:tada: update new version of the model

config.json

@@ -78,7 +78,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.29.2",
+    "transformers_version": "4.30.2",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": false,
@@ -161,7 +161,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.29.2",
+    "transformers_version": "4.30.2",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

generation_config.json

@@ -8,6 +8,6 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.30.2",
   "use_cache": false
 }

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb2d4811686ae1fa5a5ddbece1088f23033f7ae89187930e91e4367f3af832c
+size 6036958

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5040851d479f1cc732b7bc4266a943eb794c4672076efd0e67969c551c44372f
+oid sha256:c39317b40076bf60899b4514d6318b68b6e3621172b0356c452f95a4db8e031f
 size 2233126973

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0756790bb996e19575e28b3c5794bed812c7a56143b158c721c60574e44838a
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2f6dbce125c240e2f433875ddc84c2eed63df4c51523c9a034cc014ea71382
+size 627

trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.4317134916782379,
+  "best_model_checkpoint": "./checkpoint-4000",
+  "epoch": 6.592501030078286,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.835643564356436e-05,
+      "loss": 1.3928,
+      "step": 500
+    },
+    {
+      "epoch": 0.82,
+      "eval_cer": 0.15288597601847026,
+      "eval_loss": 0.7451776266098022,
+      "eval_runtime": 665.9721,
+      "eval_samples_per_second": 13.161,
+      "eval_steps_per_second": 0.823,
+      "eval_wer": 0.38850250902368166,
+      "step": 500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.6709570957095713e-05,
+      "loss": 0.6552,
+      "step": 1000
+    },
+    {
+      "epoch": 1.65,
+      "eval_cer": 0.11089595590973411,
+      "eval_loss": 0.5462419986724854,
+      "eval_runtime": 675.2942,
+      "eval_samples_per_second": 12.98,
+      "eval_steps_per_second": 0.811,
+      "eval_wer": 0.2981776564838454,
+      "step": 1000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 3.5059405940594064e-05,
+      "loss": 0.4677,
+      "step": 1500
+    },
+    {
+      "epoch": 2.47,
+      "eval_cer": 0.10123631488791242,
+      "eval_loss": 0.5031750202178955,
+      "eval_runtime": 658.2362,
+      "eval_samples_per_second": 13.316,
+      "eval_steps_per_second": 0.833,
+      "eval_wer": 0.28013029315960913,
+      "step": 1500
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.3409240924092415e-05,
+      "loss": 0.3562,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3,
+      "eval_cer": 0.0952111417293513,
+      "eval_loss": 0.4881753623485565,
+      "eval_runtime": 676.7933,
+      "eval_samples_per_second": 12.951,
+      "eval_steps_per_second": 0.81,
+      "eval_wer": 0.2703142882295977,
+      "step": 2000
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 3.175907590759076e-05,
+      "loss": 0.2742,
+      "step": 2500
+    },
+    {
+      "epoch": 4.12,
+      "eval_cer": 0.08611007671110449,
+      "eval_loss": 0.45607951283454895,
+      "eval_runtime": 672.7042,
+      "eval_samples_per_second": 13.029,
+      "eval_steps_per_second": 0.815,
+      "eval_wer": 0.24729289550136455,
+      "step": 2500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 3.0108910891089113e-05,
+      "loss": 0.2047,
+      "step": 3000
+    },
+    {
+      "epoch": 4.94,
+      "eval_cer": 0.07996574067178074,
+      "eval_loss": 0.43779700994491577,
+      "eval_runtime": 670.3674,
+      "eval_samples_per_second": 13.075,
+      "eval_steps_per_second": 0.817,
+      "eval_wer": 0.236596531384805,
+      "step": 3000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 2.845874587458746e-05,
+      "loss": 0.1452,
+      "step": 3500
+    },
+    {
+      "epoch": 5.77,
+      "eval_cer": 0.07977210099054145,
+      "eval_loss": 0.4486931562423706,
+      "eval_runtime": 668.3535,
+      "eval_samples_per_second": 13.114,
+      "eval_steps_per_second": 0.82,
+      "eval_wer": 0.2334272383132318,
+      "step": 3500
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 2.680858085808581e-05,
+      "loss": 0.1124,
+      "step": 4000
+    },
+    {
+      "epoch": 6.59,
+      "eval_cer": 0.0765323601698071,
+      "eval_loss": 0.4317134916782379,
+      "eval_runtime": 669.0454,
+      "eval_samples_per_second": 13.101,
+      "eval_steps_per_second": 0.819,
+      "eval_wer": 0.2277489215599965,
+      "step": 4000
+    }
+  ],
+  "max_steps": 12120,
+  "num_train_epochs": 20,
+  "total_flos": 6.878208895191142e+20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285f662b244cf0221eac8fbf1d07aebf10f2df8284a4689cc217fab5954a40f0
+oid sha256:be998148e7fb2d04bbcf0f3ee167cf3efff6718f9f789ec8e4a072fdb3a83554
 size 4027