Training in progress, step 9000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 613004648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8adc247d305d9f3f48cfa3878ee63336d7fa4374add45ee01ed8dda6005ec778
|
| 3 |
size 613004648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1226096954
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8859d669a35bcbc93780c06ab1a65bd8bc02a7cba417a0b1747229bae278e8c4
|
| 3 |
size 1226096954
|
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 sha256:8b9b5cbeb72cb13416d33fb3709b0d7a367e681de773132f1b73f6b02bba3582
|
| 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 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb70058e5fda25192fd22654de739fc2dcf9d8d64b5fc7673d822670c95ff92
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -6119,6 +6119,770 @@
|
|
| 6119 |
"eval_spearman_manhattan": 0.7707235385401614,
|
| 6120 |
"eval_steps_per_second": 37.072,
|
| 6121 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6122 |
}
|
| 6123 |
],
|
| 6124 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.217432052483598,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 6119 |
"eval_spearman_manhattan": 0.7707235385401614,
|
| 6120 |
"eval_steps_per_second": 37.072,
|
| 6121 |
"step": 8000
|
| 6122 |
+
},
|
| 6123 |
+
{
|
| 6124 |
+
"epoch": 3.753514526710403,
|
| 6125 |
+
"grad_norm": 3.368011713027954,
|
| 6126 |
+
"learning_rate": 9.530810684161201e-06,
|
| 6127 |
+
"loss": 0.2193,
|
| 6128 |
+
"step": 8010
|
| 6129 |
+
},
|
| 6130 |
+
{
|
| 6131 |
+
"epoch": 3.758200562324274,
|
| 6132 |
+
"grad_norm": 2.9850523471832275,
|
| 6133 |
+
"learning_rate": 9.530224929709466e-06,
|
| 6134 |
+
"loss": 0.2016,
|
| 6135 |
+
"step": 8020
|
| 6136 |
+
},
|
| 6137 |
+
{
|
| 6138 |
+
"epoch": 3.7628865979381443,
|
| 6139 |
+
"grad_norm": 2.8147449493408203,
|
| 6140 |
+
"learning_rate": 9.529639175257731e-06,
|
| 6141 |
+
"loss": 0.2215,
|
| 6142 |
+
"step": 8030
|
| 6143 |
+
},
|
| 6144 |
+
{
|
| 6145 |
+
"epoch": 3.7675726335520148,
|
| 6146 |
+
"grad_norm": 2.6306607723236084,
|
| 6147 |
+
"learning_rate": 9.529053420806e-06,
|
| 6148 |
+
"loss": 0.2015,
|
| 6149 |
+
"step": 8040
|
| 6150 |
+
},
|
| 6151 |
+
{
|
| 6152 |
+
"epoch": 3.7722586691658857,
|
| 6153 |
+
"grad_norm": 2.9150195121765137,
|
| 6154 |
+
"learning_rate": 9.528467666354265e-06,
|
| 6155 |
+
"loss": 0.2181,
|
| 6156 |
+
"step": 8050
|
| 6157 |
+
},
|
| 6158 |
+
{
|
| 6159 |
+
"epoch": 3.776944704779756,
|
| 6160 |
+
"grad_norm": 2.7011146545410156,
|
| 6161 |
+
"learning_rate": 9.52788191190253e-06,
|
| 6162 |
+
"loss": 0.2087,
|
| 6163 |
+
"step": 8060
|
| 6164 |
+
},
|
| 6165 |
+
{
|
| 6166 |
+
"epoch": 3.781630740393627,
|
| 6167 |
+
"grad_norm": 2.658383846282959,
|
| 6168 |
+
"learning_rate": 9.527296157450797e-06,
|
| 6169 |
+
"loss": 0.2274,
|
| 6170 |
+
"step": 8070
|
| 6171 |
+
},
|
| 6172 |
+
{
|
| 6173 |
+
"epoch": 3.7863167760074976,
|
| 6174 |
+
"grad_norm": 3.214911460876465,
|
| 6175 |
+
"learning_rate": 9.526710402999063e-06,
|
| 6176 |
+
"loss": 0.2062,
|
| 6177 |
+
"step": 8080
|
| 6178 |
+
},
|
| 6179 |
+
{
|
| 6180 |
+
"epoch": 3.791002811621368,
|
| 6181 |
+
"grad_norm": 2.258542537689209,
|
| 6182 |
+
"learning_rate": 9.52612464854733e-06,
|
| 6183 |
+
"loss": 0.1993,
|
| 6184 |
+
"step": 8090
|
| 6185 |
+
},
|
| 6186 |
+
{
|
| 6187 |
+
"epoch": 3.795688847235239,
|
| 6188 |
+
"grad_norm": 2.8734090328216553,
|
| 6189 |
+
"learning_rate": 9.525538894095597e-06,
|
| 6190 |
+
"loss": 0.1992,
|
| 6191 |
+
"step": 8100
|
| 6192 |
+
},
|
| 6193 |
+
{
|
| 6194 |
+
"epoch": 3.8003748828491095,
|
| 6195 |
+
"grad_norm": 2.079141616821289,
|
| 6196 |
+
"learning_rate": 9.524953139643862e-06,
|
| 6197 |
+
"loss": 0.1942,
|
| 6198 |
+
"step": 8110
|
| 6199 |
+
},
|
| 6200 |
+
{
|
| 6201 |
+
"epoch": 3.8050609184629804,
|
| 6202 |
+
"grad_norm": 2.8030195236206055,
|
| 6203 |
+
"learning_rate": 9.524367385192129e-06,
|
| 6204 |
+
"loss": 0.2289,
|
| 6205 |
+
"step": 8120
|
| 6206 |
+
},
|
| 6207 |
+
{
|
| 6208 |
+
"epoch": 3.809746954076851,
|
| 6209 |
+
"grad_norm": 3.562373399734497,
|
| 6210 |
+
"learning_rate": 9.523781630740394e-06,
|
| 6211 |
+
"loss": 0.2177,
|
| 6212 |
+
"step": 8130
|
| 6213 |
+
},
|
| 6214 |
+
{
|
| 6215 |
+
"epoch": 3.8144329896907214,
|
| 6216 |
+
"grad_norm": 3.045858144760132,
|
| 6217 |
+
"learning_rate": 9.52319587628866e-06,
|
| 6218 |
+
"loss": 0.1953,
|
| 6219 |
+
"step": 8140
|
| 6220 |
+
},
|
| 6221 |
+
{
|
| 6222 |
+
"epoch": 3.8191190253045924,
|
| 6223 |
+
"grad_norm": 1.9901701211929321,
|
| 6224 |
+
"learning_rate": 9.522610121836928e-06,
|
| 6225 |
+
"loss": 0.1873,
|
| 6226 |
+
"step": 8150
|
| 6227 |
+
},
|
| 6228 |
+
{
|
| 6229 |
+
"epoch": 3.823805060918463,
|
| 6230 |
+
"grad_norm": 3.8275070190429688,
|
| 6231 |
+
"learning_rate": 9.522024367385193e-06,
|
| 6232 |
+
"loss": 0.2081,
|
| 6233 |
+
"step": 8160
|
| 6234 |
+
},
|
| 6235 |
+
{
|
| 6236 |
+
"epoch": 3.8284910965323338,
|
| 6237 |
+
"grad_norm": 3.9077577590942383,
|
| 6238 |
+
"learning_rate": 9.52143861293346e-06,
|
| 6239 |
+
"loss": 0.2145,
|
| 6240 |
+
"step": 8170
|
| 6241 |
+
},
|
| 6242 |
+
{
|
| 6243 |
+
"epoch": 3.8331771321462043,
|
| 6244 |
+
"grad_norm": 2.799581289291382,
|
| 6245 |
+
"learning_rate": 9.520852858481725e-06,
|
| 6246 |
+
"loss": 0.2139,
|
| 6247 |
+
"step": 8180
|
| 6248 |
+
},
|
| 6249 |
+
{
|
| 6250 |
+
"epoch": 3.8378631677600747,
|
| 6251 |
+
"grad_norm": 2.7552547454833984,
|
| 6252 |
+
"learning_rate": 9.52026710402999e-06,
|
| 6253 |
+
"loss": 0.236,
|
| 6254 |
+
"step": 8190
|
| 6255 |
+
},
|
| 6256 |
+
{
|
| 6257 |
+
"epoch": 3.8425492033739457,
|
| 6258 |
+
"grad_norm": 2.6394495964050293,
|
| 6259 |
+
"learning_rate": 9.519681349578259e-06,
|
| 6260 |
+
"loss": 0.1724,
|
| 6261 |
+
"step": 8200
|
| 6262 |
+
},
|
| 6263 |
+
{
|
| 6264 |
+
"epoch": 3.847235238987816,
|
| 6265 |
+
"grad_norm": 2.702173948287964,
|
| 6266 |
+
"learning_rate": 9.519095595126524e-06,
|
| 6267 |
+
"loss": 0.1896,
|
| 6268 |
+
"step": 8210
|
| 6269 |
+
},
|
| 6270 |
+
{
|
| 6271 |
+
"epoch": 3.851921274601687,
|
| 6272 |
+
"grad_norm": 2.436673402786255,
|
| 6273 |
+
"learning_rate": 9.51850984067479e-06,
|
| 6274 |
+
"loss": 0.2018,
|
| 6275 |
+
"step": 8220
|
| 6276 |
+
},
|
| 6277 |
+
{
|
| 6278 |
+
"epoch": 3.8566073102155576,
|
| 6279 |
+
"grad_norm": 2.3034989833831787,
|
| 6280 |
+
"learning_rate": 9.517924086223056e-06,
|
| 6281 |
+
"loss": 0.1939,
|
| 6282 |
+
"step": 8230
|
| 6283 |
+
},
|
| 6284 |
+
{
|
| 6285 |
+
"epoch": 3.861293345829428,
|
| 6286 |
+
"grad_norm": 3.2450108528137207,
|
| 6287 |
+
"learning_rate": 9.517338331771321e-06,
|
| 6288 |
+
"loss": 0.209,
|
| 6289 |
+
"step": 8240
|
| 6290 |
+
},
|
| 6291 |
+
{
|
| 6292 |
+
"epoch": 3.865979381443299,
|
| 6293 |
+
"grad_norm": 2.502262830734253,
|
| 6294 |
+
"learning_rate": 9.516752577319588e-06,
|
| 6295 |
+
"loss": 0.1783,
|
| 6296 |
+
"step": 8250
|
| 6297 |
+
},
|
| 6298 |
+
{
|
| 6299 |
+
"epoch": 3.865979381443299,
|
| 6300 |
+
"eval_loss": 0.049117717891931534,
|
| 6301 |
+
"eval_pearson_cosine": 0.7772195489479836,
|
| 6302 |
+
"eval_pearson_dot": 0.5914535101164233,
|
| 6303 |
+
"eval_pearson_euclidean": 0.7459002868961946,
|
| 6304 |
+
"eval_pearson_manhattan": 0.7454618646316931,
|
| 6305 |
+
"eval_runtime": 39.5982,
|
| 6306 |
+
"eval_samples_per_second": 37.881,
|
| 6307 |
+
"eval_spearman_cosine": 0.7829045810141201,
|
| 6308 |
+
"eval_spearman_dot": 0.5984134337824631,
|
| 6309 |
+
"eval_spearman_euclidean": 0.7637144641585795,
|
| 6310 |
+
"eval_spearman_manhattan": 0.7630402590525859,
|
| 6311 |
+
"eval_steps_per_second": 37.881,
|
| 6312 |
+
"step": 8250
|
| 6313 |
+
},
|
| 6314 |
+
{
|
| 6315 |
+
"epoch": 3.8706654170571695,
|
| 6316 |
+
"grad_norm": 2.68709397315979,
|
| 6317 |
+
"learning_rate": 9.516166822867855e-06,
|
| 6318 |
+
"loss": 0.2099,
|
| 6319 |
+
"step": 8260
|
| 6320 |
+
},
|
| 6321 |
+
{
|
| 6322 |
+
"epoch": 3.8753514526710404,
|
| 6323 |
+
"grad_norm": 2.731020927429199,
|
| 6324 |
+
"learning_rate": 9.51558106841612e-06,
|
| 6325 |
+
"loss": 0.2032,
|
| 6326 |
+
"step": 8270
|
| 6327 |
+
},
|
| 6328 |
+
{
|
| 6329 |
+
"epoch": 3.880037488284911,
|
| 6330 |
+
"grad_norm": 2.9886014461517334,
|
| 6331 |
+
"learning_rate": 9.514995313964387e-06,
|
| 6332 |
+
"loss": 0.2206,
|
| 6333 |
+
"step": 8280
|
| 6334 |
+
},
|
| 6335 |
+
{
|
| 6336 |
+
"epoch": 3.8847235238987814,
|
| 6337 |
+
"grad_norm": 3.2847719192504883,
|
| 6338 |
+
"learning_rate": 9.514409559512653e-06,
|
| 6339 |
+
"loss": 0.2006,
|
| 6340 |
+
"step": 8290
|
| 6341 |
+
},
|
| 6342 |
+
{
|
| 6343 |
+
"epoch": 3.8894095595126523,
|
| 6344 |
+
"grad_norm": 2.6451122760772705,
|
| 6345 |
+
"learning_rate": 9.51382380506092e-06,
|
| 6346 |
+
"loss": 0.197,
|
| 6347 |
+
"step": 8300
|
| 6348 |
+
},
|
| 6349 |
+
{
|
| 6350 |
+
"epoch": 3.894095595126523,
|
| 6351 |
+
"grad_norm": 2.8909411430358887,
|
| 6352 |
+
"learning_rate": 9.513238050609187e-06,
|
| 6353 |
+
"loss": 0.2122,
|
| 6354 |
+
"step": 8310
|
| 6355 |
+
},
|
| 6356 |
+
{
|
| 6357 |
+
"epoch": 3.8987816307403937,
|
| 6358 |
+
"grad_norm": 2.6058146953582764,
|
| 6359 |
+
"learning_rate": 9.512652296157452e-06,
|
| 6360 |
+
"loss": 0.1812,
|
| 6361 |
+
"step": 8320
|
| 6362 |
+
},
|
| 6363 |
+
{
|
| 6364 |
+
"epoch": 3.9034676663542642,
|
| 6365 |
+
"grad_norm": 2.27011775970459,
|
| 6366 |
+
"learning_rate": 9.512066541705719e-06,
|
| 6367 |
+
"loss": 0.2184,
|
| 6368 |
+
"step": 8330
|
| 6369 |
+
},
|
| 6370 |
+
{
|
| 6371 |
+
"epoch": 3.9081537019681347,
|
| 6372 |
+
"grad_norm": 3.1832330226898193,
|
| 6373 |
+
"learning_rate": 9.511480787253984e-06,
|
| 6374 |
+
"loss": 0.2016,
|
| 6375 |
+
"step": 8340
|
| 6376 |
+
},
|
| 6377 |
+
{
|
| 6378 |
+
"epoch": 3.9128397375820057,
|
| 6379 |
+
"grad_norm": 2.791018009185791,
|
| 6380 |
+
"learning_rate": 9.510895032802249e-06,
|
| 6381 |
+
"loss": 0.215,
|
| 6382 |
+
"step": 8350
|
| 6383 |
+
},
|
| 6384 |
+
{
|
| 6385 |
+
"epoch": 3.917525773195876,
|
| 6386 |
+
"grad_norm": 2.7976248264312744,
|
| 6387 |
+
"learning_rate": 9.510309278350516e-06,
|
| 6388 |
+
"loss": 0.1905,
|
| 6389 |
+
"step": 8360
|
| 6390 |
+
},
|
| 6391 |
+
{
|
| 6392 |
+
"epoch": 3.922211808809747,
|
| 6393 |
+
"grad_norm": 3.055813789367676,
|
| 6394 |
+
"learning_rate": 9.509723523898783e-06,
|
| 6395 |
+
"loss": 0.1749,
|
| 6396 |
+
"step": 8370
|
| 6397 |
+
},
|
| 6398 |
+
{
|
| 6399 |
+
"epoch": 3.9268978444236176,
|
| 6400 |
+
"grad_norm": 2.684330940246582,
|
| 6401 |
+
"learning_rate": 9.509137769447048e-06,
|
| 6402 |
+
"loss": 0.2205,
|
| 6403 |
+
"step": 8380
|
| 6404 |
+
},
|
| 6405 |
+
{
|
| 6406 |
+
"epoch": 3.931583880037488,
|
| 6407 |
+
"grad_norm": 2.509272336959839,
|
| 6408 |
+
"learning_rate": 9.508552014995315e-06,
|
| 6409 |
+
"loss": 0.1996,
|
| 6410 |
+
"step": 8390
|
| 6411 |
+
},
|
| 6412 |
+
{
|
| 6413 |
+
"epoch": 3.936269915651359,
|
| 6414 |
+
"grad_norm": 3.171687126159668,
|
| 6415 |
+
"learning_rate": 9.50796626054358e-06,
|
| 6416 |
+
"loss": 0.2153,
|
| 6417 |
+
"step": 8400
|
| 6418 |
+
},
|
| 6419 |
+
{
|
| 6420 |
+
"epoch": 3.9409559512652295,
|
| 6421 |
+
"grad_norm": 2.5855712890625,
|
| 6422 |
+
"learning_rate": 9.507380506091847e-06,
|
| 6423 |
+
"loss": 0.1948,
|
| 6424 |
+
"step": 8410
|
| 6425 |
+
},
|
| 6426 |
+
{
|
| 6427 |
+
"epoch": 3.9456419868791004,
|
| 6428 |
+
"grad_norm": 2.6451563835144043,
|
| 6429 |
+
"learning_rate": 9.506794751640114e-06,
|
| 6430 |
+
"loss": 0.2016,
|
| 6431 |
+
"step": 8420
|
| 6432 |
+
},
|
| 6433 |
+
{
|
| 6434 |
+
"epoch": 3.950328022492971,
|
| 6435 |
+
"grad_norm": 2.763460159301758,
|
| 6436 |
+
"learning_rate": 9.50620899718838e-06,
|
| 6437 |
+
"loss": 0.1993,
|
| 6438 |
+
"step": 8430
|
| 6439 |
+
},
|
| 6440 |
+
{
|
| 6441 |
+
"epoch": 3.9550140581068414,
|
| 6442 |
+
"grad_norm": 2.799182891845703,
|
| 6443 |
+
"learning_rate": 9.505623242736646e-06,
|
| 6444 |
+
"loss": 0.2042,
|
| 6445 |
+
"step": 8440
|
| 6446 |
+
},
|
| 6447 |
+
{
|
| 6448 |
+
"epoch": 3.9597000937207123,
|
| 6449 |
+
"grad_norm": 3.084116220474243,
|
| 6450 |
+
"learning_rate": 9.505037488284911e-06,
|
| 6451 |
+
"loss": 0.1866,
|
| 6452 |
+
"step": 8450
|
| 6453 |
+
},
|
| 6454 |
+
{
|
| 6455 |
+
"epoch": 3.964386129334583,
|
| 6456 |
+
"grad_norm": 3.3838253021240234,
|
| 6457 |
+
"learning_rate": 9.504451733833178e-06,
|
| 6458 |
+
"loss": 0.1707,
|
| 6459 |
+
"step": 8460
|
| 6460 |
+
},
|
| 6461 |
+
{
|
| 6462 |
+
"epoch": 3.9690721649484537,
|
| 6463 |
+
"grad_norm": 2.19954776763916,
|
| 6464 |
+
"learning_rate": 9.503865979381444e-06,
|
| 6465 |
+
"loss": 0.2248,
|
| 6466 |
+
"step": 8470
|
| 6467 |
+
},
|
| 6468 |
+
{
|
| 6469 |
+
"epoch": 3.973758200562324,
|
| 6470 |
+
"grad_norm": 2.2361807823181152,
|
| 6471 |
+
"learning_rate": 9.50328022492971e-06,
|
| 6472 |
+
"loss": 0.1799,
|
| 6473 |
+
"step": 8480
|
| 6474 |
+
},
|
| 6475 |
+
{
|
| 6476 |
+
"epoch": 3.9784442361761947,
|
| 6477 |
+
"grad_norm": 2.890557050704956,
|
| 6478 |
+
"learning_rate": 9.502694470477977e-06,
|
| 6479 |
+
"loss": 0.1973,
|
| 6480 |
+
"step": 8490
|
| 6481 |
+
},
|
| 6482 |
+
{
|
| 6483 |
+
"epoch": 3.9831302717900656,
|
| 6484 |
+
"grad_norm": 2.7707271575927734,
|
| 6485 |
+
"learning_rate": 9.502108716026243e-06,
|
| 6486 |
+
"loss": 0.2055,
|
| 6487 |
+
"step": 8500
|
| 6488 |
+
},
|
| 6489 |
+
{
|
| 6490 |
+
"epoch": 3.9831302717900656,
|
| 6491 |
+
"eval_loss": 0.05037970840930939,
|
| 6492 |
+
"eval_pearson_cosine": 0.7775524083612311,
|
| 6493 |
+
"eval_pearson_dot": 0.5959320587932737,
|
| 6494 |
+
"eval_pearson_euclidean": 0.7480333124520797,
|
| 6495 |
+
"eval_pearson_manhattan": 0.7476197144949026,
|
| 6496 |
+
"eval_runtime": 40.1455,
|
| 6497 |
+
"eval_samples_per_second": 37.364,
|
| 6498 |
+
"eval_spearman_cosine": 0.7831727093187573,
|
| 6499 |
+
"eval_spearman_dot": 0.6016926673738828,
|
| 6500 |
+
"eval_spearman_euclidean": 0.7661681011355215,
|
| 6501 |
+
"eval_spearman_manhattan": 0.7658464354262474,
|
| 6502 |
+
"eval_steps_per_second": 37.364,
|
| 6503 |
+
"step": 8500
|
| 6504 |
+
},
|
| 6505 |
+
{
|
| 6506 |
+
"epoch": 3.987816307403936,
|
| 6507 |
+
"grad_norm": 2.6210579872131348,
|
| 6508 |
+
"learning_rate": 9.501522961574508e-06,
|
| 6509 |
+
"loss": 0.2097,
|
| 6510 |
+
"step": 8510
|
| 6511 |
+
},
|
| 6512 |
+
{
|
| 6513 |
+
"epoch": 3.992502343017807,
|
| 6514 |
+
"grad_norm": 2.6655242443084717,
|
| 6515 |
+
"learning_rate": 9.500937207122775e-06,
|
| 6516 |
+
"loss": 0.2149,
|
| 6517 |
+
"step": 8520
|
| 6518 |
+
},
|
| 6519 |
+
{
|
| 6520 |
+
"epoch": 3.9971883786316775,
|
| 6521 |
+
"grad_norm": 2.6789777278900146,
|
| 6522 |
+
"learning_rate": 9.50035145267104e-06,
|
| 6523 |
+
"loss": 0.2045,
|
| 6524 |
+
"step": 8530
|
| 6525 |
+
},
|
| 6526 |
+
{
|
| 6527 |
+
"epoch": 4.001874414245548,
|
| 6528 |
+
"grad_norm": 2.4452877044677734,
|
| 6529 |
+
"learning_rate": 9.499765698219307e-06,
|
| 6530 |
+
"loss": 0.1679,
|
| 6531 |
+
"step": 8540
|
| 6532 |
+
},
|
| 6533 |
+
{
|
| 6534 |
+
"epoch": 4.0065604498594185,
|
| 6535 |
+
"grad_norm": 2.454794406890869,
|
| 6536 |
+
"learning_rate": 9.499179943767574e-06,
|
| 6537 |
+
"loss": 0.1334,
|
| 6538 |
+
"step": 8550
|
| 6539 |
+
},
|
| 6540 |
+
{
|
| 6541 |
+
"epoch": 4.01124648547329,
|
| 6542 |
+
"grad_norm": 2.799318790435791,
|
| 6543 |
+
"learning_rate": 9.498594189315839e-06,
|
| 6544 |
+
"loss": 0.1677,
|
| 6545 |
+
"step": 8560
|
| 6546 |
+
},
|
| 6547 |
+
{
|
| 6548 |
+
"epoch": 4.01593252108716,
|
| 6549 |
+
"grad_norm": 2.66549015045166,
|
| 6550 |
+
"learning_rate": 9.498008434864106e-06,
|
| 6551 |
+
"loss": 0.1337,
|
| 6552 |
+
"step": 8570
|
| 6553 |
+
},
|
| 6554 |
+
{
|
| 6555 |
+
"epoch": 4.020618556701031,
|
| 6556 |
+
"grad_norm": 2.5295207500457764,
|
| 6557 |
+
"learning_rate": 9.497422680412371e-06,
|
| 6558 |
+
"loss": 0.1396,
|
| 6559 |
+
"step": 8580
|
| 6560 |
+
},
|
| 6561 |
+
{
|
| 6562 |
+
"epoch": 4.025304592314901,
|
| 6563 |
+
"grad_norm": 1.6832513809204102,
|
| 6564 |
+
"learning_rate": 9.496836925960638e-06,
|
| 6565 |
+
"loss": 0.1628,
|
| 6566 |
+
"step": 8590
|
| 6567 |
+
},
|
| 6568 |
+
{
|
| 6569 |
+
"epoch": 4.029990627928772,
|
| 6570 |
+
"grad_norm": 2.8461272716522217,
|
| 6571 |
+
"learning_rate": 9.496251171508905e-06,
|
| 6572 |
+
"loss": 0.1558,
|
| 6573 |
+
"step": 8600
|
| 6574 |
+
},
|
| 6575 |
+
{
|
| 6576 |
+
"epoch": 4.034676663542643,
|
| 6577 |
+
"grad_norm": 1.970751404762268,
|
| 6578 |
+
"learning_rate": 9.49566541705717e-06,
|
| 6579 |
+
"loss": 0.1166,
|
| 6580 |
+
"step": 8610
|
| 6581 |
+
},
|
| 6582 |
+
{
|
| 6583 |
+
"epoch": 4.039362699156514,
|
| 6584 |
+
"grad_norm": 2.8301377296447754,
|
| 6585 |
+
"learning_rate": 9.495079662605437e-06,
|
| 6586 |
+
"loss": 0.1616,
|
| 6587 |
+
"step": 8620
|
| 6588 |
+
},
|
| 6589 |
+
{
|
| 6590 |
+
"epoch": 4.044048734770384,
|
| 6591 |
+
"grad_norm": 2.252061367034912,
|
| 6592 |
+
"learning_rate": 9.494493908153702e-06,
|
| 6593 |
+
"loss": 0.1331,
|
| 6594 |
+
"step": 8630
|
| 6595 |
+
},
|
| 6596 |
+
{
|
| 6597 |
+
"epoch": 4.048734770384255,
|
| 6598 |
+
"grad_norm": 2.675797700881958,
|
| 6599 |
+
"learning_rate": 9.493908153701968e-06,
|
| 6600 |
+
"loss": 0.1256,
|
| 6601 |
+
"step": 8640
|
| 6602 |
+
},
|
| 6603 |
+
{
|
| 6604 |
+
"epoch": 4.053420805998125,
|
| 6605 |
+
"grad_norm": 2.7920572757720947,
|
| 6606 |
+
"learning_rate": 9.493322399250236e-06,
|
| 6607 |
+
"loss": 0.1327,
|
| 6608 |
+
"step": 8650
|
| 6609 |
+
},
|
| 6610 |
+
{
|
| 6611 |
+
"epoch": 4.0581068416119965,
|
| 6612 |
+
"grad_norm": 2.8503355979919434,
|
| 6613 |
+
"learning_rate": 9.492736644798501e-06,
|
| 6614 |
+
"loss": 0.141,
|
| 6615 |
+
"step": 8660
|
| 6616 |
+
},
|
| 6617 |
+
{
|
| 6618 |
+
"epoch": 4.062792877225867,
|
| 6619 |
+
"grad_norm": 3.100353956222534,
|
| 6620 |
+
"learning_rate": 9.492150890346767e-06,
|
| 6621 |
+
"loss": 0.1501,
|
| 6622 |
+
"step": 8670
|
| 6623 |
+
},
|
| 6624 |
+
{
|
| 6625 |
+
"epoch": 4.0674789128397375,
|
| 6626 |
+
"grad_norm": 2.2261886596679688,
|
| 6627 |
+
"learning_rate": 9.491565135895034e-06,
|
| 6628 |
+
"loss": 0.1352,
|
| 6629 |
+
"step": 8680
|
| 6630 |
+
},
|
| 6631 |
+
{
|
| 6632 |
+
"epoch": 4.072164948453608,
|
| 6633 |
+
"grad_norm": 2.125128984451294,
|
| 6634 |
+
"learning_rate": 9.490979381443299e-06,
|
| 6635 |
+
"loss": 0.1541,
|
| 6636 |
+
"step": 8690
|
| 6637 |
+
},
|
| 6638 |
+
{
|
| 6639 |
+
"epoch": 4.0768509840674785,
|
| 6640 |
+
"grad_norm": 2.3368821144104004,
|
| 6641 |
+
"learning_rate": 9.490393626991566e-06,
|
| 6642 |
+
"loss": 0.144,
|
| 6643 |
+
"step": 8700
|
| 6644 |
+
},
|
| 6645 |
+
{
|
| 6646 |
+
"epoch": 4.08153701968135,
|
| 6647 |
+
"grad_norm": 2.3971216678619385,
|
| 6648 |
+
"learning_rate": 9.489807872539833e-06,
|
| 6649 |
+
"loss": 0.1461,
|
| 6650 |
+
"step": 8710
|
| 6651 |
+
},
|
| 6652 |
+
{
|
| 6653 |
+
"epoch": 4.08622305529522,
|
| 6654 |
+
"grad_norm": 2.2589287757873535,
|
| 6655 |
+
"learning_rate": 9.489222118088098e-06,
|
| 6656 |
+
"loss": 0.1758,
|
| 6657 |
+
"step": 8720
|
| 6658 |
+
},
|
| 6659 |
+
{
|
| 6660 |
+
"epoch": 4.090909090909091,
|
| 6661 |
+
"grad_norm": 2.8072731494903564,
|
| 6662 |
+
"learning_rate": 9.488636363636365e-06,
|
| 6663 |
+
"loss": 0.1454,
|
| 6664 |
+
"step": 8730
|
| 6665 |
+
},
|
| 6666 |
+
{
|
| 6667 |
+
"epoch": 4.095595126522961,
|
| 6668 |
+
"grad_norm": 1.921200156211853,
|
| 6669 |
+
"learning_rate": 9.48805060918463e-06,
|
| 6670 |
+
"loss": 0.1404,
|
| 6671 |
+
"step": 8740
|
| 6672 |
+
},
|
| 6673 |
+
{
|
| 6674 |
+
"epoch": 4.100281162136832,
|
| 6675 |
+
"grad_norm": 2.808347225189209,
|
| 6676 |
+
"learning_rate": 9.487464854732897e-06,
|
| 6677 |
+
"loss": 0.1345,
|
| 6678 |
+
"step": 8750
|
| 6679 |
+
},
|
| 6680 |
+
{
|
| 6681 |
+
"epoch": 4.100281162136832,
|
| 6682 |
+
"eval_loss": 0.0466812327504158,
|
| 6683 |
+
"eval_pearson_cosine": 0.7762485382429531,
|
| 6684 |
+
"eval_pearson_dot": 0.6205844136544023,
|
| 6685 |
+
"eval_pearson_euclidean": 0.7434752403993485,
|
| 6686 |
+
"eval_pearson_manhattan": 0.7429057889387991,
|
| 6687 |
+
"eval_runtime": 39.0625,
|
| 6688 |
+
"eval_samples_per_second": 38.4,
|
| 6689 |
+
"eval_spearman_cosine": 0.7802221022373591,
|
| 6690 |
+
"eval_spearman_dot": 0.6303325253186769,
|
| 6691 |
+
"eval_spearman_euclidean": 0.7611130904217269,
|
| 6692 |
+
"eval_spearman_manhattan": 0.7606144833054299,
|
| 6693 |
+
"eval_steps_per_second": 38.4,
|
| 6694 |
+
"step": 8750
|
| 6695 |
+
},
|
| 6696 |
+
{
|
| 6697 |
+
"epoch": 4.104967197750703,
|
| 6698 |
+
"grad_norm": 1.7242465019226074,
|
| 6699 |
+
"learning_rate": 9.486879100281164e-06,
|
| 6700 |
+
"loss": 0.1288,
|
| 6701 |
+
"step": 8760
|
| 6702 |
+
},
|
| 6703 |
+
{
|
| 6704 |
+
"epoch": 4.109653233364574,
|
| 6705 |
+
"grad_norm": 2.2536211013793945,
|
| 6706 |
+
"learning_rate": 9.486293345829429e-06,
|
| 6707 |
+
"loss": 0.1313,
|
| 6708 |
+
"step": 8770
|
| 6709 |
+
},
|
| 6710 |
+
{
|
| 6711 |
+
"epoch": 4.114339268978444,
|
| 6712 |
+
"grad_norm": 2.289796829223633,
|
| 6713 |
+
"learning_rate": 9.485707591377696e-06,
|
| 6714 |
+
"loss": 0.1689,
|
| 6715 |
+
"step": 8780
|
| 6716 |
+
},
|
| 6717 |
+
{
|
| 6718 |
+
"epoch": 4.119025304592315,
|
| 6719 |
+
"grad_norm": 1.961803913116455,
|
| 6720 |
+
"learning_rate": 9.485121836925961e-06,
|
| 6721 |
+
"loss": 0.127,
|
| 6722 |
+
"step": 8790
|
| 6723 |
+
},
|
| 6724 |
+
{
|
| 6725 |
+
"epoch": 4.123711340206185,
|
| 6726 |
+
"grad_norm": 1.667372465133667,
|
| 6727 |
+
"learning_rate": 9.484536082474226e-06,
|
| 6728 |
+
"loss": 0.1267,
|
| 6729 |
+
"step": 8800
|
| 6730 |
+
},
|
| 6731 |
+
{
|
| 6732 |
+
"epoch": 4.1283973758200565,
|
| 6733 |
+
"grad_norm": 1.8963170051574707,
|
| 6734 |
+
"learning_rate": 9.483950328022495e-06,
|
| 6735 |
+
"loss": 0.1556,
|
| 6736 |
+
"step": 8810
|
| 6737 |
+
},
|
| 6738 |
+
{
|
| 6739 |
+
"epoch": 4.133083411433927,
|
| 6740 |
+
"grad_norm": 2.9656922817230225,
|
| 6741 |
+
"learning_rate": 9.48336457357076e-06,
|
| 6742 |
+
"loss": 0.1486,
|
| 6743 |
+
"step": 8820
|
| 6744 |
+
},
|
| 6745 |
+
{
|
| 6746 |
+
"epoch": 4.1377694470477975,
|
| 6747 |
+
"grad_norm": 1.9788974523544312,
|
| 6748 |
+
"learning_rate": 9.482778819119025e-06,
|
| 6749 |
+
"loss": 0.1542,
|
| 6750 |
+
"step": 8830
|
| 6751 |
+
},
|
| 6752 |
+
{
|
| 6753 |
+
"epoch": 4.142455482661668,
|
| 6754 |
+
"grad_norm": 2.4442574977874756,
|
| 6755 |
+
"learning_rate": 9.482193064667292e-06,
|
| 6756 |
+
"loss": 0.1318,
|
| 6757 |
+
"step": 8840
|
| 6758 |
+
},
|
| 6759 |
+
{
|
| 6760 |
+
"epoch": 4.147141518275539,
|
| 6761 |
+
"grad_norm": 2.5937938690185547,
|
| 6762 |
+
"learning_rate": 9.481607310215558e-06,
|
| 6763 |
+
"loss": 0.1451,
|
| 6764 |
+
"step": 8850
|
| 6765 |
+
},
|
| 6766 |
+
{
|
| 6767 |
+
"epoch": 4.15182755388941,
|
| 6768 |
+
"grad_norm": 2.443493366241455,
|
| 6769 |
+
"learning_rate": 9.481021555763825e-06,
|
| 6770 |
+
"loss": 0.1569,
|
| 6771 |
+
"step": 8860
|
| 6772 |
+
},
|
| 6773 |
+
{
|
| 6774 |
+
"epoch": 4.15651358950328,
|
| 6775 |
+
"grad_norm": 2.4432411193847656,
|
| 6776 |
+
"learning_rate": 9.480435801312091e-06,
|
| 6777 |
+
"loss": 0.1371,
|
| 6778 |
+
"step": 8870
|
| 6779 |
+
},
|
| 6780 |
+
{
|
| 6781 |
+
"epoch": 4.161199625117151,
|
| 6782 |
+
"grad_norm": 2.259110689163208,
|
| 6783 |
+
"learning_rate": 9.479850046860357e-06,
|
| 6784 |
+
"loss": 0.1492,
|
| 6785 |
+
"step": 8880
|
| 6786 |
+
},
|
| 6787 |
+
{
|
| 6788 |
+
"epoch": 4.165885660731021,
|
| 6789 |
+
"grad_norm": 2.7767279148101807,
|
| 6790 |
+
"learning_rate": 9.479264292408624e-06,
|
| 6791 |
+
"loss": 0.1248,
|
| 6792 |
+
"step": 8890
|
| 6793 |
+
},
|
| 6794 |
+
{
|
| 6795 |
+
"epoch": 4.170571696344892,
|
| 6796 |
+
"grad_norm": 2.309516191482544,
|
| 6797 |
+
"learning_rate": 9.478678537956889e-06,
|
| 6798 |
+
"loss": 0.14,
|
| 6799 |
+
"step": 8900
|
| 6800 |
+
},
|
| 6801 |
+
{
|
| 6802 |
+
"epoch": 4.175257731958763,
|
| 6803 |
+
"grad_norm": 1.9368172883987427,
|
| 6804 |
+
"learning_rate": 9.478092783505156e-06,
|
| 6805 |
+
"loss": 0.1343,
|
| 6806 |
+
"step": 8910
|
| 6807 |
+
},
|
| 6808 |
+
{
|
| 6809 |
+
"epoch": 4.179943767572634,
|
| 6810 |
+
"grad_norm": 3.124490976333618,
|
| 6811 |
+
"learning_rate": 9.477507029053423e-06,
|
| 6812 |
+
"loss": 0.1358,
|
| 6813 |
+
"step": 8920
|
| 6814 |
+
},
|
| 6815 |
+
{
|
| 6816 |
+
"epoch": 4.184629803186504,
|
| 6817 |
+
"grad_norm": 2.3121657371520996,
|
| 6818 |
+
"learning_rate": 9.476921274601688e-06,
|
| 6819 |
+
"loss": 0.1516,
|
| 6820 |
+
"step": 8930
|
| 6821 |
+
},
|
| 6822 |
+
{
|
| 6823 |
+
"epoch": 4.189315838800375,
|
| 6824 |
+
"grad_norm": 2.1902709007263184,
|
| 6825 |
+
"learning_rate": 9.476335520149955e-06,
|
| 6826 |
+
"loss": 0.1253,
|
| 6827 |
+
"step": 8940
|
| 6828 |
+
},
|
| 6829 |
+
{
|
| 6830 |
+
"epoch": 4.194001874414246,
|
| 6831 |
+
"grad_norm": 3.0760653018951416,
|
| 6832 |
+
"learning_rate": 9.47574976569822e-06,
|
| 6833 |
+
"loss": 0.1678,
|
| 6834 |
+
"step": 8950
|
| 6835 |
+
},
|
| 6836 |
+
{
|
| 6837 |
+
"epoch": 4.1986879100281165,
|
| 6838 |
+
"grad_norm": 2.8899242877960205,
|
| 6839 |
+
"learning_rate": 9.475164011246485e-06,
|
| 6840 |
+
"loss": 0.137,
|
| 6841 |
+
"step": 8960
|
| 6842 |
+
},
|
| 6843 |
+
{
|
| 6844 |
+
"epoch": 4.203373945641987,
|
| 6845 |
+
"grad_norm": 2.4512765407562256,
|
| 6846 |
+
"learning_rate": 9.474578256794752e-06,
|
| 6847 |
+
"loss": 0.1598,
|
| 6848 |
+
"step": 8970
|
| 6849 |
+
},
|
| 6850 |
+
{
|
| 6851 |
+
"epoch": 4.2080599812558575,
|
| 6852 |
+
"grad_norm": 2.9443392753601074,
|
| 6853 |
+
"learning_rate": 9.473992502343019e-06,
|
| 6854 |
+
"loss": 0.143,
|
| 6855 |
+
"step": 8980
|
| 6856 |
+
},
|
| 6857 |
+
{
|
| 6858 |
+
"epoch": 4.212746016869728,
|
| 6859 |
+
"grad_norm": 3.5128183364868164,
|
| 6860 |
+
"learning_rate": 9.473406747891284e-06,
|
| 6861 |
+
"loss": 0.1556,
|
| 6862 |
+
"step": 8990
|
| 6863 |
+
},
|
| 6864 |
+
{
|
| 6865 |
+
"epoch": 4.217432052483598,
|
| 6866 |
+
"grad_norm": 2.6914291381835938,
|
| 6867 |
+
"learning_rate": 9.472820993439551e-06,
|
| 6868 |
+
"loss": 0.1506,
|
| 6869 |
+
"step": 9000
|
| 6870 |
+
},
|
| 6871 |
+
{
|
| 6872 |
+
"epoch": 4.217432052483598,
|
| 6873 |
+
"eval_loss": 0.04765741899609566,
|
| 6874 |
+
"eval_pearson_cosine": 0.771092218670848,
|
| 6875 |
+
"eval_pearson_dot": 0.5978116743652393,
|
| 6876 |
+
"eval_pearson_euclidean": 0.7473151449481621,
|
| 6877 |
+
"eval_pearson_manhattan": 0.7466335380915066,
|
| 6878 |
+
"eval_runtime": 39.8559,
|
| 6879 |
+
"eval_samples_per_second": 37.636,
|
| 6880 |
+
"eval_spearman_cosine": 0.7759072486337746,
|
| 6881 |
+
"eval_spearman_dot": 0.6025471021302765,
|
| 6882 |
+
"eval_spearman_euclidean": 0.7630945437887154,
|
| 6883 |
+
"eval_spearman_manhattan": 0.7624729408213863,
|
| 6884 |
+
"eval_steps_per_second": 37.636,
|
| 6885 |
+
"step": 9000
|
| 6886 |
}
|
| 6887 |
],
|
| 6888 |
"logging_steps": 10,
|