iter 3

README.md

@@ -2,7 +2,7 @@
 license: apache-2.0
 tags:
 - automatic-speech-recognition
-- /workspace/data/hy/noizy_student_2/
+- /workspace/data/hy/noizy_student_3/
 - generated_from_trainer
 model-index:
 - name: ''
@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the /WORKSPACE/DATA/HY/NOIZY_STUDENT_2/ - NA dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the /WORKSPACE/DATA/HY/NOIZY_STUDENT_3/ - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2249
-- Wer: 0.2783
-- Cer: 0.0508
+- Loss: 0.1827
+- Wer: 0.2389
+- Cer: 0.0427
 
 ## Model description
 
@@ -46,29 +46,29 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 1600
+- training_steps: 3200
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 4.9923        | 3.84  | 100  | 3.1562          | 1.0    | 1.0    |
-| 2.1775        | 7.69  | 200  | 0.4334          | 0.5804 | 0.1122 |
-| 1.3708        | 11.53 | 300  | 0.3106          | 0.4336 | 0.0797 |
-| 1.2266        | 15.38 | 400  | 0.2675          | 0.3673 | 0.0673 |
-| 1.093         | 19.23 | 500  | 0.2416          | 0.3501 | 0.0633 |
-| 0.989         | 23.08 | 600  | 0.2320          | 0.3251 | 0.0611 |
-| 0.9518        | 26.91 | 700  | 0.2413          | 0.3193 | 0.0584 |
-| 0.9075        | 30.76 | 800  | 0.2354          | 0.3201 | 0.0593 |
-| 0.878         | 34.61 | 900  | 0.2278          | 0.3126 | 0.0579 |
-| 0.8563        | 38.46 | 1000 | 0.2327          | 0.2963 | 0.0548 |
-| 0.8084        | 42.3  | 1100 | 0.2271          | 0.2923 | 0.0541 |
-| 0.7845        | 46.15 | 1200 | 0.2333          | 0.2951 | 0.0537 |
-| 0.7487        | 49.99 | 1300 | 0.2290          | 0.2888 | 0.0525 |
-| 0.7182        | 53.84 | 1400 | 0.2341          | 0.2877 | 0.0535 |
-| 0.7095        | 57.69 | 1500 | 0.2291          | 0.2818 | 0.0515 |
-| 0.6953        | 61.53 | 1600 | 0.2249          | 0.2783 | 0.0508 |
+| 4.0311        | 3.51  | 200  | 0.7943          | 0.8981 | 0.2374 |
+| 1.4388        | 7.02  | 400  | 0.2546          | 0.3821 | 0.0658 |
+| 1.0949        | 10.53 | 600  | 0.2201          | 0.3216 | 0.0573 |
+| 1.0279        | 14.04 | 800  | 0.2250          | 0.3271 | 0.0583 |
+| 0.9923        | 17.54 | 1000 | 0.2074          | 0.3111 | 0.0543 |
+| 0.972         | 21.05 | 1200 | 0.2165          | 0.2955 | 0.0536 |
+| 0.9587        | 24.56 | 1400 | 0.2064          | 0.3017 | 0.0535 |
+| 0.9421        | 28.07 | 1600 | 0.2062          | 0.2884 | 0.0519 |
+| 0.9189        | 31.58 | 1800 | 0.2014          | 0.2822 | 0.0507 |
+| 0.8919        | 35.09 | 2000 | 0.1952          | 0.2689 | 0.0488 |
+| 0.8615        | 38.6  | 2200 | 0.2020          | 0.2685 | 0.0480 |
+| 0.834         | 42.11 | 2400 | 0.2001          | 0.2654 | 0.0467 |
+| 0.8056        | 45.61 | 2600 | 0.1935          | 0.2498 | 0.0448 |
+| 0.7888        | 49.12 | 2800 | 0.1892          | 0.2451 | 0.0446 |
+| 0.761         | 52.63 | 3000 | 0.1884          | 0.2432 | 0.0441 |
+| 0.742         | 56.14 | 3200 | 0.1827          | 0.2389 | 0.0427 |
 
 
 ### Framework versions

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 61.53,
-    "eval_cer": 0.05078401618614062,
-    "eval_loss": 0.2248678207397461,
-    "eval_runtime": 15.1655,
+    "epoch": 56.14,
+    "eval_cer": 0.04274152756702074,
+    "eval_loss": 0.18266724050045013,
+    "eval_runtime": 15.3733,
     "eval_samples": 335,
-    "eval_samples_per_second": 22.09,
-    "eval_steps_per_second": 0.396,
-    "eval_wer": 0.2782982045277127,
-    "train_loss": 1.2442097234725953,
-    "train_runtime": 17605.3989,
-    "train_samples": 3354,
-    "train_samples_per_second": 11.633,
-    "train_steps_per_second": 0.091
+    "eval_samples_per_second": 21.791,
+    "eval_steps_per_second": 0.39,
+    "eval_wer": 0.2388758782201405,
+    "train_loss": 1.1288447761535645,
+    "train_runtime": 34425.8492,
+    "train_samples": 7284,
+    "train_samples_per_second": 11.898,
+    "train_steps_per_second": 0.093
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 61.53,
-    "eval_cer": 0.05078401618614062,
-    "eval_loss": 0.2248678207397461,
-    "eval_runtime": 15.1655,
+    "epoch": 56.14,
+    "eval_cer": 0.04274152756702074,
+    "eval_loss": 0.18266724050045013,
+    "eval_runtime": 15.3733,
     "eval_samples": 335,
-    "eval_samples_per_second": 22.09,
-    "eval_steps_per_second": 0.396,
-    "eval_wer": 0.2782982045277127
+    "eval_samples_per_second": 21.791,
+    "eval_steps_per_second": 0.39,
+    "eval_wer": 0.2388758782201405
 }

mozilla-foundation_common_voice_8_0_hy-AM_test_eval_results.txt

@@ -1,2 +1,2 @@
-WER: 0.12724434035909446
-CER: 0.02716236722306525
+WER: 0.1092896174863388
+CER: 0.023773394031360646

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbfcbb3e2a2fa0ab89db84e59692c3f3bee66d7cee3154a41e036d1300fac796
+oid sha256:5841178926d310ff9b34929b7a12bd2a6884370660d7b8a36e5e68cad7b398b5
 size 3850538161

runs/Feb01_02-28-31_job-b1f4681b-d20d-47f2-af64-0c1734f4ff64/1643682600.7320218/events.out.tfevents.1643682600.job-b1f4681b-d20d-47f2-af64-0c1734f4ff64.56475.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7efa6feb747dd0cd32ce4ec27d06e70776b4b6973a356aa5d2e59ce98a0203
+size 4772

runs/Feb01_02-28-31_job-b1f4681b-d20d-47f2-af64-0c1734f4ff64/events.out.tfevents.1643682600.job-b1f4681b-d20d-47f2-af64-0c1734f4ff64.56475.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372caebe4aa87fa7bef8ad8a172467ae7445d0e019194704a802e54229f8c8b4
+size 13409

runs/Feb01_02-28-31_job-b1f4681b-d20d-47f2-af64-0c1734f4ff64/events.out.tfevents.1643717046.job-b1f4681b-d20d-47f2-af64-0c1734f4ff64.56475.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cd520a9802ba9a4bae9e6a4bc6c34e2693a822e05be353a4545c592e412324
+size 405

speech-recognition-community-v2_dev_data_hy_validation_eval_results.txt

@@ -0,0 +1,2 @@
+WER: 0.19942816297355254
+CER: 0.07332618465282714

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 61.53,
-    "train_loss": 1.2442097234725953,
-    "train_runtime": 17605.3989,
-    "train_samples": 3354,
-    "train_samples_per_second": 11.633,
-    "train_steps_per_second": 0.091
+    "epoch": 56.14,
+    "train_loss": 1.1288447761535645,
+    "train_runtime": 34425.8492,
+    "train_samples": 7284,
+    "train_samples_per_second": 11.898,
+    "train_steps_per_second": 0.093
 }

trainer_state.json

@@ -1,281 +1,281 @@
 {
-  "best_metric": 0.2248678207397461,
-  "best_model_checkpoint": "./checkpoint-1600",
-  "epoch": 61.53333333333333,
-  "global_step": 1600,
+  "best_metric": 0.18266724050045013,
+  "best_model_checkpoint": "./checkpoint-3200",
+  "epoch": 56.14035087719298,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.84,
+      "epoch": 3.51,
       "learning_rate": 4.980500000000001e-05,
-      "loss": 4.9923,
-      "step": 100
+      "loss": 4.0311,
+      "step": 200
     },
     {
-      "epoch": 3.84,
-      "eval_cer": 1.0,
-      "eval_loss": 3.156188488006592,
-      "eval_runtime": 15.7049,
-      "eval_samples_per_second": 21.331,
+      "epoch": 3.51,
+      "eval_cer": 0.23737986848760748,
+      "eval_loss": 0.794314444065094,
+      "eval_runtime": 15.7,
+      "eval_samples_per_second": 21.338,
       "eval_steps_per_second": 0.382,
-      "eval_wer": 1.0,
-      "step": 100
+      "eval_wer": 0.8981264637002342,
+      "step": 200
     },
     {
-      "epoch": 7.69,
+      "epoch": 7.02,
       "learning_rate": 8e-05,
-      "loss": 2.1775,
-      "step": 200
+      "loss": 1.4388,
+      "step": 400
     },
     {
-      "epoch": 7.69,
-      "eval_cer": 0.11219018715225089,
-      "eval_loss": 0.43336454033851624,
-      "eval_runtime": 15.2789,
-      "eval_samples_per_second": 21.926,
-      "eval_steps_per_second": 0.393,
-      "eval_wer": 0.5804059328649492,
-      "step": 200
+      "epoch": 7.02,
+      "eval_cer": 0.06575619625695499,
+      "eval_loss": 0.2545942962169647,
+      "eval_runtime": 14.891,
+      "eval_samples_per_second": 22.497,
+      "eval_steps_per_second": 0.403,
+      "eval_wer": 0.38212334113973456,
+      "step": 400
     },
     {
-      "epoch": 11.53,
+      "epoch": 10.53,
       "learning_rate": 8e-05,
-      "loss": 1.3708,
-      "step": 300
+      "loss": 1.0949,
+      "step": 600
     },
     {
-      "epoch": 11.53,
-      "eval_cer": 0.07966616084977238,
-      "eval_loss": 0.3105751574039459,
-      "eval_runtime": 15.048,
-      "eval_samples_per_second": 22.262,
-      "eval_steps_per_second": 0.399,
-      "eval_wer": 0.4336455893832943,
-      "step": 300
+      "epoch": 10.53,
+      "eval_cer": 0.057309054122407686,
+      "eval_loss": 0.22006691992282867,
+      "eval_runtime": 15.2331,
+      "eval_samples_per_second": 21.992,
+      "eval_steps_per_second": 0.394,
+      "eval_wer": 0.32162373145979706,
+      "step": 600
     },
     {
-      "epoch": 15.38,
+      "epoch": 14.04,
       "learning_rate": 8e-05,
-      "loss": 1.2266,
-      "step": 400
+      "loss": 1.0279,
+      "step": 800
     },
     {
-      "epoch": 15.38,
-      "eval_cer": 0.06732422862923622,
-      "eval_loss": 0.26751142740249634,
-      "eval_runtime": 15.232,
-      "eval_samples_per_second": 21.993,
-      "eval_steps_per_second": 0.394,
-      "eval_wer": 0.3672911787665886,
-      "step": 400
+      "epoch": 14.04,
+      "eval_cer": 0.0582701062215478,
+      "eval_loss": 0.22504645586013794,
+      "eval_runtime": 15.1767,
+      "eval_samples_per_second": 22.073,
+      "eval_steps_per_second": 0.395,
+      "eval_wer": 0.32708821233411395,
+      "step": 800
     },
     {
-      "epoch": 19.23,
+      "epoch": 17.54,
       "learning_rate": 8e-05,
-      "loss": 1.093,
-      "step": 500
+      "loss": 0.9923,
+      "step": 1000
     },
     {
-      "epoch": 19.23,
-      "eval_cer": 0.06327769347496207,
-      "eval_loss": 0.24162611365318298,
-      "eval_runtime": 14.995,
-      "eval_samples_per_second": 22.341,
-      "eval_steps_per_second": 0.4,
-      "eval_wer": 0.35011709601873536,
-      "step": 500
+      "epoch": 17.54,
+      "eval_cer": 0.0543247344461305,
+      "eval_loss": 0.2073642760515213,
+      "eval_runtime": 15.1305,
+      "eval_samples_per_second": 22.141,
+      "eval_steps_per_second": 0.397,
+      "eval_wer": 0.3110850897736144,
+      "step": 1000
     },
     {
-      "epoch": 23.08,
+      "epoch": 21.05,
       "learning_rate": 8e-05,
-      "loss": 0.989,
-      "step": 600
+      "loss": 0.972,
+      "step": 1200
     },
     {
-      "epoch": 23.08,
-      "eval_cer": 0.06105209914011128,
-      "eval_loss": 0.23200440406799316,
-      "eval_runtime": 15.3525,
-      "eval_samples_per_second": 21.821,
-      "eval_steps_per_second": 0.391,
-      "eval_wer": 0.3251366120218579,
-      "step": 600
+      "epoch": 21.05,
+      "eval_cer": 0.05361659079413252,
+      "eval_loss": 0.21649114787578583,
+      "eval_runtime": 14.9827,
+      "eval_samples_per_second": 22.359,
+      "eval_steps_per_second": 0.4,
+      "eval_wer": 0.29547228727556596,
+      "step": 1200
     },
     {
-      "epoch": 26.91,
+      "epoch": 24.56,
       "learning_rate": 8e-05,
-      "loss": 0.9518,
-      "step": 700
+      "loss": 0.9587,
+      "step": 1400
     },
     {
-      "epoch": 26.91,
-      "eval_cer": 0.05842185128983308,
-      "eval_loss": 0.2413272261619568,
-      "eval_runtime": 15.2385,
-      "eval_samples_per_second": 21.984,
-      "eval_steps_per_second": 0.394,
-      "eval_wer": 0.3192818110850898,
-      "step": 700
+      "epoch": 24.56,
+      "eval_cer": 0.05351542741527567,
+      "eval_loss": 0.2064175009727478,
+      "eval_runtime": 15.1921,
+      "eval_samples_per_second": 22.051,
+      "eval_steps_per_second": 0.395,
+      "eval_wer": 0.3017174082747853,
+      "step": 1400
     },
     {
-      "epoch": 30.76,
+      "epoch": 28.07,
       "learning_rate": 8e-05,
-      "loss": 0.9075,
-      "step": 800
+      "loss": 0.9421,
+      "step": 1600
     },
     {
-      "epoch": 30.76,
-      "eval_cer": 0.05933232169954476,
-      "eval_loss": 0.23544833064079285,
-      "eval_runtime": 15.1938,
-      "eval_samples_per_second": 22.049,
-      "eval_steps_per_second": 0.395,
-      "eval_wer": 0.3200624512099922,
-      "step": 800
+      "epoch": 28.07,
+      "eval_cer": 0.051947395042994435,
+      "eval_loss": 0.2061864584684372,
+      "eval_runtime": 15.0418,
+      "eval_samples_per_second": 22.271,
+      "eval_steps_per_second": 0.399,
+      "eval_wer": 0.28844652615144417,
+      "step": 1600
     },
     {
-      "epoch": 34.61,
+      "epoch": 31.58,
       "learning_rate": 7.059500000000001e-05,
-      "loss": 0.878,
-      "step": 900
+      "loss": 0.9189,
+      "step": 1800
     },
     {
-      "epoch": 34.61,
-      "eval_cer": 0.057916034395548814,
-      "eval_loss": 0.22777308523654938,
-      "eval_runtime": 14.9728,
-      "eval_samples_per_second": 22.374,
-      "eval_steps_per_second": 0.401,
-      "eval_wer": 0.3126463700234192,
-      "step": 900
+      "epoch": 31.58,
+      "eval_cer": 0.05073343449671219,
+      "eval_loss": 0.2014162391424179,
+      "eval_runtime": 15.125,
+      "eval_samples_per_second": 22.149,
+      "eval_steps_per_second": 0.397,
+      "eval_wer": 0.2822014051522248,
+      "step": 1800
     },
     {
-      "epoch": 38.46,
+      "epoch": 35.09,
       "learning_rate": 6.109500000000001e-05,
-      "loss": 0.8563,
-      "step": 1000
+      "loss": 0.8919,
+      "step": 2000
     },
     {
-      "epoch": 38.46,
-      "eval_cer": 0.054779969650986346,
-      "eval_loss": 0.2326740324497223,
-      "eval_runtime": 15.1749,
-      "eval_samples_per_second": 22.076,
-      "eval_steps_per_second": 0.395,
-      "eval_wer": 0.2962529274004684,
-      "step": 1000
+      "epoch": 35.09,
+      "eval_cer": 0.04881133029843197,
+      "eval_loss": 0.19518214464187622,
+      "eval_runtime": 15.0854,
+      "eval_samples_per_second": 22.207,
+      "eval_steps_per_second": 0.398,
+      "eval_wer": 0.2689305230288837,
+      "step": 2000
     },
     {
-      "epoch": 42.3,
-      "learning_rate": 5.169000000000001e-05,
-      "loss": 0.8084,
-      "step": 1100
+      "epoch": 38.6,
+      "learning_rate": 5.1594999999999996e-05,
+      "loss": 0.8615,
+      "step": 2200
     },
     {
-      "epoch": 42.3,
-      "eval_cer": 0.05407182599898837,
-      "eval_loss": 0.22712552547454834,
-      "eval_runtime": 15.3083,
-      "eval_samples_per_second": 21.884,
-      "eval_steps_per_second": 0.392,
-      "eval_wer": 0.2923497267759563,
-      "step": 1100
+      "epoch": 38.6,
+      "eval_cer": 0.04795144157814871,
+      "eval_loss": 0.20196911692619324,
+      "eval_runtime": 15.1604,
+      "eval_samples_per_second": 22.097,
+      "eval_steps_per_second": 0.396,
+      "eval_wer": 0.2685402029664325,
+      "step": 2200
     },
     {
-      "epoch": 46.15,
-      "learning_rate": 4.219000000000001e-05,
-      "loss": 0.7845,
-      "step": 1200
+      "epoch": 42.11,
+      "learning_rate": 4.2095e-05,
+      "loss": 0.834,
+      "step": 2400
     },
     {
-      "epoch": 46.15,
-      "eval_cer": 0.053667172483560954,
-      "eval_loss": 0.23326420783996582,
-      "eval_runtime": 15.1559,
-      "eval_samples_per_second": 22.104,
-      "eval_steps_per_second": 0.396,
-      "eval_wer": 0.29508196721311475,
-      "step": 1200
+      "epoch": 42.11,
+      "eval_cer": 0.04668689934243804,
+      "eval_loss": 0.2001034915447235,
+      "eval_runtime": 15.091,
+      "eval_samples_per_second": 22.199,
+      "eval_steps_per_second": 0.398,
+      "eval_wer": 0.2654176424668228,
+      "step": 2400
     },
     {
-      "epoch": 49.99,
-      "learning_rate": 3.269000000000001e-05,
-      "loss": 0.7487,
-      "step": 1300
+      "epoch": 45.61,
+      "learning_rate": 3.2595e-05,
+      "loss": 0.8056,
+      "step": 2600
     },
     {
-      "epoch": 49.99,
-      "eval_cer": 0.052453211937278706,
-      "eval_loss": 0.22895006835460663,
-      "eval_runtime": 15.373,
-      "eval_samples_per_second": 21.791,
-      "eval_steps_per_second": 0.39,
-      "eval_wer": 0.2888368462138954,
-      "step": 1300
+      "epoch": 45.61,
+      "eval_cer": 0.04481537683358624,
+      "eval_loss": 0.1934908777475357,
+      "eval_runtime": 15.4173,
+      "eval_samples_per_second": 21.729,
+      "eval_steps_per_second": 0.389,
+      "eval_wer": 0.2498048399687744,
+      "step": 2600
     },
     {
-      "epoch": 53.84,
-      "learning_rate": 2.319e-05,
-      "loss": 0.7182,
-      "step": 1400
+      "epoch": 49.12,
+      "learning_rate": 2.3095e-05,
+      "loss": 0.7888,
+      "step": 2800
     },
     {
-      "epoch": 53.84,
-      "eval_cer": 0.05346484572584724,
-      "eval_loss": 0.23406584560871124,
-      "eval_runtime": 15.2056,
-      "eval_samples_per_second": 22.031,
-      "eval_steps_per_second": 0.395,
-      "eval_wer": 0.28766588602654175,
-      "step": 1400
+      "epoch": 49.12,
+      "eval_cer": 0.04461305007587253,
+      "eval_loss": 0.18915079534053802,
+      "eval_runtime": 15.29,
+      "eval_samples_per_second": 21.91,
+      "eval_steps_per_second": 0.392,
+      "eval_wer": 0.24512099921935987,
+      "step": 2800
     },
     {
-      "epoch": 57.69,
-      "learning_rate": 1.369e-05,
-      "loss": 0.7095,
-      "step": 1500
+      "epoch": 52.63,
+      "learning_rate": 1.3595000000000008e-05,
+      "loss": 0.761,
+      "step": 3000
     },
     {
-      "epoch": 57.69,
-      "eval_cer": 0.05154274152756702,
-      "eval_loss": 0.22908572852611542,
-      "eval_runtime": 15.2684,
-      "eval_samples_per_second": 21.941,
-      "eval_steps_per_second": 0.393,
-      "eval_wer": 0.2818110850897736,
-      "step": 1500
+      "epoch": 52.63,
+      "eval_cer": 0.044056651492159836,
+      "eval_loss": 0.18836112320423126,
+      "eval_runtime": 16.204,
+      "eval_samples_per_second": 20.674,
+      "eval_steps_per_second": 0.37,
+      "eval_wer": 0.24316939890710382,
+      "step": 3000
     },
     {
-      "epoch": 61.53,
-      "learning_rate": 4.190000000000005e-06,
-      "loss": 0.6953,
-      "step": 1600
+      "epoch": 56.14,
+      "learning_rate": 4.095000000000005e-06,
+      "loss": 0.742,
+      "step": 3200
     },
     {
-      "epoch": 61.53,
-      "eval_cer": 0.05078401618614062,
-      "eval_loss": 0.2248678207397461,
-      "eval_runtime": 15.2139,
-      "eval_samples_per_second": 22.019,
-      "eval_steps_per_second": 0.394,
-      "eval_wer": 0.2782982045277127,
-      "step": 1600
+      "epoch": 56.14,
+      "eval_cer": 0.04274152756702074,
+      "eval_loss": 0.18266724050045013,
+      "eval_runtime": 15.3463,
+      "eval_samples_per_second": 21.829,
+      "eval_steps_per_second": 0.391,
+      "eval_wer": 0.2388758782201405,
+      "step": 3200
     },
     {
-      "epoch": 61.53,
-      "step": 1600,
-      "total_flos": 1.3126730002882698e+20,
-      "train_loss": 1.2442097234725953,
-      "train_runtime": 17605.3989,
-      "train_samples_per_second": 11.633,
-      "train_steps_per_second": 0.091
+      "epoch": 56.14,
+      "step": 3200,
+      "total_flos": 2.6268075931237872e+20,
+      "train_loss": 1.1288447761535645,
+      "train_runtime": 34425.8492,
+      "train_samples_per_second": 11.898,
+      "train_steps_per_second": 0.093
     }
   ],
-  "max_steps": 1600,
-  "num_train_epochs": 62,
-  "total_flos": 1.3126730002882698e+20,
+  "max_steps": 3200,
+  "num_train_epochs": 57,
+  "total_flos": 2.6268075931237872e+20,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c934f0ed6fa80bfe4f2228c9550d942f9d713597358d2f57a1375b6454c2d03d
+oid sha256:bfeb12863ac5de618f2b958c1b03e980705dda909c6bff76a929e0e5bfb2b372
 size 3055