Best000 commited on
Commit
8bc5f14
·
verified ·
1 Parent(s): 8b0b821

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 sha256:0648e4eb9ffd332d3f9c7d5dc39d7f3832d62fbd24fe8b86901b2c58dc0bb6e6
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a79b84e518dc9be68a0f9e30bbc382d9593d7dcbb75b1e178c014420f02603
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:717b3f611426bfcdf300b37e755ee0d823de3b209148887574f75a64ff814921
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13edcfeae14cda70e2cdc7ad8c907c258f66621c42142db4dc4d8f0b2b94d73
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f43bcc3e599f3eb98503de5dd95e8b076a5d52023eca741e8ab5ac1da3782c74
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe9292b93acc5d120d0451081c1f103c87e36ea135c3d8cfd8c43ee2bd7d77a
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": 0.0003827507017096198,
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": 50.822,
74
  "eval_steps_per_second": 25.415,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 106845796564992.0,
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": 0.0005741260525644297,
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": 50.822,
74
  "eval_steps_per_second": 25.415,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00044654248532788977,
79
+ "grad_norm": 0.36294376850128174,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.3252,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0005103342689461597,
86
+ "grad_norm": 0.3532055914402008,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.3688,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0005741260525644297,
93
+ "grad_norm": 0.2975287437438965,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.2587,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0005741260525644297,
100
+ "eval_loss": 0.3496640622615814,
101
+ "eval_runtime": 131.9733,
102
+ "eval_samples_per_second": 50.018,
103
+ "eval_steps_per_second": 25.013,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 158042740752384.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null