ardaspear commited on
Commit
44bd6c6
·
verified ·
1 Parent(s): 6a2c3c3

Training in progress, step 27, 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:cc44d30fb807194f934baa17018d2587be8833bd21c6d94bfbe68408be88674a
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1322c5212fa13becb0c7732a2399c8904439a71d0b755d4dce33796ee61f59a0
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3510b71b1abd0a9073de3f79a7a09084391d67f511e82e34350815c1b0e7a5e1
3
  size 132798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b22d7a134ec24b6c66c653e77107748266dcf4e3ccbca1335928aad5f376c7c
3
  size 132798
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03d057dd57daf31a4f83fa1f977b30587086adcd472d02db30db1ae091bd8ff0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db79c5cc5439263656db6134fa199281305040d42833f95cc5ecf73b101d7d07
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.006136537969828688,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 481.283,
74
  "eval_steps_per_second": 60.197,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 134762987520.0,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009204806954743032,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 481.283,
74
  "eval_steps_per_second": 60.197,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.007159294298133469,
79
+ "grad_norm": 0.4347454905509949,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 44.338,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.008182050626438252,
86
+ "grad_norm": 0.4440023601055145,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 44.3387,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.009204806954743032,
93
+ "grad_norm": 0.4840239882469177,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 44.341,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.009204806954743032,
100
+ "eval_loss": 11.084238052368164,
101
+ "eval_runtime": 10.1848,
102
+ "eval_samples_per_second": 485.137,
103
+ "eval_steps_per_second": 60.679,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 202144481280.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null