Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
HealthTeam commited on
Commit
b16bd8b
•
1 Parent(s): 58148d9

Training in progress, step 198864

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +135 -3
  6. pytorch_model.bin +1 -1
  7. runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8dc1533667dc1e5d8754a77682404d92df2ed864b7d3231ea835c0fe8164152
3
  size 2401461637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cedde736261632f89acf33553d7f1b796fa4666797a76600bc7414afba87e83
3
  size 2401461637
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e09b26a6cf4f4fcffcf0d3d40bd588e02142cf71d98c403f62ffa3a24a62fd35
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c830ba03e87ef89c167a65183788768bf905dc7f4c689fe476c351a7fc9b93b
3
  size 1200739717
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7abbc3674fcc879cafecbf33145badc8ed83c64ea9c1dd9b26cb200ce8d10b4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd594782425d26032039a6c2b147e5861095f1958bd2b0f4a2e42679340bff32
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bede8f6a32f621408b9de8844a576e6a3d9ef01c46428875735af558fc7f135c
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9febce275791009bb39a3242ecdd95ff1e50bc7a7886ff99da486505feed461
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.793966261045491,
5
- "global_step": 187816,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2274,11 +2274,143 @@
2274
  "learning_rate": 1.4048972062717565e-06,
2275
  "loss": 2.739,
2276
  "step": 187500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2277
  }
2278
  ],
2279
  "max_steps": 201666,
2280
  "num_train_epochs": 3,
2281
- "total_flos": 2.2090056412387738e+17,
2282
  "trial_name": null,
2283
  "trial_params": null
2284
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.9583172175775787,
5
+ "global_step": 198864,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
2274
  "learning_rate": 1.4048972062717565e-06,
2275
  "loss": 2.739,
2276
  "step": 187500
2277
+ },
2278
+ {
2279
+ "epoch": 2.8,
2280
+ "learning_rate": 1.3553102654884812e-06,
2281
+ "loss": 2.7633,
2282
+ "step": 188000
2283
+ },
2284
+ {
2285
+ "epoch": 2.8,
2286
+ "learning_rate": 1.3057233247052057e-06,
2287
+ "loss": 2.7516,
2288
+ "step": 188500
2289
+ },
2290
+ {
2291
+ "epoch": 2.81,
2292
+ "learning_rate": 1.2561363839219304e-06,
2293
+ "loss": 2.7638,
2294
+ "step": 189000
2295
+ },
2296
+ {
2297
+ "epoch": 2.82,
2298
+ "learning_rate": 1.2065494431386552e-06,
2299
+ "loss": 2.7397,
2300
+ "step": 189500
2301
+ },
2302
+ {
2303
+ "epoch": 2.83,
2304
+ "learning_rate": 1.1569625023553797e-06,
2305
+ "loss": 2.7614,
2306
+ "step": 190000
2307
+ },
2308
+ {
2309
+ "epoch": 2.83,
2310
+ "learning_rate": 1.1073755615721044e-06,
2311
+ "loss": 2.7235,
2312
+ "step": 190500
2313
+ },
2314
+ {
2315
+ "epoch": 2.84,
2316
+ "learning_rate": 1.0577886207888292e-06,
2317
+ "loss": 2.7401,
2318
+ "step": 191000
2319
+ },
2320
+ {
2321
+ "epoch": 2.85,
2322
+ "learning_rate": 1.0082016800055539e-06,
2323
+ "loss": 2.7573,
2324
+ "step": 191500
2325
+ },
2326
+ {
2327
+ "epoch": 2.86,
2328
+ "learning_rate": 9.586147392222784e-07,
2329
+ "loss": 2.7452,
2330
+ "step": 192000
2331
+ },
2332
+ {
2333
+ "epoch": 2.86,
2334
+ "learning_rate": 9.090277984390032e-07,
2335
+ "loss": 2.7505,
2336
+ "step": 192500
2337
+ },
2338
+ {
2339
+ "epoch": 2.87,
2340
+ "learning_rate": 8.594408576557279e-07,
2341
+ "loss": 2.7233,
2342
+ "step": 193000
2343
+ },
2344
+ {
2345
+ "epoch": 2.88,
2346
+ "learning_rate": 8.098539168724526e-07,
2347
+ "loss": 2.7409,
2348
+ "step": 193500
2349
+ },
2350
+ {
2351
+ "epoch": 2.89,
2352
+ "learning_rate": 7.602669760891772e-07,
2353
+ "loss": 2.7424,
2354
+ "step": 194000
2355
+ },
2356
+ {
2357
+ "epoch": 2.89,
2358
+ "learning_rate": 7.10680035305902e-07,
2359
+ "loss": 2.7563,
2360
+ "step": 194500
2361
+ },
2362
+ {
2363
+ "epoch": 2.9,
2364
+ "learning_rate": 6.610930945226266e-07,
2365
+ "loss": 2.7478,
2366
+ "step": 195000
2367
+ },
2368
+ {
2369
+ "epoch": 2.91,
2370
+ "learning_rate": 6.115061537393512e-07,
2371
+ "loss": 2.7555,
2372
+ "step": 195500
2373
+ },
2374
+ {
2375
+ "epoch": 2.92,
2376
+ "learning_rate": 5.619192129560759e-07,
2377
+ "loss": 2.7679,
2378
+ "step": 196000
2379
+ },
2380
+ {
2381
+ "epoch": 2.92,
2382
+ "learning_rate": 5.123322721728006e-07,
2383
+ "loss": 2.7219,
2384
+ "step": 196500
2385
+ },
2386
+ {
2387
+ "epoch": 2.93,
2388
+ "learning_rate": 4.6274533138952524e-07,
2389
+ "loss": 2.7283,
2390
+ "step": 197000
2391
+ },
2392
+ {
2393
+ "epoch": 2.94,
2394
+ "learning_rate": 4.131583906062499e-07,
2395
+ "loss": 2.7703,
2396
+ "step": 197500
2397
+ },
2398
+ {
2399
+ "epoch": 2.95,
2400
+ "learning_rate": 3.6357144982297465e-07,
2401
+ "loss": 2.7606,
2402
+ "step": 198000
2403
+ },
2404
+ {
2405
+ "epoch": 2.95,
2406
+ "learning_rate": 3.1398450903969933e-07,
2407
+ "loss": 2.7247,
2408
+ "step": 198500
2409
  }
2410
  ],
2411
  "max_steps": 201666,
2412
  "num_train_epochs": 3,
2413
+ "total_flos": 2.3390721608830157e+17,
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:e09b26a6cf4f4fcffcf0d3d40bd588e02142cf71d98c403f62ffa3a24a62fd35
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c830ba03e87ef89c167a65183788768bf905dc7f4c689fe476c351a7fc9b93b
3
  size 1200739717
runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1176956b862393d9e6e40ad4a6cb5dc97a6996dda8497059a0c5e1a17ea27e09
3
- size 64671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3418c4d48d9655d66cec7f231aa9eca5c7d2436ae748697c02e220abc2d1378
3
+ size 68191