Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HealthTeam commited on
Commit
58148d9
•
1 Parent(s): c032c2b

Training in progress, step 187816

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:dab7c11e32bc742d74bdc97f13f6eba893be4230d872eaecd0689a72f1fc3083
3
  size 2401461637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8dc1533667dc1e5d8754a77682404d92df2ed864b7d3231ea835c0fe8164152
3
  size 2401461637
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c2991727b803e8a0b02542f03f6557f0258a9e36d172bbf826844685e5c5185
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09b26a6cf4f4fcffcf0d3d40bd588e02142cf71d98c403f62ffa3a24a62fd35
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:a7fc5cf4ee407f42d02567591ae73b57604321015aed2152689ffa91a768c5cd
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7abbc3674fcc879cafecbf33145badc8ed83c64ea9c1dd9b26cb200ce8d10b4
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c9fc3a1a25e64cc5d7eeddd2fe8bdbd04e891f66624bb894c6a839cce384bc5
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bede8f6a32f621408b9de8844a576e6a3d9ef01c46428875735af558fc7f135c
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": 2.629615304513403,
5
- "global_step": 176768,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2142,11 +2142,143 @@
2142
  "learning_rate": 2.4958099035038134e-06,
2143
  "loss": 2.7393,
2144
  "step": 176500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2145
  }
2146
  ],
2147
  "max_steps": 201666,
2148
  "num_train_epochs": 3,
2149
- "total_flos": 2.0788079286996173e+17,
2150
  "trial_name": null,
2151
  "trial_params": null
2152
  }
 
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,
 
2142
  "learning_rate": 2.4958099035038134e-06,
2143
  "loss": 2.7393,
2144
  "step": 176500
2145
+ },
2146
+ {
2147
+ "epoch": 2.63,
2148
+ "learning_rate": 2.446222962720538e-06,
2149
+ "loss": 2.7727,
2150
+ "step": 177000
2151
+ },
2152
+ {
2153
+ "epoch": 2.64,
2154
+ "learning_rate": 2.396636021937263e-06,
2155
+ "loss": 2.736,
2156
+ "step": 177500
2157
+ },
2158
+ {
2159
+ "epoch": 2.65,
2160
+ "learning_rate": 2.3470490811539874e-06,
2161
+ "loss": 2.7546,
2162
+ "step": 178000
2163
+ },
2164
+ {
2165
+ "epoch": 2.66,
2166
+ "learning_rate": 2.297462140370712e-06,
2167
+ "loss": 2.7601,
2168
+ "step": 178500
2169
+ },
2170
+ {
2171
+ "epoch": 2.66,
2172
+ "learning_rate": 2.247875199587437e-06,
2173
+ "loss": 2.7456,
2174
+ "step": 179000
2175
+ },
2176
+ {
2177
+ "epoch": 2.67,
2178
+ "learning_rate": 2.1982882588041614e-06,
2179
+ "loss": 2.76,
2180
+ "step": 179500
2181
+ },
2182
+ {
2183
+ "epoch": 2.68,
2184
+ "learning_rate": 2.1487013180208863e-06,
2185
+ "loss": 2.7396,
2186
+ "step": 180000
2187
+ },
2188
+ {
2189
+ "epoch": 2.69,
2190
+ "learning_rate": 2.099114377237611e-06,
2191
+ "loss": 2.761,
2192
+ "step": 180500
2193
+ },
2194
+ {
2195
+ "epoch": 2.69,
2196
+ "learning_rate": 2.0495274364543354e-06,
2197
+ "loss": 2.7603,
2198
+ "step": 181000
2199
+ },
2200
+ {
2201
+ "epoch": 2.7,
2202
+ "learning_rate": 1.9999404956710603e-06,
2203
+ "loss": 2.7614,
2204
+ "step": 181500
2205
+ },
2206
+ {
2207
+ "epoch": 2.71,
2208
+ "learning_rate": 1.950353554887785e-06,
2209
+ "loss": 2.7638,
2210
+ "step": 182000
2211
+ },
2212
+ {
2213
+ "epoch": 2.71,
2214
+ "learning_rate": 1.9007666141045096e-06,
2215
+ "loss": 2.7806,
2216
+ "step": 182500
2217
+ },
2218
+ {
2219
+ "epoch": 2.72,
2220
+ "learning_rate": 1.8511796733212343e-06,
2221
+ "loss": 2.7561,
2222
+ "step": 183000
2223
+ },
2224
+ {
2225
+ "epoch": 2.73,
2226
+ "learning_rate": 1.801592732537959e-06,
2227
+ "loss": 2.7473,
2228
+ "step": 183500
2229
+ },
2230
+ {
2231
+ "epoch": 2.74,
2232
+ "learning_rate": 1.7520057917546838e-06,
2233
+ "loss": 2.7405,
2234
+ "step": 184000
2235
+ },
2236
+ {
2237
+ "epoch": 2.74,
2238
+ "learning_rate": 1.7024188509714083e-06,
2239
+ "loss": 2.742,
2240
+ "step": 184500
2241
+ },
2242
+ {
2243
+ "epoch": 2.75,
2244
+ "learning_rate": 1.652831910188133e-06,
2245
+ "loss": 2.7387,
2246
+ "step": 185000
2247
+ },
2248
+ {
2249
+ "epoch": 2.76,
2250
+ "learning_rate": 1.6032449694048577e-06,
2251
+ "loss": 2.7681,
2252
+ "step": 185500
2253
+ },
2254
+ {
2255
+ "epoch": 2.77,
2256
+ "learning_rate": 1.5536580286215825e-06,
2257
+ "loss": 2.7599,
2258
+ "step": 186000
2259
+ },
2260
+ {
2261
+ "epoch": 2.77,
2262
+ "learning_rate": 1.504071087838307e-06,
2263
+ "loss": 2.7497,
2264
+ "step": 186500
2265
+ },
2266
+ {
2267
+ "epoch": 2.78,
2268
+ "learning_rate": 1.4544841470550317e-06,
2269
+ "loss": 2.7417,
2270
+ "step": 187000
2271
+ },
2272
+ {
2273
+ "epoch": 2.79,
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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c2991727b803e8a0b02542f03f6557f0258a9e36d172bbf826844685e5c5185
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09b26a6cf4f4fcffcf0d3d40bd588e02142cf71d98c403f62ffa3a24a62fd35
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:a5e4f0ed5da7d5706ba5011c8ef271d1d10c08c2a0dcb249dc605188bb19cec7
3
- size 61151
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1176956b862393d9e6e40ad4a6cb5dc97a6996dda8497059a0c5e1a17ea27e09
3
+ size 64671