Instructions to use Team-PIXEL/pixel-small-words with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Team-PIXEL/pixel-small-words with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForPreTraining model = AutoModelForPreTraining.from_pretrained("Team-PIXEL/pixel-small-words", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 120000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 202194449
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1e0bc201a48037c117cf182b1af5c6f4d1de81608cab594dcb7b0df89e16d70
|
| 3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102501541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23090dda99868abea6a7796871fd763d22a4e00fff59d8a65d78e70f06487cae
|
| 3 |
size 102501541
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc32c00ec3a14d611f2862ea85a2017db3bf307d1ec3917eebae34f57b515
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60ddf5c33f60196860027b40e8443017b8ed479cc5dfb73f8a076fe07f546fd4
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2206,11 +2206,211 @@
|
|
| 2206 |
"eval_samples_per_second": 824.682,
|
| 2207 |
"eval_steps_per_second": 13.195,
|
| 2208 |
"step": 110000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2209 |
}
|
| 2210 |
],
|
| 2211 |
"max_steps": 500000,
|
| 2212 |
"num_train_epochs": 13,
|
| 2213 |
-
"total_flos": 3.
|
| 2214 |
"trial_name": null,
|
| 2215 |
"trial_params": null
|
| 2216 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.058259850145267,
|
| 5 |
+
"global_step": 120000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2206 |
"eval_samples_per_second": 824.682,
|
| 2207 |
"eval_steps_per_second": 13.195,
|
| 2208 |
"step": 110000
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.82,
|
| 2212 |
+
"learning_rate": 0.0002774275491977922,
|
| 2213 |
+
"loss": 0.3111,
|
| 2214 |
+
"step": 110500
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.83,
|
| 2218 |
+
"learning_rate": 0.0002771699479464853,
|
| 2219 |
+
"loss": 0.3089,
|
| 2220 |
+
"step": 111000
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 2.83,
|
| 2224 |
+
"eval_loss": 0.8333858847618103,
|
| 2225 |
+
"eval_runtime": 1.2664,
|
| 2226 |
+
"eval_samples_per_second": 789.664,
|
| 2227 |
+
"eval_steps_per_second": 12.635,
|
| 2228 |
+
"step": 111000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.84,
|
| 2232 |
+
"learning_rate": 0.00027691101066420104,
|
| 2233 |
+
"loss": 0.3091,
|
| 2234 |
+
"step": 111500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 2.85,
|
| 2238 |
+
"learning_rate": 0.0002766507401826361,
|
| 2239 |
+
"loss": 0.3089,
|
| 2240 |
+
"step": 112000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 2.85,
|
| 2244 |
+
"eval_loss": 0.8437691330909729,
|
| 2245 |
+
"eval_runtime": 1.2859,
|
| 2246 |
+
"eval_samples_per_second": 777.686,
|
| 2247 |
+
"eval_steps_per_second": 12.443,
|
| 2248 |
+
"step": 112000
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 2.87,
|
| 2252 |
+
"learning_rate": 0.0002763891393480666,
|
| 2253 |
+
"loss": 0.3086,
|
| 2254 |
+
"step": 112500
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 2.88,
|
| 2258 |
+
"learning_rate": 0.0002761262110213175,
|
| 2259 |
+
"loss": 0.3088,
|
| 2260 |
+
"step": 113000
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 2.88,
|
| 2264 |
+
"eval_loss": 0.8328044414520264,
|
| 2265 |
+
"eval_runtime": 1.2617,
|
| 2266 |
+
"eval_samples_per_second": 792.564,
|
| 2267 |
+
"eval_steps_per_second": 12.681,
|
| 2268 |
+
"step": 113000
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 2.89,
|
| 2272 |
+
"learning_rate": 0.00027586195807773083,
|
| 2273 |
+
"loss": 0.308,
|
| 2274 |
+
"step": 113500
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 2.91,
|
| 2278 |
+
"learning_rate": 0.00027559638340713435,
|
| 2279 |
+
"loss": 0.3085,
|
| 2280 |
+
"step": 114000
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 2.91,
|
| 2284 |
+
"eval_loss": 0.831738293170929,
|
| 2285 |
+
"eval_runtime": 1.2398,
|
| 2286 |
+
"eval_samples_per_second": 806.55,
|
| 2287 |
+
"eval_steps_per_second": 12.905,
|
| 2288 |
+
"step": 114000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 2.92,
|
| 2292 |
+
"learning_rate": 0.00027532948991381025,
|
| 2293 |
+
"loss": 0.3079,
|
| 2294 |
+
"step": 114500
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 2.93,
|
| 2298 |
+
"learning_rate": 0.00027506128051646287,
|
| 2299 |
+
"loss": 0.3097,
|
| 2300 |
+
"step": 115000
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 2.93,
|
| 2304 |
+
"eval_loss": 0.8462249636650085,
|
| 2305 |
+
"eval_runtime": 1.2264,
|
| 2306 |
+
"eval_samples_per_second": 815.428,
|
| 2307 |
+
"eval_steps_per_second": 13.047,
|
| 2308 |
+
"step": 115000
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 2.94,
|
| 2312 |
+
"learning_rate": 0.00027479175814818733,
|
| 2313 |
+
"loss": 0.3082,
|
| 2314 |
+
"step": 115500
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 2.96,
|
| 2318 |
+
"learning_rate": 0.000274520925756437,
|
| 2319 |
+
"loss": 0.3082,
|
| 2320 |
+
"step": 116000
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.96,
|
| 2324 |
+
"eval_loss": 0.8435738682746887,
|
| 2325 |
+
"eval_runtime": 1.3152,
|
| 2326 |
+
"eval_samples_per_second": 760.322,
|
| 2327 |
+
"eval_steps_per_second": 12.165,
|
| 2328 |
+
"step": 116000
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 2.97,
|
| 2332 |
+
"learning_rate": 0.00027424878630299157,
|
| 2333 |
+
"loss": 0.3074,
|
| 2334 |
+
"step": 116500
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.98,
|
| 2338 |
+
"learning_rate": 0.0002739753427639244,
|
| 2339 |
+
"loss": 0.3077,
|
| 2340 |
+
"step": 117000
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.98,
|
| 2344 |
+
"eval_loss": 0.8435785174369812,
|
| 2345 |
+
"eval_runtime": 1.2302,
|
| 2346 |
+
"eval_samples_per_second": 812.844,
|
| 2347 |
+
"eval_steps_per_second": 13.006,
|
| 2348 |
+
"step": 117000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.99,
|
| 2352 |
+
"learning_rate": 0.0002737005981295704,
|
| 2353 |
+
"loss": 0.3078,
|
| 2354 |
+
"step": 117500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 3.01,
|
| 2358 |
+
"learning_rate": 0.0002734245554044927,
|
| 2359 |
+
"loss": 0.3086,
|
| 2360 |
+
"step": 118000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 3.01,
|
| 2364 |
+
"eval_loss": 0.8482502698898315,
|
| 2365 |
+
"eval_runtime": 1.3338,
|
| 2366 |
+
"eval_samples_per_second": 749.745,
|
| 2367 |
+
"eval_steps_per_second": 11.996,
|
| 2368 |
+
"step": 118000
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 3.02,
|
| 2372 |
+
"learning_rate": 0.0002731472176074504,
|
| 2373 |
+
"loss": 0.307,
|
| 2374 |
+
"step": 118500
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 3.03,
|
| 2378 |
+
"learning_rate": 0.0002728685877713653,
|
| 2379 |
+
"loss": 0.3072,
|
| 2380 |
+
"step": 119000
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 3.03,
|
| 2384 |
+
"eval_loss": 0.8354719281196594,
|
| 2385 |
+
"eval_runtime": 1.4002,
|
| 2386 |
+
"eval_samples_per_second": 714.17,
|
| 2387 |
+
"eval_steps_per_second": 11.427,
|
| 2388 |
+
"step": 119000
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 3.05,
|
| 2392 |
+
"learning_rate": 0.0002725886689432884,
|
| 2393 |
+
"loss": 0.3075,
|
| 2394 |
+
"step": 119500
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 3.06,
|
| 2398 |
+
"learning_rate": 0.0002723074641843674,
|
| 2399 |
+
"loss": 0.3066,
|
| 2400 |
+
"step": 120000
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 3.06,
|
| 2404 |
+
"eval_loss": 0.8281124234199524,
|
| 2405 |
+
"eval_runtime": 1.3099,
|
| 2406 |
+
"eval_samples_per_second": 763.433,
|
| 2407 |
+
"eval_steps_per_second": 12.215,
|
| 2408 |
+
"step": 120000
|
| 2409 |
}
|
| 2410 |
],
|
| 2411 |
"max_steps": 500000,
|
| 2412 |
"num_train_epochs": 13,
|
| 2413 |
+
"total_flos": 3.833805228554865e+21,
|
| 2414 |
"trial_name": null,
|
| 2415 |
"trial_params": null
|
| 2416 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102501541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23090dda99868abea6a7796871fd763d22a4e00fff59d8a65d78e70f06487cae
|
| 3 |
size 102501541
|