vermoney commited on
Commit
521f1f7
·
verified ·
1 Parent(s): a1f19a4

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 sha256:331467b068adbe8768d0ea7a83378b90f7a846a4352adab06dbb7c5258be71e3
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5fb791f1c1fafd0504f70d0af1a0490b2214e9dc056bf591491258e4dfe372
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88884f5eff8e8440f57be206f7f5cdf9e87f4051d3c4faa8603043401f28c549
3
  size 239892858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915e235ae025f4c2761e7840fbeb6c2355bdc302cc63a6ea2573e88922f4f5cd
3
  size 239892858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd1ebf454031a941c8766869644643e5857c05165f3942927e75947630136d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a518ffcf1704ed6bb871672d16e0ae98e928d067ab51aa37e7629c34ebaaa55a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1126813888549805,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.0010031725331360428,
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": 9.942,
90
  "eval_steps_per_second": 4.971,
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": 2791603735363584.0,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0986448526382446,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-30",
4
+ "epoch": 0.0015047587997040642,
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": 9.942,
90
  "eval_steps_per_second": 4.971,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.0010533311597928448,
95
+ "grad_norm": 0.3344358801841736,
96
+ "learning_rate": 2.8711035421746367e-05,
97
+ "loss": 1.1238,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.0012038070397632514,
102
+ "grad_norm": 0.3562895655632019,
103
+ "learning_rate": 1.3551568628929434e-05,
104
+ "loss": 1.1788,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.0012539656664200534,
109
+ "eval_loss": 1.1017963886260986,
110
+ "eval_runtime": 845.0947,
111
+ "eval_samples_per_second": 9.934,
112
+ "eval_steps_per_second": 4.967,
113
+ "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.0013542829197336578,
117
+ "grad_norm": 0.3746950328350067,
118
+ "learning_rate": 3.511175705587433e-06,
119
+ "loss": 1.1727,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.0015047587997040642,
124
+ "grad_norm": 0.38321593403816223,
125
+ "learning_rate": 0.0,
126
+ "loss": 1.2448,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.0015047587997040642,
131
+ "eval_loss": 1.0986448526382446,
132
+ "eval_runtime": 845.1473,
133
+ "eval_samples_per_second": 9.933,
134
+ "eval_steps_per_second": 4.967,
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": 4170173481222144.0,
165
  "train_batch_size": 2,
166
  "trial_name": null,
167
  "trial_params": null