Training in progress, step 20, 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:
|
3 |
size 17640136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fdc23f1213146453a075053e93bc4cbc4caf0d1904286b8e30e0dbf5b4795b1
|
3 |
size 17640136
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9568884
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3386e4d9cbb35b7a15e6a94f035e296499d252beb243cb2aa31b83947ceb5d8
|
3 |
size 9568884
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ddb7b575b177a0f4a3c1bf5ad5c41eb95c3cd6853ac85a61ebf5719b0e442ff
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -101,6 +101,92 @@
|
|
101 |
"eval_samples_per_second": 6.647,
|
102 |
"eval_steps_per_second": 3.324,
|
103 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
}
|
105 |
],
|
106 |
"logging_steps": 1,
|
@@ -129,7 +215,7 @@
|
|
129 |
"attributes": {}
|
130 |
}
|
131 |
},
|
132 |
-
"total_flos":
|
133 |
"train_batch_size": 2,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.443589687347412,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-20",
|
4 |
+
"epoch": 0.023682652457075192,
|
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,
|
|
|
101 |
"eval_samples_per_second": 6.647,
|
102 |
"eval_steps_per_second": 3.324,
|
103 |
"step": 10
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.013025458851391355,
|
107 |
+
"grad_norm": 0.9684340357780457,
|
108 |
+
"learning_rate": 0.00019781476007338058,
|
109 |
+
"loss": 1.9317,
|
110 |
+
"step": 11
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.014209591474245116,
|
114 |
+
"grad_norm": 1.5347967147827148,
|
115 |
+
"learning_rate": 0.0001913545457642601,
|
116 |
+
"loss": 2.2451,
|
117 |
+
"step": 12
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.015393724097098875,
|
121 |
+
"grad_norm": 0.6658350825309753,
|
122 |
+
"learning_rate": 0.00018090169943749476,
|
123 |
+
"loss": 1.1592,
|
124 |
+
"step": 13
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.016577856719952634,
|
128 |
+
"grad_norm": 0.5862579345703125,
|
129 |
+
"learning_rate": 0.00016691306063588583,
|
130 |
+
"loss": 1.0437,
|
131 |
+
"step": 14
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.017761989342806393,
|
135 |
+
"grad_norm": 0.8402700424194336,
|
136 |
+
"learning_rate": 0.00015000000000000001,
|
137 |
+
"loss": 1.6701,
|
138 |
+
"step": 15
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 0.017761989342806393,
|
142 |
+
"eval_loss": 1.4690113067626953,
|
143 |
+
"eval_runtime": 58.5466,
|
144 |
+
"eval_samples_per_second": 6.081,
|
145 |
+
"eval_steps_per_second": 3.04,
|
146 |
+
"step": 15
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.018946121965660152,
|
150 |
+
"grad_norm": 1.071670413017273,
|
151 |
+
"learning_rate": 0.00013090169943749476,
|
152 |
+
"loss": 1.7594,
|
153 |
+
"step": 16
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.020130254588513915,
|
157 |
+
"grad_norm": 1.167551040649414,
|
158 |
+
"learning_rate": 0.00011045284632676536,
|
159 |
+
"loss": 1.8349,
|
160 |
+
"step": 17
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.021314387211367674,
|
164 |
+
"grad_norm": 0.730896532535553,
|
165 |
+
"learning_rate": 8.954715367323468e-05,
|
166 |
+
"loss": 1.137,
|
167 |
+
"step": 18
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.022498519834221433,
|
171 |
+
"grad_norm": 0.7160881757736206,
|
172 |
+
"learning_rate": 6.909830056250527e-05,
|
173 |
+
"loss": 1.7813,
|
174 |
+
"step": 19
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.023682652457075192,
|
178 |
+
"grad_norm": 0.6176623106002808,
|
179 |
+
"learning_rate": 5.000000000000002e-05,
|
180 |
+
"loss": 0.993,
|
181 |
+
"step": 20
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.023682652457075192,
|
185 |
+
"eval_loss": 1.443589687347412,
|
186 |
+
"eval_runtime": 55.9559,
|
187 |
+
"eval_samples_per_second": 6.362,
|
188 |
+
"eval_steps_per_second": 3.181,
|
189 |
+
"step": 20
|
190 |
}
|
191 |
],
|
192 |
"logging_steps": 1,
|
|
|
215 |
"attributes": {}
|
216 |
}
|
217 |
},
|
218 |
+
"total_flos": 276018307792896.0,
|
219 |
"train_batch_size": 2,
|
220 |
"trial_name": null,
|
221 |
"trial_params": null
|