vmpsergio commited on
Commit
dcbb4cb
·
verified ·
1 Parent(s): f9deb1a

Training in progress, step 30, 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:b07fd4ca4b40a1d776db5c0aca17e1347ab8fabdcfc14104b16ca78db241079a
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f5ce4c5b4503d896751aac2cae3886be31b8b7465be208f002f67496fde2ab
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61011cd3485e114ee310f579180055b42574257e7a48f0cc19d2646e57aac6b0
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a90c2c1be188954247e7fdfddef87956be12130619986355be51b45ec03387
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9827acb5724dcff666ad9d8e1a99fdd806027902b7bd91dbcce7886db5462728
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88aba22895962b26303ea1a36cdd5d6b81481e02cf6072eb0e06104884befc67
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.106920838356018,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.0013807148651214167,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -89,6 +89,50 @@
89
  "eval_samples_per_second": 7.251,
90
  "eval_steps_per_second": 3.626,
91
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -112,12 +156,12 @@
112
  "should_evaluate": false,
113
  "should_log": false,
114
  "should_save": true,
115
- "should_training_stop": false
116
  },
117
  "attributes": {}
118
  }
119
  },
120
- "total_flos": 7697214247796736.0,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.100005030632019,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-30",
4
+ "epoch": 0.002071072297682125,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 7.251,
90
  "eval_steps_per_second": 3.626,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.0014497506083774874,
95
+ "grad_norm": 0.7518830299377441,
96
+ "learning_rate": 8.435655349597689e-05,
97
+ "loss": 0.8878,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.0016568578381456998,
102
+ "grad_norm": 0.9861083626747131,
103
+ "learning_rate": 4.12214747707527e-05,
104
+ "loss": 1.0354,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.0017258935814017707,
109
+ "eval_loss": 1.101482629776001,
110
+ "eval_runtime": 841.5375,
111
+ "eval_samples_per_second": 7.247,
112
+ "eval_steps_per_second": 3.624,
113
+ "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.0018639650679139123,
117
+ "grad_norm": 0.7286344170570374,
118
+ "learning_rate": 1.0899347581163221e-05,
119
+ "loss": 1.2035,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.002071072297682125,
124
+ "grad_norm": 0.6946622729301453,
125
+ "learning_rate": 0.0,
126
+ "loss": 0.9832,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.002071072297682125,
131
+ "eval_loss": 1.100005030632019,
132
+ "eval_runtime": 842.0664,
133
+ "eval_samples_per_second": 7.243,
134
+ "eval_steps_per_second": 3.622,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
156
  "should_evaluate": false,
157
  "should_log": false,
158
  "should_save": true,
159
+ "should_training_stop": true
160
  },
161
  "attributes": {}
162
  }
163
  },
164
+ "total_flos": 1.1777665174339584e+16,
165
  "train_batch_size": 2,
166
  "trial_name": null,
167
  "trial_params": null