adammandic87 commited on
Commit
48d609d
·
verified ·
1 Parent(s): 2fc6881

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 sha256:2215aad23cad14b5f096533ae7ddb6c023bb789cdbc9114f88b32b5d27d7c330
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b358b0c553dce1e4c5572c4e0385d9d9c247348a241681d638a48bec9216d143
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6804096694a33dbf356cc12deaf53f08737ba844a84edb42ff4788fcfdcc9f73
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a63bfc27ed7af8b258c2640746c7aa6e4f5548d007f56f4d43f201440058fb
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3f9f40d597a7abf41ad3ecf49e11bba5a13f6731550efb96e2fa2f1ae0dfe08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4dd2959c43a2400319de9619aa75664f6053b7ca8bf12b1e8d41e00d166b414
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": 0.026030368763557483,
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": 54.503,
74
  "eval_steps_per_second": 27.532,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 75069652992000.0,
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": 0.039045553145336226,
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": 54.503,
74
  "eval_steps_per_second": 27.532,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.03036876355748373,
79
+ "grad_norm": 1.790845274925232,
80
+ "learning_rate": 0.00014,
81
+ "loss": 14.4129,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.03470715835140998,
86
+ "grad_norm": 2.659196376800537,
87
+ "learning_rate": 0.00016,
88
+ "loss": 14.8636,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.039045553145336226,
93
+ "grad_norm": 2.014044761657715,
94
+ "learning_rate": 0.00018,
95
+ "loss": 15.2331,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.039045553145336226,
100
+ "eval_loss": 3.7499704360961914,
101
+ "eval_runtime": 1.7895,
102
+ "eval_samples_per_second": 54.205,
103
+ "eval_steps_per_second": 27.382,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 114481220812800.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null