Uploaded checkpoint-17500
Browse files- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- trainer_state.json +378 -3
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4986380064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55542cf68a7a56641df7a59e91b124f6d16eb72304a4aab6742a0f93a5b3d6a9
|
| 3 |
size 4986380064
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 399532808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5ecbf27a334befe14f1464c73a6a77128f6598de400961bb7d5097ecfb48f69
|
| 3 |
size 399532808
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2699039674
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10a07aad0a46264c45185ced9dd0645d835455a11a08613ac0cc316256bf2101
|
| 3 |
size 2699039674
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc99115bf5f04a1f69339b55b87574e78f76c0017fb7fbc54425e463c53fe09
|
| 3 |
+
size 14244
|
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:d75cd0c4e544f7391f9754fd838738017fc0e36a7e8de482816ca502f9dc5c07
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2257,6 +2257,381 @@
|
|
| 2257 |
"eval_samples_per_second": 10.165,
|
| 2258 |
"eval_steps_per_second": 10.165,
|
| 2259 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2260 |
}
|
| 2261 |
],
|
| 2262 |
"logging_steps": 100,
|
|
@@ -2264,7 +2639,7 @@
|
|
| 2264 |
"num_input_tokens_seen": 0,
|
| 2265 |
"num_train_epochs": 1,
|
| 2266 |
"save_steps": 2500,
|
| 2267 |
-
"total_flos": 2.
|
| 2268 |
"train_batch_size": 1,
|
| 2269 |
"trial_name": null,
|
| 2270 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4375,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 17500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2257 |
"eval_samples_per_second": 10.165,
|
| 2258 |
"eval_steps_per_second": 10.165,
|
| 2259 |
"step": 15000
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.38,
|
| 2263 |
+
"grad_norm": 6.856844902038574,
|
| 2264 |
+
"learning_rate": 5.025641025641026e-06,
|
| 2265 |
+
"loss": 0.6922,
|
| 2266 |
+
"step": 15100
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.38,
|
| 2270 |
+
"eval_loss": 0.6971193552017212,
|
| 2271 |
+
"eval_runtime": 98.4333,
|
| 2272 |
+
"eval_samples_per_second": 10.159,
|
| 2273 |
+
"eval_steps_per_second": 10.159,
|
| 2274 |
+
"step": 15100
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 0.38,
|
| 2278 |
+
"grad_norm": 4.937108039855957,
|
| 2279 |
+
"learning_rate": 4.923076923076924e-06,
|
| 2280 |
+
"loss": 0.6843,
|
| 2281 |
+
"step": 15200
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 0.38,
|
| 2285 |
+
"eval_loss": 0.6769686937332153,
|
| 2286 |
+
"eval_runtime": 98.4292,
|
| 2287 |
+
"eval_samples_per_second": 10.16,
|
| 2288 |
+
"eval_steps_per_second": 10.16,
|
| 2289 |
+
"step": 15200
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 0.38,
|
| 2293 |
+
"grad_norm": 7.337194442749023,
|
| 2294 |
+
"learning_rate": 4.820512820512821e-06,
|
| 2295 |
+
"loss": 0.7265,
|
| 2296 |
+
"step": 15300
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 0.38,
|
| 2300 |
+
"eval_loss": 0.6937099695205688,
|
| 2301 |
+
"eval_runtime": 98.3534,
|
| 2302 |
+
"eval_samples_per_second": 10.167,
|
| 2303 |
+
"eval_steps_per_second": 10.167,
|
| 2304 |
+
"step": 15300
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.39,
|
| 2308 |
+
"grad_norm": 6.544970512390137,
|
| 2309 |
+
"learning_rate": 4.717948717948718e-06,
|
| 2310 |
+
"loss": 0.6854,
|
| 2311 |
+
"step": 15400
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.39,
|
| 2315 |
+
"eval_loss": 0.6800307631492615,
|
| 2316 |
+
"eval_runtime": 98.3657,
|
| 2317 |
+
"eval_samples_per_second": 10.166,
|
| 2318 |
+
"eval_steps_per_second": 10.166,
|
| 2319 |
+
"step": 15400
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.39,
|
| 2323 |
+
"grad_norm": 4.409825801849365,
|
| 2324 |
+
"learning_rate": 4.615384615384616e-06,
|
| 2325 |
+
"loss": 0.7084,
|
| 2326 |
+
"step": 15500
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.39,
|
| 2330 |
+
"eval_loss": 0.6897458434104919,
|
| 2331 |
+
"eval_runtime": 98.3938,
|
| 2332 |
+
"eval_samples_per_second": 10.163,
|
| 2333 |
+
"eval_steps_per_second": 10.163,
|
| 2334 |
+
"step": 15500
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.39,
|
| 2338 |
+
"grad_norm": 4.764963150024414,
|
| 2339 |
+
"learning_rate": 4.512820512820513e-06,
|
| 2340 |
+
"loss": 0.6835,
|
| 2341 |
+
"step": 15600
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.39,
|
| 2345 |
+
"eval_loss": 0.6795360445976257,
|
| 2346 |
+
"eval_runtime": 98.3753,
|
| 2347 |
+
"eval_samples_per_second": 10.165,
|
| 2348 |
+
"eval_steps_per_second": 10.165,
|
| 2349 |
+
"step": 15600
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.39,
|
| 2353 |
+
"grad_norm": 4.578685283660889,
|
| 2354 |
+
"learning_rate": 4.4102564102564104e-06,
|
| 2355 |
+
"loss": 0.6789,
|
| 2356 |
+
"step": 15700
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.39,
|
| 2360 |
+
"eval_loss": 0.6842684149742126,
|
| 2361 |
+
"eval_runtime": 98.3424,
|
| 2362 |
+
"eval_samples_per_second": 10.169,
|
| 2363 |
+
"eval_steps_per_second": 10.169,
|
| 2364 |
+
"step": 15700
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.4,
|
| 2368 |
+
"grad_norm": 7.085032939910889,
|
| 2369 |
+
"learning_rate": 4.307692307692308e-06,
|
| 2370 |
+
"loss": 0.6473,
|
| 2371 |
+
"step": 15800
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.4,
|
| 2375 |
+
"eval_loss": 0.6702744364738464,
|
| 2376 |
+
"eval_runtime": 98.3744,
|
| 2377 |
+
"eval_samples_per_second": 10.165,
|
| 2378 |
+
"eval_steps_per_second": 10.165,
|
| 2379 |
+
"step": 15800
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 0.4,
|
| 2383 |
+
"grad_norm": 9.547301292419434,
|
| 2384 |
+
"learning_rate": 4.2051282051282055e-06,
|
| 2385 |
+
"loss": 0.6666,
|
| 2386 |
+
"step": 15900
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 0.4,
|
| 2390 |
+
"eval_loss": 0.6775800585746765,
|
| 2391 |
+
"eval_runtime": 98.3228,
|
| 2392 |
+
"eval_samples_per_second": 10.171,
|
| 2393 |
+
"eval_steps_per_second": 10.171,
|
| 2394 |
+
"step": 15900
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 0.4,
|
| 2398 |
+
"grad_norm": 2.161081075668335,
|
| 2399 |
+
"learning_rate": 4.102564102564103e-06,
|
| 2400 |
+
"loss": 0.6968,
|
| 2401 |
+
"step": 16000
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 0.4,
|
| 2405 |
+
"eval_loss": 0.683419942855835,
|
| 2406 |
+
"eval_runtime": 98.4131,
|
| 2407 |
+
"eval_samples_per_second": 10.161,
|
| 2408 |
+
"eval_steps_per_second": 10.161,
|
| 2409 |
+
"step": 16000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.4,
|
| 2413 |
+
"grad_norm": 4.315452575683594,
|
| 2414 |
+
"learning_rate": 4.000000000000001e-06,
|
| 2415 |
+
"loss": 0.64,
|
| 2416 |
+
"step": 16100
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 0.4,
|
| 2420 |
+
"eval_loss": 0.6916409134864807,
|
| 2421 |
+
"eval_runtime": 98.331,
|
| 2422 |
+
"eval_samples_per_second": 10.17,
|
| 2423 |
+
"eval_steps_per_second": 10.17,
|
| 2424 |
+
"step": 16100
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.41,
|
| 2428 |
+
"grad_norm": 4.9351582527160645,
|
| 2429 |
+
"learning_rate": 3.897435897435898e-06,
|
| 2430 |
+
"loss": 0.6516,
|
| 2431 |
+
"step": 16200
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.41,
|
| 2435 |
+
"eval_loss": 0.6831104755401611,
|
| 2436 |
+
"eval_runtime": 98.342,
|
| 2437 |
+
"eval_samples_per_second": 10.169,
|
| 2438 |
+
"eval_steps_per_second": 10.169,
|
| 2439 |
+
"step": 16200
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.41,
|
| 2443 |
+
"grad_norm": 2.858851432800293,
|
| 2444 |
+
"learning_rate": 3.794871794871795e-06,
|
| 2445 |
+
"loss": 0.6626,
|
| 2446 |
+
"step": 16300
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.41,
|
| 2450 |
+
"eval_loss": 0.6660827398300171,
|
| 2451 |
+
"eval_runtime": 98.3507,
|
| 2452 |
+
"eval_samples_per_second": 10.168,
|
| 2453 |
+
"eval_steps_per_second": 10.168,
|
| 2454 |
+
"step": 16300
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 0.41,
|
| 2458 |
+
"grad_norm": 10.384642601013184,
|
| 2459 |
+
"learning_rate": 3.692307692307693e-06,
|
| 2460 |
+
"loss": 0.7119,
|
| 2461 |
+
"step": 16400
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 0.41,
|
| 2465 |
+
"eval_loss": 0.6715333461761475,
|
| 2466 |
+
"eval_runtime": 98.3678,
|
| 2467 |
+
"eval_samples_per_second": 10.166,
|
| 2468 |
+
"eval_steps_per_second": 10.166,
|
| 2469 |
+
"step": 16400
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 0.41,
|
| 2473 |
+
"grad_norm": 2.9744458198547363,
|
| 2474 |
+
"learning_rate": 3.58974358974359e-06,
|
| 2475 |
+
"loss": 0.6827,
|
| 2476 |
+
"step": 16500
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 0.41,
|
| 2480 |
+
"eval_loss": 0.6574322581291199,
|
| 2481 |
+
"eval_runtime": 98.3789,
|
| 2482 |
+
"eval_samples_per_second": 10.165,
|
| 2483 |
+
"eval_steps_per_second": 10.165,
|
| 2484 |
+
"step": 16500
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 0.41,
|
| 2488 |
+
"grad_norm": 3.588651657104492,
|
| 2489 |
+
"learning_rate": 3.487179487179487e-06,
|
| 2490 |
+
"loss": 0.7398,
|
| 2491 |
+
"step": 16600
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 0.41,
|
| 2495 |
+
"eval_loss": 0.6578336358070374,
|
| 2496 |
+
"eval_runtime": 98.3458,
|
| 2497 |
+
"eval_samples_per_second": 10.168,
|
| 2498 |
+
"eval_steps_per_second": 10.168,
|
| 2499 |
+
"step": 16600
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 0.42,
|
| 2503 |
+
"grad_norm": 3.190857410430908,
|
| 2504 |
+
"learning_rate": 3.384615384615385e-06,
|
| 2505 |
+
"loss": 0.6553,
|
| 2506 |
+
"step": 16700
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 0.42,
|
| 2510 |
+
"eval_loss": 0.6542092561721802,
|
| 2511 |
+
"eval_runtime": 98.3756,
|
| 2512 |
+
"eval_samples_per_second": 10.165,
|
| 2513 |
+
"eval_steps_per_second": 10.165,
|
| 2514 |
+
"step": 16700
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 0.42,
|
| 2518 |
+
"grad_norm": 3.513176441192627,
|
| 2519 |
+
"learning_rate": 3.2820512820512823e-06,
|
| 2520 |
+
"loss": 0.6531,
|
| 2521 |
+
"step": 16800
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.42,
|
| 2525 |
+
"eval_loss": 0.6713552474975586,
|
| 2526 |
+
"eval_runtime": 98.3796,
|
| 2527 |
+
"eval_samples_per_second": 10.165,
|
| 2528 |
+
"eval_steps_per_second": 10.165,
|
| 2529 |
+
"step": 16800
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.42,
|
| 2533 |
+
"grad_norm": 5.897684574127197,
|
| 2534 |
+
"learning_rate": 3.1794871794871795e-06,
|
| 2535 |
+
"loss": 0.6923,
|
| 2536 |
+
"step": 16900
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.42,
|
| 2540 |
+
"eval_loss": 0.6415435075759888,
|
| 2541 |
+
"eval_runtime": 98.3575,
|
| 2542 |
+
"eval_samples_per_second": 10.167,
|
| 2543 |
+
"eval_steps_per_second": 10.167,
|
| 2544 |
+
"step": 16900
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.42,
|
| 2548 |
+
"grad_norm": 5.851967811584473,
|
| 2549 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 2550 |
+
"loss": 0.6582,
|
| 2551 |
+
"step": 17000
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.42,
|
| 2555 |
+
"eval_loss": 0.6755939722061157,
|
| 2556 |
+
"eval_runtime": 98.3485,
|
| 2557 |
+
"eval_samples_per_second": 10.168,
|
| 2558 |
+
"eval_steps_per_second": 10.168,
|
| 2559 |
+
"step": 17000
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 0.43,
|
| 2563 |
+
"grad_norm": 3.1814448833465576,
|
| 2564 |
+
"learning_rate": 2.9743589743589746e-06,
|
| 2565 |
+
"loss": 0.6471,
|
| 2566 |
+
"step": 17100
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 0.43,
|
| 2570 |
+
"eval_loss": 0.6580842733383179,
|
| 2571 |
+
"eval_runtime": 98.3328,
|
| 2572 |
+
"eval_samples_per_second": 10.17,
|
| 2573 |
+
"eval_steps_per_second": 10.17,
|
| 2574 |
+
"step": 17100
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 0.43,
|
| 2578 |
+
"grad_norm": 3.3297533988952637,
|
| 2579 |
+
"learning_rate": 2.8717948717948717e-06,
|
| 2580 |
+
"loss": 0.6238,
|
| 2581 |
+
"step": 17200
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.43,
|
| 2585 |
+
"eval_loss": 0.6540150046348572,
|
| 2586 |
+
"eval_runtime": 98.392,
|
| 2587 |
+
"eval_samples_per_second": 10.163,
|
| 2588 |
+
"eval_steps_per_second": 10.163,
|
| 2589 |
+
"step": 17200
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 0.43,
|
| 2593 |
+
"grad_norm": 4.152995586395264,
|
| 2594 |
+
"learning_rate": 2.7692307692307697e-06,
|
| 2595 |
+
"loss": 0.6523,
|
| 2596 |
+
"step": 17300
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 0.43,
|
| 2600 |
+
"eval_loss": 0.6668370366096497,
|
| 2601 |
+
"eval_runtime": 98.343,
|
| 2602 |
+
"eval_samples_per_second": 10.168,
|
| 2603 |
+
"eval_steps_per_second": 10.168,
|
| 2604 |
+
"step": 17300
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 0.43,
|
| 2608 |
+
"grad_norm": 8.26444149017334,
|
| 2609 |
+
"learning_rate": 2.666666666666667e-06,
|
| 2610 |
+
"loss": 0.6453,
|
| 2611 |
+
"step": 17400
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 0.43,
|
| 2615 |
+
"eval_loss": 0.6706939935684204,
|
| 2616 |
+
"eval_runtime": 98.3728,
|
| 2617 |
+
"eval_samples_per_second": 10.165,
|
| 2618 |
+
"eval_steps_per_second": 10.165,
|
| 2619 |
+
"step": 17400
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.44,
|
| 2623 |
+
"grad_norm": 4.3345627784729,
|
| 2624 |
+
"learning_rate": 2.564102564102564e-06,
|
| 2625 |
+
"loss": 0.6436,
|
| 2626 |
+
"step": 17500
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.44,
|
| 2630 |
+
"eval_loss": 0.6370129585266113,
|
| 2631 |
+
"eval_runtime": 98.3453,
|
| 2632 |
+
"eval_samples_per_second": 10.168,
|
| 2633 |
+
"eval_steps_per_second": 10.168,
|
| 2634 |
+
"step": 17500
|
| 2635 |
}
|
| 2636 |
],
|
| 2637 |
"logging_steps": 100,
|
|
|
|
| 2639 |
"num_input_tokens_seen": 0,
|
| 2640 |
"num_train_epochs": 1,
|
| 2641 |
"save_steps": 2500,
|
| 2642 |
+
"total_flos": 2.7533972078592e+17,
|
| 2643 |
"train_batch_size": 1,
|
| 2644 |
"trial_name": null,
|
| 2645 |
"trial_params": null
|