Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a8be296d9693102c2d75dc7be4c3c4dc69e79ecab2acc7233710ac2661a364
+oid sha256:85f0e09ecc93465e0a0221ba66dcfb3297029be6496ecd7742a3367c03b2dddf
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af704705ef0da7f09f726648a246c4dd765dd9cbdb61aaf391803c45ff6d1dc
+oid sha256:7faa3deaf7772fdd5c0b956a58b34d5abc85013a67b67c9e291879541658bcbc
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b392e7666c071a2d6510caf8f2c7432c070724f46481df44ca2199dfdbb3d3
+oid sha256:d89bc68118b2bdfe67b2a1e276ef1fcd92b1616b6e5c253bf79def97355e27b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda99ba66ec317fa211d4111d8e4f978ee38e5bbccdd4109849ebc8aea65894b
+oid sha256:3ccdac996a7746ff581f40b984dc6b1b8e12cdd0754c04482dcb7dee59b625cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 77.56275148495881,
   "best_model_checkpoint": "./whisper-small-ha-v10/checkpoint-3000",
-  "epoch": 63.69426751592356,
+  "epoch": 66.87898089171975,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3007,6 +3007,156 @@
       "eval_wer": 81.68231461965894,
       "eval_wer_ortho": 83.7109375,
       "step": 10000
+    },
+    {
+      "epoch": 63.853503184713375,
+      "grad_norm": 2.015751361846924,
+      "learning_rate": 3e-05,
+      "loss": 0.0041,
+      "step": 10025
+    },
+    {
+      "epoch": 64.01273885350318,
+      "grad_norm": 2.141650676727295,
+      "learning_rate": 3e-05,
+      "loss": 0.0128,
+      "step": 10050
+    },
+    {
+      "epoch": 64.171974522293,
+      "grad_norm": 0.3167494237422943,
+      "learning_rate": 3e-05,
+      "loss": 0.0084,
+      "step": 10075
+    },
+    {
+      "epoch": 64.3312101910828,
+      "grad_norm": 1.8153035640716553,
+      "learning_rate": 3e-05,
+      "loss": 0.0086,
+      "step": 10100
+    },
+    {
+      "epoch": 64.49044585987261,
+      "grad_norm": 0.3989582061767578,
+      "learning_rate": 3e-05,
+      "loss": 0.0057,
+      "step": 10125
+    },
+    {
+      "epoch": 64.64968152866243,
+      "grad_norm": 1.5880628824234009,
+      "learning_rate": 3e-05,
+      "loss": 0.0086,
+      "step": 10150
+    },
+    {
+      "epoch": 64.80891719745223,
+      "grad_norm": 0.07060195505619049,
+      "learning_rate": 3e-05,
+      "loss": 0.0079,
+      "step": 10175
+    },
+    {
+      "epoch": 64.96815286624204,
+      "grad_norm": 1.7613017559051514,
+      "learning_rate": 3e-05,
+      "loss": 0.0086,
+      "step": 10200
+    },
+    {
+      "epoch": 65.12738853503184,
+      "grad_norm": 0.047506798058748245,
+      "learning_rate": 3e-05,
+      "loss": 0.0115,
+      "step": 10225
+    },
+    {
+      "epoch": 65.28662420382166,
+      "grad_norm": 1.2768458127975464,
+      "learning_rate": 3e-05,
+      "loss": 0.006,
+      "step": 10250
+    },
+    {
+      "epoch": 65.44585987261146,
+      "grad_norm": 2.424394130706787,
+      "learning_rate": 3e-05,
+      "loss": 0.0291,
+      "step": 10275
+    },
+    {
+      "epoch": 65.60509554140127,
+      "grad_norm": 0.09524156898260117,
+      "learning_rate": 3e-05,
+      "loss": 0.0129,
+      "step": 10300
+    },
+    {
+      "epoch": 65.76433121019109,
+      "grad_norm": 3.080942153930664,
+      "learning_rate": 3e-05,
+      "loss": 0.0076,
+      "step": 10325
+    },
+    {
+      "epoch": 65.92356687898089,
+      "grad_norm": 0.5182892680168152,
+      "learning_rate": 3e-05,
+      "loss": 0.01,
+      "step": 10350
+    },
+    {
+      "epoch": 66.0828025477707,
+      "grad_norm": 4.24620246887207,
+      "learning_rate": 3e-05,
+      "loss": 0.0074,
+      "step": 10375
+    },
+    {
+      "epoch": 66.24203821656052,
+      "grad_norm": 0.21629653871059418,
+      "learning_rate": 3e-05,
+      "loss": 0.0086,
+      "step": 10400
+    },
+    {
+      "epoch": 66.40127388535032,
+      "grad_norm": 0.24145953357219696,
+      "learning_rate": 3e-05,
+      "loss": 0.0112,
+      "step": 10425
+    },
+    {
+      "epoch": 66.56050955414013,
+      "grad_norm": 0.3760283291339874,
+      "learning_rate": 3e-05,
+      "loss": 0.0072,
+      "step": 10450
+    },
+    {
+      "epoch": 66.71974522292993,
+      "grad_norm": 0.07463686168193817,
+      "learning_rate": 3e-05,
+      "loss": 0.0138,
+      "step": 10475
+    },
+    {
+      "epoch": 66.87898089171975,
+      "grad_norm": 2.895296335220337,
+      "learning_rate": 3e-05,
+      "loss": 0.0093,
+      "step": 10500
+    },
+    {
+      "epoch": 66.87898089171975,
+      "eval_loss": 2.654149293899536,
+      "eval_runtime": 146.7787,
+      "eval_samples_per_second": 4.497,
+      "eval_steps_per_second": 0.286,
+      "eval_wer": 80.34106150603564,
+      "eval_wer_ortho": 82.44140625,
+      "step": 10500
     }
   ],
   "logging_steps": 25,
@@ -3035,7 +3185,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.614249682796544e+19,
+  "total_flos": 4.84477170057216e+19,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null