ClarenceDan commited on
Commit
4677692
·
verified ·
1 Parent(s): 63e9f19

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 sha256:0008497c916c297f1ebd6bd74439f518a68a665eb78eefeb0b102ca0eafb72e1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789949f60fb904f74bdea66ac9eda7e49f5bfce5b6b490fb308e8c6bf3055a14
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6497fd39d4d02b0308ed4d495d9a3c4d06c518aed89b1a27bc3553b9560bbb7
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521fbb10077b1cd14e46ed474c521831345fe7c2e0b701d202aea8e9d30e5f02
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:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df342e12f5c8177b234bccf3ed8fd60c478a1873dba9a7db1e26b1f1caf1d1fa
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": 0.00028267552383308013,
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": 28.794,
74
  "eval_steps_per_second": 14.397,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109738548887552.0,
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": 0.00042401328574962014,
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": 28.794,
74
  "eval_steps_per_second": 14.397,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00032978811113859347,
79
+ "grad_norm": 1.233701229095459,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.0872,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003769006984441068,
86
+ "grad_norm": 1.4318066835403442,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.1394,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00042401328574962014,
93
+ "grad_norm": 1.458452820777893,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.783,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00042401328574962014,
100
+ "eval_loss": 1.9945000410079956,
101
+ "eval_runtime": 310.4496,
102
+ "eval_samples_per_second": 28.791,
103
+ "eval_steps_per_second": 14.395,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1757086035738624.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null