ClarenceDan commited on
Commit
d99aeaa
·
verified ·
1 Parent(s): a45af66

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:e834d6bc45f7d8f41a25212c350fa3bab801a4c22aa81a396000fd123287fb9b
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17088b32df10f04aacc47b1b8cbb5dee8a793a4ce3174a731c8bf165207112d
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5923bdf2ec75bba510c0bff97c2d368cb78231fec74a8e3f2548af212fbd6ea
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67271076d68d8fbe24f97c345cdf9aed8a6da30e87c78ab50fbbf6444ae8b203
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bc9c4ad8c3558326425d08fc7925a9d4d280fa26469651ba5bb02a0067d8a55
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3bffcd26b2943975a328029e20bbfd16e1b4d717f0bb20bdd3c8ced03d9dc7
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": 0.0001456001456001456,
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": 57.9,
74
  "eval_steps_per_second": 28.952,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 408093327360000.0,
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": 0.0002184002184002184,
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": 57.9,
74
  "eval_steps_per_second": 28.952,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0001698668365335032,
79
+ "grad_norm": 4.765990734100342,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.1913,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0001941335274668608,
86
+ "grad_norm": 11.631158828735352,
87
+ "learning_rate": 0.00016,
88
+ "loss": 14.2611,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002184002184002184,
93
+ "grad_norm": 6.4442057609558105,
94
+ "learning_rate": 0.00018,
95
+ "loss": 11.4726,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002184002184002184,
100
+ "eval_loss": 2.878862142562866,
101
+ "eval_runtime": 299.2739,
102
+ "eval_samples_per_second": 57.977,
103
+ "eval_steps_per_second": 28.99,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 603978124492800.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null