Best000 commited on
Commit
c74f7a0
·
verified ·
1 Parent(s): 8a6237f

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 sha256:388811f44089829ea611251171f6e0afa1c2d88f9a3141e4a46bc44e98b6b437
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26067a988666ae920c76f1db9bed31da79cd856700c46f4c56a3764cb7bbe1b8
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:415f719e167765d69e4508bf6f78d00b4ad424b818f723a78f8dcf67dc70497b
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5e59e9ebce831bce3959a231d3a7e90938989cbecc68868e5fa0c431aac666
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
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": 0.0023666305098116558,
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": 77.098,
74
  "eval_steps_per_second": 38.549,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 45041791795200.0,
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": 0.0035499457647174834,
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": 77.098,
74
  "eval_steps_per_second": 38.549,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0027610689281135983,
79
+ "grad_norm": 10.318655014038086,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.1476,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.003155507346415541,
86
+ "grad_norm": 5.208636283874512,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.3855,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0035499457647174834,
93
+ "grad_norm": 8.321920394897461,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.9613,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0035499457647174834,
100
+ "eval_loss": 0.5362862944602966,
101
+ "eval_runtime": 13.6474,
102
+ "eval_samples_per_second": 78.257,
103
+ "eval_steps_per_second": 39.128,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 67562687692800.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null