ClarenceDan commited on
Commit
7535185
·
verified ·
1 Parent(s): 7fbd6ee

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 sha256:03d8a3c134fe14f7c8643e815a0ef6323b32d96309c66dba6563229f232b4dcd
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84d04512c0da1ebca248ab8e17978b6c7333a0acd8b4d1fc63a6cb0a780eb88
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff0e6af66f41afd530ac1918451cc8c7dc68ced60a55d9fb163e95a0380e15a1
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45292e773b689a2e7361f51e274c06b805c5fb568aaadef12c613596aa600903
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3253e1657e0e5e1dce4606e0080d6574b33a3e708581e44bc5526ab5260da9
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": 0.0017599178704993767,
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": 19.992,
74
  "eval_steps_per_second": 9.996,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1231436170395648.0,
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": 0.002639876805749065,
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": 19.992,
74
  "eval_steps_per_second": 9.996,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002053237515582606,
79
+ "grad_norm": 1.442993402481079,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.5645,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0023465571606658357,
86
+ "grad_norm": 1.2980412244796753,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.4136,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002639876805749065,
93
+ "grad_norm": 0.9257961511611938,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2589,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002639876805749065,
100
+ "eval_loss": 1.2421820163726807,
101
+ "eval_runtime": 71.8958,
102
+ "eval_samples_per_second": 19.973,
103
+ "eval_steps_per_second": 9.987,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1847154255593472.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null