brixeus commited on
Commit
26ca2d2
·
verified ·
1 Parent(s): 435e309

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 sha256:787049ebf6b4d61eba0f43e7f286d54fbdb497e76d7d355df938821fd52fff56
3
  size 25192688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d1cbdd2420b77ef31b47aa41fc368fbe7fc800bc15c4fc79e4b6dba34f7895
3
  size 25192688
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9fe16cbea6e9b0d3f949482af39db2c87fe95edb906870d9ddc25bc2f096c23
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f390a4e398dd3a26569640ce7e598af3f59eea7cac69be6f691f82125b12eafa
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f592bf86b4fd2e71efe8302e785834bcc22f802bc4e707ef42478cdb4e0a73fb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b229f45074966770145b12da34b6565744a4f0dc74eb342b733ec86a2ce1df1
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": 0.00598056316969848,
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": 22.904,
74
  "eval_steps_per_second": 2.865,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1532023491526656.0,
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": 0.00897084475454772,
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": 22.904,
74
  "eval_steps_per_second": 2.865,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.00697732369798156,
79
+ "grad_norm": 5.275881290435791,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 7.3881,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.00797408422626464,
86
+ "grad_norm": 4.454370975494385,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 7.0281,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.00897084475454772,
93
+ "grad_norm": 4.078393936157227,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 6.9298,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.00897084475454772,
100
+ "eval_loss": 1.7337881326675415,
101
+ "eval_runtime": 221.3769,
102
+ "eval_samples_per_second": 22.898,
103
+ "eval_steps_per_second": 2.864,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2244945314316288.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null