kostiantynk1205 commited on
Commit
a5ba6b5
·
verified ·
1 Parent(s): 779cd3a

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 sha256:980512ee695cc6be6c28f785540821e6ff22107bbb2abeebf3c7ea3710533e95
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e33bfde58e7d675a3002f6f0be5a1b9470b2b742d5d02bdc458c9d0b57b781
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76cd143f39ecc6ed2287102a67055e5246aef4bca1621fdc2cac79f08417abf3
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3050865d703f34c75af3fdd61a84186e35fac3e106356111a1cb1e9833fc57d4
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3834acef3f7d0460f517eef54fb9e752ced2048603b5633c411f56f883afb7c5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5364d09e27bdf541cc4080b011a0a833388b061da2ef703197275a4e77a4aa4
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": 0.0007561913164030499,
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": 50.51,
74
  "eval_steps_per_second": 25.262,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 84586255613952.0,
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": 0.001134286974604575,
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": 50.51,
74
  "eval_steps_per_second": 25.262,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.000882223202470225,
79
+ "grad_norm": 0.6224209070205688,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.9561,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0010082550885374,
86
+ "grad_norm": 0.620303213596344,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.9573,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.001134286974604575,
93
+ "grad_norm": 0.907393217086792,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.1493,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.001134286974604575,
100
+ "eval_loss": 1.0724258422851562,
101
+ "eval_runtime": 65.794,
102
+ "eval_samples_per_second": 50.78,
103
+ "eval_steps_per_second": 25.397,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 133557245706240.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null