kk-aivio commited on
Commit
6d173c0
·
verified ·
1 Parent(s): 08431f1

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:de5497f4f5f4cf4e5aa8135e9b592358395f23dc05313e741b0f50d80c3f859c
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23bf9cd944aeafcd51f99b9b886385d3a8e0fecd07d79e7c2f146b5cef0defe2
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8813c66b482d8f2aac8d972216c82b30c5f0e474bdcca3d45731cafc6b4c9a9e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7cfe52eff9ec53ecda845b26cf3ad9906436ffed504ab0932a1e98a01ca970
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:124eff5ccdba19f1c014b29d8c32c807a8d3d8b0706b00018af320ef09a3bf5e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01db2ee336282e9fa52adde814dca6a22070d1f49093cdf705c3bc6c64432f2
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": 0.00013907964047912936,
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": 18.629,
74
  "eval_steps_per_second": 9.315,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2126998885367808.0,
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": 0.00020861946071869405,
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": 18.629,
74
  "eval_steps_per_second": 9.315,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00016225958055898426,
79
+ "grad_norm": 0.7307805418968201,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.2766,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00018543952063883914,
86
+ "grad_norm": 0.3102991282939911,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.1606,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00020861946071869405,
93
+ "grad_norm": 0.4250812530517578,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.1873,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00020861946071869405,
100
+ "eval_loss": 0.22364288568496704,
101
+ "eval_runtime": 975.2905,
102
+ "eval_samples_per_second": 18.625,
103
+ "eval_steps_per_second": 9.313,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3190498328051712.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null