oldiday commited on
Commit
07305e8
·
verified ·
1 Parent(s): a1a8f2c

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 sha256:17921cbf8e208b02de560309bbd39110367b43a8d642d6c638c29062d011b2ab
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0851e2753a1c19f21be847c465b11e2b1e2dd2ac321c098b9131b220e9b0229a
3
  size 97307544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e1a7ad95d8f1bbe7e169d4999f5f14ce5eeba4f28406c5999f4e802084313a2
3
  size 49846260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc69dbc85174d2072d9056d630dcd065fdd05256675b63082ee057768d7abe82
3
  size 49846260
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ec14f7f6e9166b5c3b97d8df0f7d7fb1d9924e55c835bbbf7266ab7a7ff1f3e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f65646a59f5101e9f4395867ec30b54ec52d28a6f66c87a21e2e8ef9cca9012
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": 0.008334297951151754,
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": 24.817,
74
  "eval_steps_per_second": 3.104,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1.0061434545242112e+16,
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": 0.01250144692672763,
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": 24.817,
74
  "eval_steps_per_second": 3.104,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.009723347609677045,
79
+ "grad_norm": 0.49809256196022034,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 1.8012,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.011112397268202338,
86
+ "grad_norm": 0.6324176788330078,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 1.7509,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.01250144692672763,
93
+ "grad_norm": 0.539840042591095,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 1.7469,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.01250144692672763,
100
+ "eval_loss": 1.7146458625793457,
101
+ "eval_runtime": 146.5822,
102
+ "eval_samples_per_second": 24.819,
103
+ "eval_steps_per_second": 3.104,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1.5092151817863168e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null