Training in progress, step 350

{checkpoint-150 → checkpoint-350}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f8e6594c4e496478e4866e70b042c6a88c87612acaf661f65750f58a301e4f
-size 2490361937
+oid sha256:646667c125c12f737d1ffee17d6371268d6575f3796018a92eb4102f5f1fff0b
+size 2490362385

{checkpoint-150 → checkpoint-350}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386439db8a06ec7bb8279d96099b6db5fee78683933dd8e79efdb684fee3e2c0
+oid sha256:f0d76767012f4da5dc0d5f53230af28368c23a384f4a2b862a3afb09aea2dc6d
 size 1262075377

{checkpoint-150 → checkpoint-350}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f704415bae2d9ff4df8dc44b817ddfc862d4dd0c72e611cb60926dc7d7e582d1
+oid sha256:4671c6ef20752fdeca41dd978833212c15422e660369baad61a24c693eba960d
 size 14567

{checkpoint-150 → checkpoint-350}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968c71c75fc57c68b8d331de92abbf974f36bbab2c395cec452f6a60d0999a20
+oid sha256:11a38190a29b2e515a160c453a45f3b2acc23e2c8c2240009e053ed0dbf017f0
 size 559

{checkpoint-150 → checkpoint-350}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac0ff029249bda5eded6c55167fca809c071e881ce886494b4c2d2d40b64c39
+oid sha256:68cb16be7c67302d24fc36708cbe6b5ff6ca823143d0ed4ccd59b12de9852185
 size 623

{checkpoint-150 → checkpoint-350}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43509789702683105,
-  "global_step": 150,
+  "epoch": 1.0174039158810733,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,11 +123,167 @@
       "eval_steps_per_second": 4.573,
       "eval_wer": 1.0,
       "step": 150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.9393712574850293e-05,
+      "loss": 3.0588,
+      "step": 160
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.827095808383233e-05,
+      "loss": 3.0477,
+      "step": 170
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.714820359281436e-05,
+      "loss": 3.045,
+      "step": 180
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.602544910179641e-05,
+      "loss": 3.0439,
+      "step": 190
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.490269461077844e-05,
+      "loss": 3.0846,
+      "step": 200
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 3.079519271850586,
+      "eval_runtime": 125.7215,
+      "eval_samples_per_second": 36.748,
+      "eval_steps_per_second": 4.597,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.3779940119760477e-05,
+      "loss": 3.0512,
+      "step": 210
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.265718562874251e-05,
+      "loss": 3.0143,
+      "step": 220
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.1534431137724546e-05,
+      "loss": 3.0387,
+      "step": 230
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.0411676646706584e-05,
+      "loss": 3.0311,
+      "step": 240
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.9288922155688615e-05,
+      "loss": 3.0417,
+      "step": 250
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 3.069390058517456,
+      "eval_runtime": 125.7339,
+      "eval_samples_per_second": 36.744,
+      "eval_steps_per_second": 4.597,
+      "eval_wer": 1.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.816616766467066e-05,
+      "loss": 3.0219,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.704341317365269e-05,
+      "loss": 3.0194,
+      "step": 270
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.592065868263473e-05,
+      "loss": 2.9974,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.479790419161676e-05,
+      "loss": 2.9996,
+      "step": 290
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.36751497005988e-05,
+      "loss": 3.0016,
+      "step": 300
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 3.0347490310668945,
+      "eval_runtime": 132.3039,
+      "eval_samples_per_second": 34.92,
+      "eval_steps_per_second": 4.369,
+      "eval_wer": 1.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.255239520958083e-05,
+      "loss": 3.0052,
+      "step": 310
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.142964071856287e-05,
+      "loss": 2.9826,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.030688622754491e-05,
+      "loss": 2.9747,
+      "step": 330
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.918413173652694e-05,
+      "loss": 2.9617,
+      "step": 340
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.806137724550898e-05,
+      "loss": 3.2053,
+      "step": 350
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 2.984886407852173,
+      "eval_runtime": 149.1508,
+      "eval_samples_per_second": 30.975,
+      "eval_steps_per_second": 3.875,
+      "eval_wer": 1.0,
+      "step": 350
     }
   ],
   "max_steps": 688,
   "num_train_epochs": 2,
-  "total_flos": 4.4091799296804864e+17,
+  "total_flos": 1.0437262031798554e+18,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edb565b658376cb9cf7a44bbc1bfea5a26ebcd17d3f36739a8535e85a13dcee
+oid sha256:f0d76767012f4da5dc0d5f53230af28368c23a384f4a2b862a3afb09aea2dc6d
 size 1262075377