Training in progress, step 4000, 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 737580392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34566692b409c5ac91614f85431dcd34c66b34e43f4a92470ac88cb8a7f59789
|
| 3 |
size 737580392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475248442
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dde92a9190daf4d6cde776e30b6451c543ea444edee3b9afc951fa9a8b0c5c7
|
| 3 |
size 1475248442
|
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 sha256:8f9aa43992237c34da047eae3e4635545e3cbee9026436669a8ec61ef48f58c1
|
| 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 sha256:5a5a37a50084edc8f378e7d4e65f501b6827a819c6aec4a25edf84ae7f0723a0
|
| 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": 1.
|
| 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,
|
|
@@ -2299,6 +2299,770 @@
|
|
| 2299 |
"eval_spearman_manhattan": 0.8142678938453525,
|
| 2300 |
"eval_steps_per_second": 27.696,
|
| 2301 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2302 |
}
|
| 2303 |
],
|
| 2304 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8744142455482662,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2299 |
"eval_spearman_manhattan": 0.8142678938453525,
|
| 2300 |
"eval_steps_per_second": 27.696,
|
| 2301 |
"step": 3000
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 1.4104967197750704,
|
| 2305 |
+
"grad_norm": 2.0516934394836426,
|
| 2306 |
+
"learning_rate": 1.911843955014058e-05,
|
| 2307 |
+
"loss": 0.2469,
|
| 2308 |
+
"step": 3010
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 1.415182755388941,
|
| 2312 |
+
"grad_norm": 1.8646856546401978,
|
| 2313 |
+
"learning_rate": 1.9115510777881914e-05,
|
| 2314 |
+
"loss": 0.2434,
|
| 2315 |
+
"step": 3020
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 1.4198687910028116,
|
| 2319 |
+
"grad_norm": 1.746596097946167,
|
| 2320 |
+
"learning_rate": 1.9112582005623243e-05,
|
| 2321 |
+
"loss": 0.2392,
|
| 2322 |
+
"step": 3030
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 1.4245548266166823,
|
| 2326 |
+
"grad_norm": 1.7546746730804443,
|
| 2327 |
+
"learning_rate": 1.9109653233364576e-05,
|
| 2328 |
+
"loss": 0.2141,
|
| 2329 |
+
"step": 3040
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 1.429240862230553,
|
| 2333 |
+
"grad_norm": 1.7862520217895508,
|
| 2334 |
+
"learning_rate": 1.9106724461105905e-05,
|
| 2335 |
+
"loss": 0.2424,
|
| 2336 |
+
"step": 3050
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 1.4339268978444237,
|
| 2340 |
+
"grad_norm": 2.089353322982788,
|
| 2341 |
+
"learning_rate": 1.910379568884724e-05,
|
| 2342 |
+
"loss": 0.2493,
|
| 2343 |
+
"step": 3060
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 1.4386129334582942,
|
| 2347 |
+
"grad_norm": 1.7390618324279785,
|
| 2348 |
+
"learning_rate": 1.9100866916588568e-05,
|
| 2349 |
+
"loss": 0.2317,
|
| 2350 |
+
"step": 3070
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 1.443298969072165,
|
| 2354 |
+
"grad_norm": 1.9297877550125122,
|
| 2355 |
+
"learning_rate": 1.90979381443299e-05,
|
| 2356 |
+
"loss": 0.2335,
|
| 2357 |
+
"step": 3080
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 1.4479850046860356,
|
| 2361 |
+
"grad_norm": 1.872578740119934,
|
| 2362 |
+
"learning_rate": 1.909500937207123e-05,
|
| 2363 |
+
"loss": 0.222,
|
| 2364 |
+
"step": 3090
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 1.4526710402999063,
|
| 2368 |
+
"grad_norm": 1.646843433380127,
|
| 2369 |
+
"learning_rate": 1.909208059981256e-05,
|
| 2370 |
+
"loss": 0.2154,
|
| 2371 |
+
"step": 3100
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 1.457357075913777,
|
| 2375 |
+
"grad_norm": 1.8208719491958618,
|
| 2376 |
+
"learning_rate": 1.9089151827553893e-05,
|
| 2377 |
+
"loss": 0.2887,
|
| 2378 |
+
"step": 3110
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 1.4620431115276475,
|
| 2382 |
+
"grad_norm": 1.6147174835205078,
|
| 2383 |
+
"learning_rate": 1.9086223055295222e-05,
|
| 2384 |
+
"loss": 0.2292,
|
| 2385 |
+
"step": 3120
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 1.4667291471415183,
|
| 2389 |
+
"grad_norm": 2.147585391998291,
|
| 2390 |
+
"learning_rate": 1.908329428303655e-05,
|
| 2391 |
+
"loss": 0.2598,
|
| 2392 |
+
"step": 3130
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 1.471415182755389,
|
| 2396 |
+
"grad_norm": 2.17818284034729,
|
| 2397 |
+
"learning_rate": 1.9080365510777884e-05,
|
| 2398 |
+
"loss": 0.2177,
|
| 2399 |
+
"step": 3140
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 1.4761012183692597,
|
| 2403 |
+
"grad_norm": 1.7800393104553223,
|
| 2404 |
+
"learning_rate": 1.9077436738519214e-05,
|
| 2405 |
+
"loss": 0.2091,
|
| 2406 |
+
"step": 3150
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 1.4807872539831304,
|
| 2410 |
+
"grad_norm": 1.8269144296646118,
|
| 2411 |
+
"learning_rate": 1.9074507966260543e-05,
|
| 2412 |
+
"loss": 0.241,
|
| 2413 |
+
"step": 3160
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 1.4854732895970009,
|
| 2417 |
+
"grad_norm": 1.4544728994369507,
|
| 2418 |
+
"learning_rate": 1.9071579194001876e-05,
|
| 2419 |
+
"loss": 0.2481,
|
| 2420 |
+
"step": 3170
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 1.4901593252108716,
|
| 2424 |
+
"grad_norm": 2.5941991806030273,
|
| 2425 |
+
"learning_rate": 1.9068650421743206e-05,
|
| 2426 |
+
"loss": 0.266,
|
| 2427 |
+
"step": 3180
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 1.4948453608247423,
|
| 2431 |
+
"grad_norm": 1.9068180322647095,
|
| 2432 |
+
"learning_rate": 1.906572164948454e-05,
|
| 2433 |
+
"loss": 0.2546,
|
| 2434 |
+
"step": 3190
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 1.499531396438613,
|
| 2438 |
+
"grad_norm": 1.590065598487854,
|
| 2439 |
+
"learning_rate": 1.9062792877225868e-05,
|
| 2440 |
+
"loss": 0.2292,
|
| 2441 |
+
"step": 3200
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 1.5042174320524837,
|
| 2445 |
+
"grad_norm": 1.9283113479614258,
|
| 2446 |
+
"learning_rate": 1.9059864104967198e-05,
|
| 2447 |
+
"loss": 0.2485,
|
| 2448 |
+
"step": 3210
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 1.5089034676663542,
|
| 2452 |
+
"grad_norm": 2.1952388286590576,
|
| 2453 |
+
"learning_rate": 1.905693533270853e-05,
|
| 2454 |
+
"loss": 0.2197,
|
| 2455 |
+
"step": 3220
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 1.513589503280225,
|
| 2459 |
+
"grad_norm": 1.554611086845398,
|
| 2460 |
+
"learning_rate": 1.905400656044986e-05,
|
| 2461 |
+
"loss": 0.2136,
|
| 2462 |
+
"step": 3230
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 1.5182755388940956,
|
| 2466 |
+
"grad_norm": 1.5786999464035034,
|
| 2467 |
+
"learning_rate": 1.9051077788191193e-05,
|
| 2468 |
+
"loss": 0.2333,
|
| 2469 |
+
"step": 3240
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 1.522961574507966,
|
| 2473 |
+
"grad_norm": 2.7858917713165283,
|
| 2474 |
+
"learning_rate": 1.9048149015932523e-05,
|
| 2475 |
+
"loss": 0.2328,
|
| 2476 |
+
"step": 3250
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 1.522961574507966,
|
| 2480 |
+
"eval_loss": 0.04040240868926048,
|
| 2481 |
+
"eval_pearson_cosine": 0.8187130517711054,
|
| 2482 |
+
"eval_pearson_dot": 0.7426107734380025,
|
| 2483 |
+
"eval_pearson_euclidean": 0.8069722435152613,
|
| 2484 |
+
"eval_pearson_manhattan": 0.8083599378238802,
|
| 2485 |
+
"eval_runtime": 3.6772,
|
| 2486 |
+
"eval_samples_per_second": 407.917,
|
| 2487 |
+
"eval_spearman_cosine": 0.8202782064729509,
|
| 2488 |
+
"eval_spearman_dot": 0.7414284976652127,
|
| 2489 |
+
"eval_spearman_euclidean": 0.8153801634076588,
|
| 2490 |
+
"eval_spearman_manhattan": 0.8165145388144227,
|
| 2491 |
+
"eval_steps_per_second": 25.563,
|
| 2492 |
+
"step": 3250
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 1.527647610121837,
|
| 2496 |
+
"grad_norm": 1.9804577827453613,
|
| 2497 |
+
"learning_rate": 1.9045220243673855e-05,
|
| 2498 |
+
"loss": 0.252,
|
| 2499 |
+
"step": 3260
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 1.5323336457357075,
|
| 2503 |
+
"grad_norm": 1.8716363906860352,
|
| 2504 |
+
"learning_rate": 1.9042291471415185e-05,
|
| 2505 |
+
"loss": 0.2266,
|
| 2506 |
+
"step": 3270
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 1.5370196813495782,
|
| 2510 |
+
"grad_norm": 1.834250569343567,
|
| 2511 |
+
"learning_rate": 1.9039362699156518e-05,
|
| 2512 |
+
"loss": 0.2314,
|
| 2513 |
+
"step": 3280
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 1.541705716963449,
|
| 2517 |
+
"grad_norm": 2.0380077362060547,
|
| 2518 |
+
"learning_rate": 1.9036433926897847e-05,
|
| 2519 |
+
"loss": 0.2545,
|
| 2520 |
+
"step": 3290
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 1.5463917525773194,
|
| 2524 |
+
"grad_norm": 1.8950886726379395,
|
| 2525 |
+
"learning_rate": 1.9033505154639177e-05,
|
| 2526 |
+
"loss": 0.2902,
|
| 2527 |
+
"step": 3300
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"epoch": 1.5510777881911904,
|
| 2531 |
+
"grad_norm": 1.4216679334640503,
|
| 2532 |
+
"learning_rate": 1.9030576382380506e-05,
|
| 2533 |
+
"loss": 0.2344,
|
| 2534 |
+
"step": 3310
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 1.5557638238050608,
|
| 2538 |
+
"grad_norm": 1.2056218385696411,
|
| 2539 |
+
"learning_rate": 1.902764761012184e-05,
|
| 2540 |
+
"loss": 0.252,
|
| 2541 |
+
"step": 3320
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 1.5604498594189316,
|
| 2545 |
+
"grad_norm": 1.8112496137619019,
|
| 2546 |
+
"learning_rate": 1.902471883786317e-05,
|
| 2547 |
+
"loss": 0.2406,
|
| 2548 |
+
"step": 3330
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 1.5651358950328023,
|
| 2552 |
+
"grad_norm": 1.9375700950622559,
|
| 2553 |
+
"learning_rate": 1.9021790065604498e-05,
|
| 2554 |
+
"loss": 0.2728,
|
| 2555 |
+
"step": 3340
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 1.569821930646673,
|
| 2559 |
+
"grad_norm": 2.4203391075134277,
|
| 2560 |
+
"learning_rate": 1.901886129334583e-05,
|
| 2561 |
+
"loss": 0.2434,
|
| 2562 |
+
"step": 3350
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 1.5745079662605437,
|
| 2566 |
+
"grad_norm": 2.114474058151245,
|
| 2567 |
+
"learning_rate": 1.901593252108716e-05,
|
| 2568 |
+
"loss": 0.2535,
|
| 2569 |
+
"step": 3360
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 1.5791940018744142,
|
| 2573 |
+
"grad_norm": 1.5152201652526855,
|
| 2574 |
+
"learning_rate": 1.9013003748828493e-05,
|
| 2575 |
+
"loss": 0.2537,
|
| 2576 |
+
"step": 3370
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 1.5838800374882849,
|
| 2580 |
+
"grad_norm": 1.8051055669784546,
|
| 2581 |
+
"learning_rate": 1.9010074976569823e-05,
|
| 2582 |
+
"loss": 0.2271,
|
| 2583 |
+
"step": 3380
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 1.5885660731021556,
|
| 2587 |
+
"grad_norm": 2.005028247833252,
|
| 2588 |
+
"learning_rate": 1.9007146204311156e-05,
|
| 2589 |
+
"loss": 0.2508,
|
| 2590 |
+
"step": 3390
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 1.5932521087160263,
|
| 2594 |
+
"grad_norm": 1.534379005432129,
|
| 2595 |
+
"learning_rate": 1.9004217432052485e-05,
|
| 2596 |
+
"loss": 0.2358,
|
| 2597 |
+
"step": 3400
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 1.597938144329897,
|
| 2601 |
+
"grad_norm": 1.2152713537216187,
|
| 2602 |
+
"learning_rate": 1.9001288659793815e-05,
|
| 2603 |
+
"loss": 0.203,
|
| 2604 |
+
"step": 3410
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 1.6026241799437675,
|
| 2608 |
+
"grad_norm": 1.584352970123291,
|
| 2609 |
+
"learning_rate": 1.8998359887535148e-05,
|
| 2610 |
+
"loss": 0.2369,
|
| 2611 |
+
"step": 3420
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 1.6073102155576382,
|
| 2615 |
+
"grad_norm": 1.8603837490081787,
|
| 2616 |
+
"learning_rate": 1.8995431115276477e-05,
|
| 2617 |
+
"loss": 0.2576,
|
| 2618 |
+
"step": 3430
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 1.611996251171509,
|
| 2622 |
+
"grad_norm": 1.300493597984314,
|
| 2623 |
+
"learning_rate": 1.899250234301781e-05,
|
| 2624 |
+
"loss": 0.2048,
|
| 2625 |
+
"step": 3440
|
| 2626 |
+
},
|
| 2627 |
+
{
|
| 2628 |
+
"epoch": 1.6166822867853796,
|
| 2629 |
+
"grad_norm": 1.6629600524902344,
|
| 2630 |
+
"learning_rate": 1.898957357075914e-05,
|
| 2631 |
+
"loss": 0.2305,
|
| 2632 |
+
"step": 3450
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 1.6213683223992503,
|
| 2636 |
+
"grad_norm": 2.555297374725342,
|
| 2637 |
+
"learning_rate": 1.8986644798500473e-05,
|
| 2638 |
+
"loss": 0.2487,
|
| 2639 |
+
"step": 3460
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 1.6260543580131208,
|
| 2643 |
+
"grad_norm": 2.425975799560547,
|
| 2644 |
+
"learning_rate": 1.8983716026241802e-05,
|
| 2645 |
+
"loss": 0.241,
|
| 2646 |
+
"step": 3470
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 1.6307403936269915,
|
| 2650 |
+
"grad_norm": 1.912858247756958,
|
| 2651 |
+
"learning_rate": 1.898078725398313e-05,
|
| 2652 |
+
"loss": 0.2074,
|
| 2653 |
+
"step": 3480
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 1.6354264292408622,
|
| 2657 |
+
"grad_norm": 2.066469430923462,
|
| 2658 |
+
"learning_rate": 1.897785848172446e-05,
|
| 2659 |
+
"loss": 0.2157,
|
| 2660 |
+
"step": 3490
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 1.640112464854733,
|
| 2664 |
+
"grad_norm": 1.5405519008636475,
|
| 2665 |
+
"learning_rate": 1.8974929709465794e-05,
|
| 2666 |
+
"loss": 0.2052,
|
| 2667 |
+
"step": 3500
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 1.640112464854733,
|
| 2671 |
+
"eval_loss": 0.03896905109286308,
|
| 2672 |
+
"eval_pearson_cosine": 0.8147239668269464,
|
| 2673 |
+
"eval_pearson_dot": 0.74259279719071,
|
| 2674 |
+
"eval_pearson_euclidean": 0.803459120860885,
|
| 2675 |
+
"eval_pearson_manhattan": 0.8045289290680273,
|
| 2676 |
+
"eval_runtime": 3.5517,
|
| 2677 |
+
"eval_samples_per_second": 422.338,
|
| 2678 |
+
"eval_spearman_cosine": 0.8164243711017356,
|
| 2679 |
+
"eval_spearman_dot": 0.742209739118843,
|
| 2680 |
+
"eval_spearman_euclidean": 0.8121850450179654,
|
| 2681 |
+
"eval_spearman_manhattan": 0.8128758362528613,
|
| 2682 |
+
"eval_steps_per_second": 26.467,
|
| 2683 |
+
"step": 3500
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 1.6447985004686037,
|
| 2687 |
+
"grad_norm": 1.4605026245117188,
|
| 2688 |
+
"learning_rate": 1.8972000937207123e-05,
|
| 2689 |
+
"loss": 0.2329,
|
| 2690 |
+
"step": 3510
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 1.6494845360824741,
|
| 2694 |
+
"grad_norm": 1.496071457862854,
|
| 2695 |
+
"learning_rate": 1.8969072164948453e-05,
|
| 2696 |
+
"loss": 0.2171,
|
| 2697 |
+
"step": 3520
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 1.6541705716963448,
|
| 2701 |
+
"grad_norm": 1.5330686569213867,
|
| 2702 |
+
"learning_rate": 1.8966143392689786e-05,
|
| 2703 |
+
"loss": 0.235,
|
| 2704 |
+
"step": 3530
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 1.6588566073102156,
|
| 2708 |
+
"grad_norm": 1.77309250831604,
|
| 2709 |
+
"learning_rate": 1.8963214620431115e-05,
|
| 2710 |
+
"loss": 0.2398,
|
| 2711 |
+
"step": 3540
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 1.6635426429240863,
|
| 2715 |
+
"grad_norm": 2.6333131790161133,
|
| 2716 |
+
"learning_rate": 1.8960285848172448e-05,
|
| 2717 |
+
"loss": 0.2444,
|
| 2718 |
+
"step": 3550
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 1.668228678537957,
|
| 2722 |
+
"grad_norm": 1.7444895505905151,
|
| 2723 |
+
"learning_rate": 1.8957357075913778e-05,
|
| 2724 |
+
"loss": 0.2308,
|
| 2725 |
+
"step": 3560
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 1.6729147141518275,
|
| 2729 |
+
"grad_norm": 1.9555528163909912,
|
| 2730 |
+
"learning_rate": 1.895442830365511e-05,
|
| 2731 |
+
"loss": 0.2177,
|
| 2732 |
+
"step": 3570
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 1.6776007497656982,
|
| 2736 |
+
"grad_norm": 1.8581876754760742,
|
| 2737 |
+
"learning_rate": 1.895149953139644e-05,
|
| 2738 |
+
"loss": 0.2287,
|
| 2739 |
+
"step": 3580
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 1.6822867853795689,
|
| 2743 |
+
"grad_norm": 1.9251590967178345,
|
| 2744 |
+
"learning_rate": 1.894857075913777e-05,
|
| 2745 |
+
"loss": 0.2547,
|
| 2746 |
+
"step": 3590
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 1.6869728209934396,
|
| 2750 |
+
"grad_norm": 1.6071839332580566,
|
| 2751 |
+
"learning_rate": 1.8945641986879102e-05,
|
| 2752 |
+
"loss": 0.2409,
|
| 2753 |
+
"step": 3600
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 1.6916588566073103,
|
| 2757 |
+
"grad_norm": 1.735236406326294,
|
| 2758 |
+
"learning_rate": 1.8942713214620432e-05,
|
| 2759 |
+
"loss": 0.2315,
|
| 2760 |
+
"step": 3610
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 1.6963448922211808,
|
| 2764 |
+
"grad_norm": 1.5945345163345337,
|
| 2765 |
+
"learning_rate": 1.8939784442361765e-05,
|
| 2766 |
+
"loss": 0.2283,
|
| 2767 |
+
"step": 3620
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 1.7010309278350515,
|
| 2771 |
+
"grad_norm": 1.8697439432144165,
|
| 2772 |
+
"learning_rate": 1.8936855670103094e-05,
|
| 2773 |
+
"loss": 0.2382,
|
| 2774 |
+
"step": 3630
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 1.7057169634489222,
|
| 2778 |
+
"grad_norm": 1.9775031805038452,
|
| 2779 |
+
"learning_rate": 1.8933926897844427e-05,
|
| 2780 |
+
"loss": 0.2167,
|
| 2781 |
+
"step": 3640
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 1.710402999062793,
|
| 2785 |
+
"grad_norm": 1.7976644039154053,
|
| 2786 |
+
"learning_rate": 1.8930998125585757e-05,
|
| 2787 |
+
"loss": 0.2252,
|
| 2788 |
+
"step": 3650
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 1.7150890346766636,
|
| 2792 |
+
"grad_norm": 1.9334297180175781,
|
| 2793 |
+
"learning_rate": 1.8928069353327086e-05,
|
| 2794 |
+
"loss": 0.207,
|
| 2795 |
+
"step": 3660
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 1.7197750702905341,
|
| 2799 |
+
"grad_norm": 1.661363124847412,
|
| 2800 |
+
"learning_rate": 1.892514058106842e-05,
|
| 2801 |
+
"loss": 0.2531,
|
| 2802 |
+
"step": 3670
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 1.7244611059044048,
|
| 2806 |
+
"grad_norm": 2.2192280292510986,
|
| 2807 |
+
"learning_rate": 1.892221180880975e-05,
|
| 2808 |
+
"loss": 0.2552,
|
| 2809 |
+
"step": 3680
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 1.7291471415182755,
|
| 2813 |
+
"grad_norm": 1.9910961389541626,
|
| 2814 |
+
"learning_rate": 1.8919283036551078e-05,
|
| 2815 |
+
"loss": 0.2288,
|
| 2816 |
+
"step": 3690
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 1.7338331771321462,
|
| 2820 |
+
"grad_norm": 1.6120171546936035,
|
| 2821 |
+
"learning_rate": 1.8916354264292408e-05,
|
| 2822 |
+
"loss": 0.2122,
|
| 2823 |
+
"step": 3700
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 1.738519212746017,
|
| 2827 |
+
"grad_norm": 1.8387460708618164,
|
| 2828 |
+
"learning_rate": 1.891342549203374e-05,
|
| 2829 |
+
"loss": 0.2292,
|
| 2830 |
+
"step": 3710
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 1.7432052483598874,
|
| 2834 |
+
"grad_norm": 1.9124442338943481,
|
| 2835 |
+
"learning_rate": 1.891049671977507e-05,
|
| 2836 |
+
"loss": 0.2469,
|
| 2837 |
+
"step": 3720
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 1.7478912839737581,
|
| 2841 |
+
"grad_norm": 2.267001152038574,
|
| 2842 |
+
"learning_rate": 1.8907567947516403e-05,
|
| 2843 |
+
"loss": 0.2139,
|
| 2844 |
+
"step": 3730
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 1.7525773195876289,
|
| 2848 |
+
"grad_norm": 1.9495887756347656,
|
| 2849 |
+
"learning_rate": 1.8904639175257732e-05,
|
| 2850 |
+
"loss": 0.2476,
|
| 2851 |
+
"step": 3740
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 1.7572633552014996,
|
| 2855 |
+
"grad_norm": 1.8650192022323608,
|
| 2856 |
+
"learning_rate": 1.8901710402999065e-05,
|
| 2857 |
+
"loss": 0.262,
|
| 2858 |
+
"step": 3750
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 1.7572633552014996,
|
| 2862 |
+
"eval_loss": 0.04190748557448387,
|
| 2863 |
+
"eval_pearson_cosine": 0.8188060652498521,
|
| 2864 |
+
"eval_pearson_dot": 0.7306266271006336,
|
| 2865 |
+
"eval_pearson_euclidean": 0.8067178845162717,
|
| 2866 |
+
"eval_pearson_manhattan": 0.8079651581429825,
|
| 2867 |
+
"eval_runtime": 3.6866,
|
| 2868 |
+
"eval_samples_per_second": 406.882,
|
| 2869 |
+
"eval_spearman_cosine": 0.8203796294288378,
|
| 2870 |
+
"eval_spearman_dot": 0.7294293478148326,
|
| 2871 |
+
"eval_spearman_euclidean": 0.8157749153170877,
|
| 2872 |
+
"eval_spearman_manhattan": 0.8170299724489123,
|
| 2873 |
+
"eval_steps_per_second": 25.498,
|
| 2874 |
+
"step": 3750
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 1.7619493908153703,
|
| 2878 |
+
"grad_norm": 1.78036367893219,
|
| 2879 |
+
"learning_rate": 1.8898781630740395e-05,
|
| 2880 |
+
"loss": 0.2441,
|
| 2881 |
+
"step": 3760
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 1.7666354264292408,
|
| 2885 |
+
"grad_norm": 2.0995302200317383,
|
| 2886 |
+
"learning_rate": 1.8895852858481728e-05,
|
| 2887 |
+
"loss": 0.2528,
|
| 2888 |
+
"step": 3770
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 1.7713214620431117,
|
| 2892 |
+
"grad_norm": 1.7772722244262695,
|
| 2893 |
+
"learning_rate": 1.8892924086223057e-05,
|
| 2894 |
+
"loss": 0.2305,
|
| 2895 |
+
"step": 3780
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 1.7760074976569822,
|
| 2899 |
+
"grad_norm": 2.158984661102295,
|
| 2900 |
+
"learning_rate": 1.8889995313964387e-05,
|
| 2901 |
+
"loss": 0.2374,
|
| 2902 |
+
"step": 3790
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 1.780693533270853,
|
| 2906 |
+
"grad_norm": 1.888215184211731,
|
| 2907 |
+
"learning_rate": 1.888706654170572e-05,
|
| 2908 |
+
"loss": 0.2458,
|
| 2909 |
+
"step": 3800
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 1.7853795688847236,
|
| 2913 |
+
"grad_norm": 2.109557867050171,
|
| 2914 |
+
"learning_rate": 1.888413776944705e-05,
|
| 2915 |
+
"loss": 0.2463,
|
| 2916 |
+
"step": 3810
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 1.790065604498594,
|
| 2920 |
+
"grad_norm": 1.715156078338623,
|
| 2921 |
+
"learning_rate": 1.8881208997188382e-05,
|
| 2922 |
+
"loss": 0.2421,
|
| 2923 |
+
"step": 3820
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 1.794751640112465,
|
| 2927 |
+
"grad_norm": 2.860567808151245,
|
| 2928 |
+
"learning_rate": 1.887828022492971e-05,
|
| 2929 |
+
"loss": 0.2728,
|
| 2930 |
+
"step": 3830
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 1.7994376757263355,
|
| 2934 |
+
"grad_norm": 1.527709722518921,
|
| 2935 |
+
"learning_rate": 1.887535145267104e-05,
|
| 2936 |
+
"loss": 0.1982,
|
| 2937 |
+
"step": 3840
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 1.8041237113402062,
|
| 2941 |
+
"grad_norm": 2.2306032180786133,
|
| 2942 |
+
"learning_rate": 1.8872422680412374e-05,
|
| 2943 |
+
"loss": 0.2269,
|
| 2944 |
+
"step": 3850
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 1.808809746954077,
|
| 2948 |
+
"grad_norm": 1.285987377166748,
|
| 2949 |
+
"learning_rate": 1.8869493908153703e-05,
|
| 2950 |
+
"loss": 0.1879,
|
| 2951 |
+
"step": 3860
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 1.8134957825679474,
|
| 2955 |
+
"grad_norm": 1.7815241813659668,
|
| 2956 |
+
"learning_rate": 1.8866565135895033e-05,
|
| 2957 |
+
"loss": 0.2337,
|
| 2958 |
+
"step": 3870
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 1.8181818181818183,
|
| 2962 |
+
"grad_norm": 1.5507057905197144,
|
| 2963 |
+
"learning_rate": 1.8863636363636366e-05,
|
| 2964 |
+
"loss": 0.2542,
|
| 2965 |
+
"step": 3880
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 1.8228678537956888,
|
| 2969 |
+
"grad_norm": 1.8540301322937012,
|
| 2970 |
+
"learning_rate": 1.8860707591377695e-05,
|
| 2971 |
+
"loss": 0.2668,
|
| 2972 |
+
"step": 3890
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 1.8275538894095595,
|
| 2976 |
+
"grad_norm": 1.5156047344207764,
|
| 2977 |
+
"learning_rate": 1.8857778819119025e-05,
|
| 2978 |
+
"loss": 0.2438,
|
| 2979 |
+
"step": 3900
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 1.8322399250234302,
|
| 2983 |
+
"grad_norm": 1.752375841140747,
|
| 2984 |
+
"learning_rate": 1.8854850046860358e-05,
|
| 2985 |
+
"loss": 0.2324,
|
| 2986 |
+
"step": 3910
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 1.8369259606373007,
|
| 2990 |
+
"grad_norm": 1.9103461503982544,
|
| 2991 |
+
"learning_rate": 1.8851921274601687e-05,
|
| 2992 |
+
"loss": 0.2049,
|
| 2993 |
+
"step": 3920
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 1.8416119962511717,
|
| 2997 |
+
"grad_norm": 2.043072462081909,
|
| 2998 |
+
"learning_rate": 1.884899250234302e-05,
|
| 2999 |
+
"loss": 0.2178,
|
| 3000 |
+
"step": 3930
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"epoch": 1.8462980318650422,
|
| 3004 |
+
"grad_norm": 1.7910971641540527,
|
| 3005 |
+
"learning_rate": 1.884606373008435e-05,
|
| 3006 |
+
"loss": 0.2527,
|
| 3007 |
+
"step": 3940
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 1.8509840674789129,
|
| 3011 |
+
"grad_norm": 2.146057605743408,
|
| 3012 |
+
"learning_rate": 1.8843134957825682e-05,
|
| 3013 |
+
"loss": 0.2235,
|
| 3014 |
+
"step": 3950
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 1.8556701030927836,
|
| 3018 |
+
"grad_norm": 2.3780410289764404,
|
| 3019 |
+
"learning_rate": 1.8840206185567012e-05,
|
| 3020 |
+
"loss": 0.2122,
|
| 3021 |
+
"step": 3960
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 1.860356138706654,
|
| 3025 |
+
"grad_norm": 1.7693490982055664,
|
| 3026 |
+
"learning_rate": 1.8837277413308345e-05,
|
| 3027 |
+
"loss": 0.2663,
|
| 3028 |
+
"step": 3970
|
| 3029 |
+
},
|
| 3030 |
+
{
|
| 3031 |
+
"epoch": 1.865042174320525,
|
| 3032 |
+
"grad_norm": 1.9694123268127441,
|
| 3033 |
+
"learning_rate": 1.8834348641049674e-05,
|
| 3034 |
+
"loss": 0.2357,
|
| 3035 |
+
"step": 3980
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 1.8697282099343955,
|
| 3039 |
+
"grad_norm": 1.9589118957519531,
|
| 3040 |
+
"learning_rate": 1.8831419868791004e-05,
|
| 3041 |
+
"loss": 0.2549,
|
| 3042 |
+
"step": 3990
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 1.8744142455482662,
|
| 3046 |
+
"grad_norm": 1.7447434663772583,
|
| 3047 |
+
"learning_rate": 1.8828491096532337e-05,
|
| 3048 |
+
"loss": 0.2269,
|
| 3049 |
+
"step": 4000
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 1.8744142455482662,
|
| 3053 |
+
"eval_loss": 0.03927910327911377,
|
| 3054 |
+
"eval_pearson_cosine": 0.8218360838151568,
|
| 3055 |
+
"eval_pearson_dot": 0.7383648469379267,
|
| 3056 |
+
"eval_pearson_euclidean": 0.79845453202784,
|
| 3057 |
+
"eval_pearson_manhattan": 0.8001969992210543,
|
| 3058 |
+
"eval_runtime": 3.608,
|
| 3059 |
+
"eval_samples_per_second": 415.741,
|
| 3060 |
+
"eval_spearman_cosine": 0.8235262235943273,
|
| 3061 |
+
"eval_spearman_dot": 0.7374591899505454,
|
| 3062 |
+
"eval_spearman_euclidean": 0.8094068736950194,
|
| 3063 |
+
"eval_spearman_manhattan": 0.8111787861762638,
|
| 3064 |
+
"eval_steps_per_second": 26.053,
|
| 3065 |
+
"step": 4000
|
| 3066 |
}
|
| 3067 |
],
|
| 3068 |
"logging_steps": 10,
|