+ "eval_steps_per_second": 18.708,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1028395184947200.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null