End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [youdiniplays/tl-ceb-model-v2](https://huggingface.co/youdiniplays/tl-ceb-model-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4749
-- Bleu: 3.8223
-- Gen Len: 18.208
+- Loss: 0.4204
+- Bleu: 3.642
+- Gen Len: 18.299
 
 ## Model description
 
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
-| 0.6089        | 1.0   | 6516  | 0.5061          | 3.6822 | 18.235  |
-| 0.5687        | 2.0   | 13032 | 0.4956          | 3.7119 | 18.222  |
-| 0.525         | 3.0   | 19548 | 0.4869          | 3.8722 | 18.219  |
-| 0.488         | 4.0   | 26064 | 0.4795          | 3.7886 | 18.23   |
-| 0.4527        | 5.0   | 32580 | 0.4749          | 3.8223 | 18.208  |
+| 0.552         | 1.0   | 6516  | 0.4449          | 3.5422 | 18.301  |
+| 0.5154        | 2.0   | 13032 | 0.4440          | 3.4964 | 18.336  |
+| 0.4821        | 3.0   | 19548 | 0.4356          | 3.5832 | 18.309  |
+| 0.4398        | 4.0   | 26064 | 0.4224          | 3.6303 | 18.305  |
+| 0.4031        | 5.0   | 32580 | 0.4204          | 3.642  | 18.299  |
 
 
 ### Framework versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ad4fae3cb368e1108a698448c2180a61f7ce3dbdd3d4a5029c8f332c57c8a6
+oid sha256:c43564e930260fa3abbd24ef8bc8e2019043f8ab0ea3f357c88632def606095f
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc180befcc96c4d6cf5aa5864822fa50dd5216ecd55530428f649f0b5f9c56d
+oid sha256:5157a79613ec248ac8f7d1c8901dc35a0467ddf892a8d4eace27612fd7b9473d
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64996838d00245e925fc4810b966d5b49a79df56c1de39902bc8d8f7a6f38f1c
+oid sha256:af796267785b8380aa702da74322c3a84f42d9cab004eb98c1af133c0218d64a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e6f55bcc217a43fef0a794bb548420d34ff2f529f3e814b7aa83539a026216
+oid sha256:5b2103b3ba42c5a974b79f170c6d33390323651972016338595643ea512a6c2b
 size 1064

last-checkpoint/trainer_state.json

@@ -11,431 +11,431 @@
     {
       "epoch": 0.08,
       "learning_rate": 0.0009846531614487416,
-      "loss": 0.4942,
+      "loss": 0.5762,
       "step": 500
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0009693063228974831,
-      "loss": 0.5285,
+      "loss": 0.6042,
       "step": 1000
     },
     {
       "epoch": 0.23,
       "learning_rate": 0.0009539594843462247,
-      "loss": 0.5364,
+      "loss": 0.6024,
       "step": 1500
     },
     {
       "epoch": 0.31,
       "learning_rate": 0.0009386126457949663,
-      "loss": 0.5424,
+      "loss": 0.6057,
       "step": 2000
     },
     {
       "epoch": 0.38,
       "learning_rate": 0.0009232658072437078,
-      "loss": 0.5394,
+      "loss": 0.6143,
       "step": 2500
     },
     {
       "epoch": 0.46,
       "learning_rate": 0.0009079189686924494,
-      "loss": 0.5466,
+      "loss": 0.6081,
       "step": 3000
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.000892572130141191,
-      "loss": 0.5491,
+      "loss": 0.611,
       "step": 3500
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.0008772252915899325,
-      "loss": 0.5548,
+      "loss": 0.6104,
       "step": 4000
     },
     {
       "epoch": 0.69,
       "learning_rate": 0.0008619091467157766,
-      "loss": 0.5513,
+      "loss": 0.6154,
       "step": 4500
     },
     {
       "epoch": 0.77,
       "learning_rate": 0.0008465623081645181,
-      "loss": 0.5505,
+      "loss": 0.6151,
       "step": 5000
     },
     {
       "epoch": 0.84,
       "learning_rate": 0.0008312154696132597,
-      "loss": 0.5562,
+      "loss": 0.611,
       "step": 5500
     },
     {
       "epoch": 0.92,
       "learning_rate": 0.0008158686310620012,
-      "loss": 0.5522,
+      "loss": 0.617,
       "step": 6000
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0008005524861878454,
-      "loss": 0.552,
+      "loss": 0.6089,
       "step": 6500
     },
     {
       "epoch": 1.0,
-      "eval_bleu": 3.5422,
-      "eval_gen_len": 18.301,
-      "eval_loss": 0.44493627548217773,
-      "eval_runtime": 26.1469,
-      "eval_samples_per_second": 38.245,
-      "eval_steps_per_second": 2.409,
+      "eval_bleu": 3.6822,
+      "eval_gen_len": 18.235,
+      "eval_loss": 0.506125271320343,
+      "eval_runtime": 27.1471,
+      "eval_samples_per_second": 36.836,
+      "eval_steps_per_second": 2.321,
       "step": 6516
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.0007852056476365869,
-      "loss": 0.5122,
+      "loss": 0.5657,
       "step": 7000
     },
     {
       "epoch": 1.15,
       "learning_rate": 0.0007698588090853285,
-      "loss": 0.511,
+      "loss": 0.5623,
       "step": 7500
     },
     {
       "epoch": 1.23,
       "learning_rate": 0.0007545119705340699,
-      "loss": 0.5156,
+      "loss": 0.5669,
       "step": 8000
     },
     {
       "epoch": 1.3,
       "learning_rate": 0.000739195825659914,
-      "loss": 0.5192,
+      "loss": 0.5793,
       "step": 8500
     },
     {
       "epoch": 1.38,
       "learning_rate": 0.0007238489871086557,
-      "loss": 0.5172,
+      "loss": 0.5743,
       "step": 9000
     },
     {
       "epoch": 1.46,
-      "learning_rate": 0.0007085021485573971,
-      "loss": 0.5211,
+      "learning_rate": 0.0007085328422344997,
+      "loss": 0.5722,
       "step": 9500
     },
     {
       "epoch": 1.53,
-      "learning_rate": 0.0006931553100061387,
-      "loss": 0.5175,
+      "learning_rate": 0.0006931860036832413,
+      "loss": 0.5749,
       "step": 10000
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.0006778391651319828,
-      "loss": 0.5182,
+      "loss": 0.5776,
       "step": 10500
     },
     {
       "epoch": 1.69,
       "learning_rate": 0.0006624923265807244,
-      "loss": 0.5177,
+      "loss": 0.5694,
       "step": 11000
     },
     {
       "epoch": 1.76,
       "learning_rate": 0.0006471454880294659,
-      "loss": 0.5141,
+      "loss": 0.5716,
       "step": 11500
     },
     {
       "epoch": 1.84,
       "learning_rate": 0.0006317986494782076,
-      "loss": 0.5207,
+      "loss": 0.5665,
       "step": 12000
     },
     {
       "epoch": 1.92,
       "learning_rate": 0.000616451810926949,
-      "loss": 0.5154,
+      "loss": 0.5671,
       "step": 12500
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.0006011356660527931,
-      "loss": 0.5154,
+      "learning_rate": 0.0006011049723756906,
+      "loss": 0.5687,
       "step": 13000
     },
     {
       "epoch": 2.0,
-      "eval_bleu": 3.4964,
-      "eval_gen_len": 18.336,
-      "eval_loss": 0.44400554895401,
-      "eval_runtime": 24.0346,
-      "eval_samples_per_second": 41.607,
-      "eval_steps_per_second": 2.621,
+      "eval_bleu": 3.7119,
+      "eval_gen_len": 18.222,
+      "eval_loss": 0.495604932308197,
+      "eval_runtime": 23.8741,
+      "eval_samples_per_second": 41.886,
+      "eval_steps_per_second": 2.639,
       "step": 13032
     },
     {
       "epoch": 2.07,
       "learning_rate": 0.0005857888275015347,
-      "loss": 0.4746,
+      "loss": 0.5307,
       "step": 13500
     },
     {
       "epoch": 2.15,
       "learning_rate": 0.0005704419889502763,
-      "loss": 0.4745,
+      "loss": 0.5325,
       "step": 14000
     },
     {
       "epoch": 2.23,
       "learning_rate": 0.0005550951503990178,
-      "loss": 0.4775,
+      "loss": 0.5353,
       "step": 14500
     },
     {
       "epoch": 2.3,
-      "learning_rate": 0.0005397790055248619,
-      "loss": 0.4819,
+      "learning_rate": 0.0005397483118477594,
+      "loss": 0.5289,
       "step": 15000
     },
     {
       "epoch": 2.38,
-      "learning_rate": 0.0005244321669736034,
-      "loss": 0.4803,
+      "learning_rate": 0.0005244014732965009,
+      "loss": 0.5321,
       "step": 15500
     },
     {
       "epoch": 2.46,
       "learning_rate": 0.000509085328422345,
-      "loss": 0.4779,
+      "loss": 0.5271,
       "step": 16000
     },
     {
       "epoch": 2.53,
       "learning_rate": 0.0004937384898710866,
-      "loss": 0.4778,
+      "loss": 0.5295,
       "step": 16500
     },
     {
       "epoch": 2.61,
       "learning_rate": 0.00047839165131982814,
-      "loss": 0.4773,
+      "loss": 0.524,
       "step": 17000
     },
     {
       "epoch": 2.69,
-      "learning_rate": 0.0004630755064456722,
-      "loss": 0.4721,
+      "learning_rate": 0.0004630448127685697,
+      "loss": 0.526,
       "step": 17500
     },
     {
       "epoch": 2.76,
       "learning_rate": 0.00044772866789441376,
-      "loss": 0.4744,
+      "loss": 0.5323,
       "step": 18000
     },
     {
       "epoch": 2.84,
       "learning_rate": 0.00043238182934315537,
-      "loss": 0.4812,
+      "loss": 0.5236,
       "step": 18500
     },
     {
       "epoch": 2.92,
       "learning_rate": 0.00041703499079189687,
-      "loss": 0.4757,
+      "loss": 0.5266,
       "step": 19000
     },
     {
       "epoch": 2.99,
-      "learning_rate": 0.00040171884591774093,
-      "loss": 0.4821,
+      "learning_rate": 0.0004016881522406384,
+      "loss": 0.525,
       "step": 19500
     },
     {
       "epoch": 3.0,
-      "eval_bleu": 3.5832,
-      "eval_gen_len": 18.309,
-      "eval_loss": 0.4355914294719696,
-      "eval_runtime": 25.3154,
-      "eval_samples_per_second": 39.502,
-      "eval_steps_per_second": 2.489,
+      "eval_bleu": 3.8722,
+      "eval_gen_len": 18.219,
+      "eval_loss": 0.4868793785572052,
+      "eval_runtime": 23.2067,
+      "eval_samples_per_second": 43.091,
+      "eval_steps_per_second": 2.715,
       "step": 19548
     },
     {
       "epoch": 3.07,
       "learning_rate": 0.00038637200736648254,
-      "loss": 0.4381,
+      "loss": 0.4934,
       "step": 20000
     },
     {
       "epoch": 3.15,
       "learning_rate": 0.0003710251688152241,
-      "loss": 0.4407,
+      "loss": 0.4869,
       "step": 20500
     },
     {
       "epoch": 3.22,
       "learning_rate": 0.0003556783302639656,
-      "loss": 0.4427,
+      "loss": 0.4917,
       "step": 21000
     },
     {
       "epoch": 3.3,
       "learning_rate": 0.00034033149171270715,
-      "loss": 0.4375,
+      "loss": 0.4841,
       "step": 21500
     },
     {
       "epoch": 3.38,
-      "learning_rate": 0.00032498465316144876,
-      "loss": 0.4418,
+      "learning_rate": 0.00032501534683855126,
+      "loss": 0.4906,
       "step": 22000
     },
     {
       "epoch": 3.45,
-      "learning_rate": 0.0003096378146101903,
-      "loss": 0.4379,
+      "learning_rate": 0.0003096685082872928,
+      "loss": 0.4884,
       "step": 22500
     },
     {
       "epoch": 3.53,
-      "learning_rate": 0.00029429097605893187,
-      "loss": 0.4412,
+      "learning_rate": 0.0002943216697360344,
+      "loss": 0.486,
       "step": 23000
     },
     {
       "epoch": 3.61,
       "learning_rate": 0.00027897483118477593,
-      "loss": 0.4382,
+      "loss": 0.4932,
       "step": 23500
     },
     {
       "epoch": 3.68,
       "learning_rate": 0.00026365868631062,
-      "loss": 0.4397,
+      "loss": 0.4951,
       "step": 24000
     },
     {
       "epoch": 3.76,
       "learning_rate": 0.0002483118477593616,
-      "loss": 0.4368,
+      "loss": 0.4896,
       "step": 24500
     },
     {
       "epoch": 3.84,
       "learning_rate": 0.00023296500920810313,
-      "loss": 0.4377,
+      "loss": 0.4832,
       "step": 25000
     },
     {
       "epoch": 3.91,
       "learning_rate": 0.00021761817065684468,
-      "loss": 0.4387,
+      "loss": 0.4874,
       "step": 25500
     },
     {
       "epoch": 3.99,
       "learning_rate": 0.00020230202578268877,
-      "loss": 0.4398,
+      "loss": 0.488,
       "step": 26000
     },
     {
       "epoch": 4.0,
-      "eval_bleu": 3.6303,
-      "eval_gen_len": 18.305,
-      "eval_loss": 0.4224185645580292,
-      "eval_runtime": 23.5328,
-      "eval_samples_per_second": 42.494,
-      "eval_steps_per_second": 2.677,
+      "eval_bleu": 3.7886,
+      "eval_gen_len": 18.23,
+      "eval_loss": 0.4795362949371338,
+      "eval_runtime": 23.2422,
+      "eval_samples_per_second": 43.025,
+      "eval_steps_per_second": 2.711,
       "step": 26064
     },
     {
       "epoch": 4.07,
       "learning_rate": 0.00018695518723143033,
-      "loss": 0.4097,
+      "loss": 0.4583,
       "step": 26500
     },
     {
       "epoch": 4.14,
       "learning_rate": 0.00017160834868017188,
-      "loss": 0.4057,
+      "loss": 0.4495,
       "step": 27000
     },
     {
       "epoch": 4.22,
       "learning_rate": 0.00015626151012891346,
-      "loss": 0.4058,
+      "loss": 0.454,
       "step": 27500
     },
     {
       "epoch": 4.3,
       "learning_rate": 0.00014094536525475752,
-      "loss": 0.4049,
+      "loss": 0.4547,
       "step": 28000
     },
     {
       "epoch": 4.37,
       "learning_rate": 0.00012559852670349908,
-      "loss": 0.4058,
+      "loss": 0.4588,
       "step": 28500
     },
     {
       "epoch": 4.45,
       "learning_rate": 0.00011025168815224063,
-      "loss": 0.4055,
+      "loss": 0.453,
       "step": 29000
     },
     {
       "epoch": 4.53,
       "learning_rate": 9.49048496009822e-05,
-      "loss": 0.405,
+      "loss": 0.4549,
       "step": 29500
     },
     {
       "epoch": 4.6,
       "learning_rate": 7.955801104972376e-05,
-      "loss": 0.4032,
+      "loss": 0.4533,
       "step": 30000
     },
     {
       "epoch": 4.68,
       "learning_rate": 6.424186617556783e-05,
-      "loss": 0.4089,
+      "loss": 0.4495,
       "step": 30500
     },
     {
       "epoch": 4.76,
       "learning_rate": 4.8895027624309394e-05,
-      "loss": 0.4057,
+      "loss": 0.4555,
       "step": 31000
     },
     {
       "epoch": 4.83,
       "learning_rate": 3.3548189073050956e-05,
-      "loss": 0.3978,
+      "loss": 0.4563,
       "step": 31500
     },
     {
       "epoch": 4.91,
       "learning_rate": 1.820135052179251e-05,
-      "loss": 0.4011,
+      "loss": 0.4563,
       "step": 32000
     },
     {
       "epoch": 4.99,
-      "learning_rate": 2.85451197053407e-06,
-      "loss": 0.4031,
+      "learning_rate": 2.885205647636587e-06,
+      "loss": 0.4527,
       "step": 32500
     }
   ],
@@ -443,7 +443,7 @@
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.7234743264149504e+16,
+  "total_flos": 1.7233985138589696e+16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e769153e1530bd8e47a2f0b7a7df8c3974ef6c0591382fcb5397ece912b6194
+oid sha256:bbbc9f6fd02ff4264ade394c37847b822a605f5a9ef106ad63ba6639ed6bf7c2
 size 4792

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ad4fae3cb368e1108a698448c2180a61f7ce3dbdd3d4a5029c8f332c57c8a6
+oid sha256:7939d439dd6b3e66709084b0c9d94ee80069463f1d5f6e3750825ada2fa1b763
 size 242041896

runs/Jan20_14-02-20_b4d7770f8402/events.out.tfevents.1705759341.b4d7770f8402.183.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3edab546e5d925dcee711a42b20381a67d858e71be16204864be3da1412a165d
-size 17066
+oid sha256:74504e642541ceb221a3b10a3d5ce6d734f7ac4b7a30906a5ee0ec11deab1a47
+size 17803