Training in progress, step 200

checkpoint-10/trainer_state.json

@@ -1,94 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.029006526468455404,
-  "global_step": 10,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0,
-      "learning_rate": 3.75e-06,
-      "loss": 13.605,
-      "step": 1
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 7.5e-06,
-      "loss": 11.0063,
-      "step": 2
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 1.1249999999999999e-05,
-      "loss": 11.6693,
-      "step": 3
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 1.5e-05,
-      "loss": 13.432,
-      "step": 4
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 1.875e-05,
-      "loss": 10.3458,
-      "step": 5
-    },
-    {
-      "epoch": 0.01,
-      "eval_loss": 15.09913444519043,
-      "eval_runtime": 139.8551,
-      "eval_samples_per_second": 33.034,
-      "eval_steps_per_second": 4.133,
-      "eval_wer": 1.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 2.2499999999999998e-05,
-      "loss": 15.2451,
-      "step": 6
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 2.625e-05,
-      "loss": 10.0481,
-      "step": 7
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 3e-05,
-      "loss": 12.3838,
-      "step": 8
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 3.3749999999999994e-05,
-      "loss": 11.9858,
-      "step": 9
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 3.75e-05,
-      "loss": 11.9029,
-      "step": 10
-    },
-    {
-      "epoch": 0.03,
-      "eval_loss": 14.213573455810547,
-      "eval_runtime": 160.2552,
-      "eval_samples_per_second": 28.829,
-      "eval_steps_per_second": 3.607,
-      "eval_wer": 1.0,
-      "step": 10
-    }
-  ],
-  "max_steps": 10,
-  "num_train_epochs": 1,
-  "total_flos": 4.405923604988928e+16,
-  "trial_name": null,
-  "trial_params": null
-}

{checkpoint-10 → checkpoint-200}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edcb67a936a475709d3e3723b7e3224e64b185948f313f11f94438218cf2c5b2
+oid sha256:b1202a5092b4eef4129f21d94d892672eedd0f405c7b97384c527938ad263ff2
 size 2490361937

{checkpoint-10 → checkpoint-200}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd61f5511562b14319e58a1b70c496d7e20b55df954b4ca337e122de41cab04e
+oid sha256:81a809773f4c41661a588636b358c9e5380d7596cf519d3864f59d078d6b5d56
 size 1262075377

{checkpoint-10 → checkpoint-200}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd055f4e5c4ffd4371a3565bfa995a6c8cb41314bc604e8debedf999343a113
+oid sha256:aac8c2cbd9ad36e5da5c9bde6c85c2a957009b424972b91ca2f61d198a65abaf
 size 14567

{checkpoint-10 → checkpoint-200}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e4b012b4b9ab1daa876390beea4afff370d4f83e20e939f16cdf1855daf52f
+oid sha256:456d3f8c3511ae0b0f0b3bf14cf84027d3dd6e2dd5258c9c8a92b9132d6ccfef
 size 559

{checkpoint-10 → checkpoint-200}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e3ad42da29f9983fc79cb4c120fb5415e138f4bb390c579ef4600450de045a
+oid sha256:efd672a046efb6eb5df47d5237a07689c59887dac098586f96bf610f5cf17f77
 size 623

checkpoint-200/trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.580130529369108,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.75e-05,
+      "loss": 12.1562,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.125e-05,
+      "loss": 8.7679,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.398952095808383e-05,
+      "loss": 5.3683,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 7.286676646706586e-05,
+      "loss": 4.3219,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 7.17440119760479e-05,
+      "loss": 3.7182,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 3.836604595184326,
+      "eval_runtime": 133.4846,
+      "eval_samples_per_second": 34.611,
+      "eval_steps_per_second": 4.33,
+      "eval_wer": 1.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.062125748502993e-05,
+      "loss": 3.478,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 6.949850299401197e-05,
+      "loss": 3.4492,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 6.837574850299401e-05,
+      "loss": 3.3928,
+      "step": 80
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 6.725299401197604e-05,
+      "loss": 3.3183,
+      "step": 90
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.613023952095809e-05,
+      "loss": 3.2075,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 3.258362293243408,
+      "eval_runtime": 126.6078,
+      "eval_samples_per_second": 36.491,
+      "eval_steps_per_second": 4.565,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.500748502994012e-05,
+      "loss": 3.14,
+      "step": 110
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.388473053892215e-05,
+      "loss": 3.1281,
+      "step": 120
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 6.276197604790418e-05,
+      "loss": 3.0987,
+      "step": 130
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.163922155688622e-05,
+      "loss": 3.1003,
+      "step": 140
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.0516467065868256e-05,
+      "loss": 3.0922,
+      "step": 150
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 3.127869129180908,
+      "eval_runtime": 126.3837,
+      "eval_samples_per_second": 36.555,
+      "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
+    }
+  ],
+  "max_steps": 688,
+  "num_train_epochs": 2,
+  "total_flos": 5.906333355279667e+17,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-10 → checkpoint-200}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0148471a0b194f620865125fd17f84a2e502a9e0a6acef5304251538d67e034
+oid sha256:77806a16ec6ef209c8a5c1c085159a0bc8e45c23f2d143f2c13e01527f13b5b2
 size 2991

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386439db8a06ec7bb8279d96099b6db5fee78683933dd8e79efdb684fee3e2c0
+oid sha256:81a809773f4c41661a588636b358c9e5380d7596cf519d3864f59d078d6b5d56
 size 1262075377