AlexZigma commited on
Commit
2aaf5b5
1 Parent(s): 974e009

Training in progress, step 3000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:751681fff189905e64d2ae7d13632b19604941456b96bf64a11dc8220255f98d
3
  size 2073453967
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a71d9e3d892503eceeb874150567630d5ca7891c64bc8d57a36f141207d6d60
3
  size 2073453967
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab68e42afc0d1d87e8261e067db8957a01009cb8fb6d5a40b42c2a2ec32dab84
3
  size 1036763317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8039b6e3103ec7096ad872005c3540f3a27d4b4d11f388d0fc57f063fbeaff
3
  size 1036763317
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08674f71bafc22c499a5cbc265132cc8d6ad45e22d1afa588bee4734a92e1cd5
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db8241e99d0a120ac47b3a2d4b91d99919947c28166e60c69937b30e9123a6b
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88b0035a4650983d26589711937eadc9ba441d8ec9849d4bd0d0c7fbc7757356
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d83271d1cc3591071f2842c6ca7becc46867cb039622ffd40c96568bb351033
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": 1.4732965009208103,
5
- "global_step": 2400,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -246,11 +246,71 @@
246
  "eval_samples_per_second": 1.16,
247
  "eval_steps_per_second": 0.147,
248
  "step": 2400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
249
  }
250
  ],
251
  "max_steps": 3258,
252
  "num_train_epochs": 2,
253
- "total_flos": 1.6350382469320704e+19,
254
  "trial_name": null,
255
  "trial_params": null
256
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8416206261510129,
5
+ "global_step": 3000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
246
  "eval_samples_per_second": 1.16,
247
  "eval_steps_per_second": 0.147,
248
  "step": 2400
249
+ },
250
+ {
251
+ "epoch": 1.6,
252
+ "learning_rate": 1.0098219766728055e-05,
253
+ "loss": 1.0909,
254
+ "step": 2600
255
+ },
256
+ {
257
+ "epoch": 1.6,
258
+ "eval_bleu": 4.4782,
259
+ "eval_gen_len": 9.533199195171026,
260
+ "eval_loss": 1.3094563484191895,
261
+ "eval_rouge1": 30.0233,
262
+ "eval_rouge2": 8.4896,
263
+ "eval_rougeL": 29.2562,
264
+ "eval_rougeLsum": 29.2375,
265
+ "eval_runtime": 429.1068,
266
+ "eval_samples_per_second": 1.158,
267
+ "eval_steps_per_second": 0.147,
268
+ "step": 2600
269
+ },
270
+ {
271
+ "epoch": 1.72,
272
+ "learning_rate": 7.0288520564763666e-06,
273
+ "loss": 1.1205,
274
+ "step": 2800
275
+ },
276
+ {
277
+ "epoch": 1.72,
278
+ "eval_bleu": 4.44,
279
+ "eval_gen_len": 9.533199195171026,
280
+ "eval_loss": 1.2991728782653809,
281
+ "eval_rouge1": 29.7164,
282
+ "eval_rouge2": 8.007,
283
+ "eval_rougeL": 28.5027,
284
+ "eval_rougeLsum": 28.5018,
285
+ "eval_runtime": 423.565,
286
+ "eval_samples_per_second": 1.173,
287
+ "eval_steps_per_second": 0.149,
288
+ "step": 2800
289
+ },
290
+ {
291
+ "epoch": 1.84,
292
+ "learning_rate": 3.959484346224679e-06,
293
+ "loss": 1.1069,
294
+ "step": 3000
295
+ },
296
+ {
297
+ "epoch": 1.84,
298
+ "eval_bleu": 4.6065,
299
+ "eval_gen_len": 9.533199195171026,
300
+ "eval_loss": 1.283018708229065,
301
+ "eval_rouge1": 29.851,
302
+ "eval_rouge2": 8.4312,
303
+ "eval_rougeL": 28.8139,
304
+ "eval_rougeLsum": 28.8205,
305
+ "eval_runtime": 425.8103,
306
+ "eval_samples_per_second": 1.167,
307
+ "eval_steps_per_second": 0.148,
308
+ "step": 3000
309
  }
310
  ],
311
  "max_steps": 3258,
312
  "num_train_epochs": 2,
313
+ "total_flos": 2.0430752431509504e+19,
314
  "trial_name": null,
315
  "trial_params": null
316
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8572277769ba3533fac8fd9e6dbc3818380e2f979b5abf90d9235eb3442b42da
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c55bec6f2294d365c3cdee3d09e5d8253c99a78af7df3ab6cf2c5b8c3716f8
3
  size 4219
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab68e42afc0d1d87e8261e067db8957a01009cb8fb6d5a40b42c2a2ec32dab84
3
  size 1036763317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8039b6e3103ec7096ad872005c3540f3a27d4b4d11f388d0fc57f063fbeaff
3
  size 1036763317
runs/Jul13_08-26-36_0388ea093402/events.out.tfevents.1689236820.0388ea093402.188.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7642427c0c4070cbedd0b981376fe5945c845adb976a118f8f0e21a487d4a2
3
+ size 34237
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8572277769ba3533fac8fd9e6dbc3818380e2f979b5abf90d9235eb3442b42da
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c55bec6f2294d365c3cdee3d09e5d8253c99a78af7df3ab6cf2c5b8c3716f8
3
  size 4219