Training in progress, step 200, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +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 +10 -80
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2066752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23835aa3baa0dcf892abf69863f1f0c1ea20a2c3908d99240a722cf7177381d0
|
| 3 |
size 2066752
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2162798
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a4936925c982bfdc0019eba2398a3694957cfa3a1ee1a1b0a1af1673552c9b0
|
| 3 |
size 2162798
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9927ec66b801c0f4855203d926f0323830f03e7abef37344059118107768879f
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:319005a7acd12212946f28795d824f4aa3bb9ae8b8a8fa8426acf8d1683c7711
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6e15e0019059647c2b2120160188600af8acd95ba49388e85735382c6fec110
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee6bd9483dc526698ba668e9cd1c38d218e9960bb3776fb46ce2d46403967e58
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e3c33d4b9177e702fbc3b7fe348e5bc53c0acdd468c8fa1d8d47c41439445bb
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:befcb54359f53141f634f3331a650f261e163fb42877249c8517ea83d36a7124
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d14477440f631aa977c46e3038b7d41c1e28d50b31065840e8a8470d3bdfe80
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a246be5cf8c2f6460956f9737bacb1b56ffc6195bb80d3c3d20f45b6c2226d5
|
| 3 |
size 15984
|
last-checkpoint/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 sha256:5197657cfe0474e002b5e477499687f2485548beb0dd654c8444eec350c0acb8
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -11,9 +11,9 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.3333333333333333,
|
| 13 |
"eval_loss": 10.375551223754883,
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second":
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
|
@@ -159,80 +159,10 @@
|
|
| 159 |
{
|
| 160 |
"epoch": 66.66666666666667,
|
| 161 |
"eval_loss": 9.681697845458984,
|
| 162 |
-
"eval_runtime": 0.
|
| 163 |
-
"eval_samples_per_second":
|
| 164 |
-
"eval_steps_per_second": 6.
|
| 165 |
"step": 200
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 70.0,
|
| 169 |
-
"grad_norm": 0.36328125,
|
| 170 |
-
"learning_rate": 4.12214747707527e-05,
|
| 171 |
-
"loss": 9.6678,
|
| 172 |
-
"step": 210
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 73.33333333333333,
|
| 176 |
-
"grad_norm": 0.36328125,
|
| 177 |
-
"learning_rate": 3.308693936411421e-05,
|
| 178 |
-
"loss": 9.6641,
|
| 179 |
-
"step": 220
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 76.66666666666667,
|
| 183 |
-
"grad_norm": 0.36328125,
|
| 184 |
-
"learning_rate": 2.5685517452260567e-05,
|
| 185 |
-
"loss": 9.6616,
|
| 186 |
-
"step": 230
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 80.0,
|
| 190 |
-
"grad_norm": 0.36328125,
|
| 191 |
-
"learning_rate": 1.9098300562505266e-05,
|
| 192 |
-
"loss": 9.6605,
|
| 193 |
-
"step": 240
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 83.33333333333333,
|
| 197 |
-
"grad_norm": 0.365234375,
|
| 198 |
-
"learning_rate": 1.339745962155613e-05,
|
| 199 |
-
"loss": 9.6596,
|
| 200 |
-
"step": 250
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 86.66666666666667,
|
| 204 |
-
"grad_norm": 0.36328125,
|
| 205 |
-
"learning_rate": 8.645454235739903e-06,
|
| 206 |
-
"loss": 9.6597,
|
| 207 |
-
"step": 260
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 90.0,
|
| 211 |
-
"grad_norm": 0.36328125,
|
| 212 |
-
"learning_rate": 4.8943483704846475e-06,
|
| 213 |
-
"loss": 9.6595,
|
| 214 |
-
"step": 270
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 93.33333333333333,
|
| 218 |
-
"grad_norm": 0.361328125,
|
| 219 |
-
"learning_rate": 2.1852399266194314e-06,
|
| 220 |
-
"loss": 9.6595,
|
| 221 |
-
"step": 280
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 96.66666666666667,
|
| 225 |
-
"grad_norm": 0.3671875,
|
| 226 |
-
"learning_rate": 5.478104631726711e-07,
|
| 227 |
-
"loss": 9.659,
|
| 228 |
-
"step": 290
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 100.0,
|
| 232 |
-
"grad_norm": 0.36328125,
|
| 233 |
-
"learning_rate": 0.0,
|
| 234 |
-
"loss": 9.6596,
|
| 235 |
-
"step": 300
|
| 236 |
}
|
| 237 |
],
|
| 238 |
"logging_steps": 10,
|
|
@@ -247,12 +177,12 @@
|
|
| 247 |
"should_evaluate": false,
|
| 248 |
"should_log": false,
|
| 249 |
"should_save": true,
|
| 250 |
-
"should_training_stop":
|
| 251 |
},
|
| 252 |
"attributes": {}
|
| 253 |
}
|
| 254 |
},
|
| 255 |
-
"total_flos":
|
| 256 |
"train_batch_size": 32,
|
| 257 |
"trial_name": null,
|
| 258 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 66.66666666666667,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.3333333333333333,
|
| 13 |
"eval_loss": 10.375551223754883,
|
| 14 |
+
"eval_runtime": 1.0009,
|
| 15 |
+
"eval_samples_per_second": 1499.719,
|
| 16 |
+
"eval_steps_per_second": 5.995,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
|
|
|
| 159 |
{
|
| 160 |
"epoch": 66.66666666666667,
|
| 161 |
"eval_loss": 9.681697845458984,
|
| 162 |
+
"eval_runtime": 0.9613,
|
| 163 |
+
"eval_samples_per_second": 1561.466,
|
| 164 |
+
"eval_steps_per_second": 6.242,
|
| 165 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
}
|
| 167 |
],
|
| 168 |
"logging_steps": 10,
|
|
|
|
| 177 |
"should_evaluate": false,
|
| 178 |
"should_log": false,
|
| 179 |
"should_save": true,
|
| 180 |
+
"should_training_stop": false
|
| 181 |
},
|
| 182 |
"attributes": {}
|
| 183 |
}
|
| 184 |
},
|
| 185 |
+
"total_flos": 327326839603200.0,
|
| 186 |
"train_batch_size": 32,
|
| 187 |
"trial_name": null,
|
| 188 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9629b97ec393ef093e4840cb93f3f7c6eafc6cfa1b3cb229133bf54718ca98cb
|
| 3 |
size 6840
|