Training in progress, step 5664
Browse files- adapter_model.safetensors +1 -1
- trainer_state.json +35 -5
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3089143504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aacb3f9f436b2e23a3db07bc2dd8c9f311053d3533138f47470082d0efd3eff
|
| 3 |
size 3089143504
|
trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 5500,
|
| 3 |
"best_metric": 1.8417972326278687,
|
| 4 |
"best_model_checkpoint": "/kaggle/working/checkpoints/checkpoint-5500",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1239,11 +1239,41 @@
|
|
| 1239 |
"eval_steps_per_second": 1.768,
|
| 1240 |
"num_input_tokens_seen": 22510080,
|
| 1241 |
"step": 5500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1242 |
}
|
| 1243 |
],
|
| 1244 |
"logging_steps": 50,
|
| 1245 |
"max_steps": 5664,
|
| 1246 |
-
"num_input_tokens_seen":
|
| 1247 |
"num_train_epochs": 6,
|
| 1248 |
"save_steps": 500,
|
| 1249 |
"stateful_callbacks": {
|
|
@@ -1253,12 +1283,12 @@
|
|
| 1253 |
"should_evaluate": false,
|
| 1254 |
"should_log": false,
|
| 1255 |
"should_save": true,
|
| 1256 |
-
"should_training_stop":
|
| 1257 |
},
|
| 1258 |
"attributes": {}
|
| 1259 |
}
|
| 1260 |
},
|
| 1261 |
-
"total_flos": 4.
|
| 1262 |
"train_batch_size": 8,
|
| 1263 |
"trial_name": null,
|
| 1264 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 5500,
|
| 3 |
"best_metric": 1.8417972326278687,
|
| 4 |
"best_model_checkpoint": "/kaggle/working/checkpoints/checkpoint-5500",
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5664,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1239 |
"eval_steps_per_second": 1.768,
|
| 1240 |
"num_input_tokens_seen": 22510080,
|
| 1241 |
"step": 5500
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 5.879936390140472,
|
| 1245 |
+
"grad_norm": 0.7171221375465393,
|
| 1246 |
+
"learning_rate": 6.279577721150346e-06,
|
| 1247 |
+
"loss": 8.624059448242187,
|
| 1248 |
+
"num_input_tokens_seen": 22714880,
|
| 1249 |
+
"step": 5550,
|
| 1250 |
+
"train_runtime": 11215.8439,
|
| 1251 |
+
"train_tokens_per_second": 2025.249
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 5.932944606413994,
|
| 1255 |
+
"grad_norm": 0.6685547232627869,
|
| 1256 |
+
"learning_rate": 3.549326538041499e-06,
|
| 1257 |
+
"loss": 8.639024047851562,
|
| 1258 |
+
"num_input_tokens_seen": 22919680,
|
| 1259 |
+
"step": 5600,
|
| 1260 |
+
"train_runtime": 11307.5506,
|
| 1261 |
+
"train_tokens_per_second": 2026.936
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 5.9859528226875165,
|
| 1265 |
+
"grad_norm": 0.6983809471130371,
|
| 1266 |
+
"learning_rate": 8.190753549326538e-07,
|
| 1267 |
+
"loss": 8.527723388671875,
|
| 1268 |
+
"num_input_tokens_seen": 23124480,
|
| 1269 |
+
"step": 5650,
|
| 1270 |
+
"train_runtime": 11399.0902,
|
| 1271 |
+
"train_tokens_per_second": 2028.625
|
| 1272 |
}
|
| 1273 |
],
|
| 1274 |
"logging_steps": 50,
|
| 1275 |
"max_steps": 5664,
|
| 1276 |
+
"num_input_tokens_seen": 23178240,
|
| 1277 |
"num_train_epochs": 6,
|
| 1278 |
"save_steps": 500,
|
| 1279 |
"stateful_callbacks": {
|
|
|
|
| 1283 |
"should_evaluate": false,
|
| 1284 |
"should_log": false,
|
| 1285 |
"should_save": true,
|
| 1286 |
+
"should_training_stop": true
|
| 1287 |
},
|
| 1288 |
"attributes": {}
|
| 1289 |
}
|
| 1290 |
},
|
| 1291 |
+
"total_flos": 4.229533786963968e+16,
|
| 1292 |
"train_batch_size": 8,
|
| 1293 |
"trial_name": null,
|
| 1294 |
"trial_params": null
|