Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece6b48235a9ef14ff0e00b277b6b394ae84dddf28e4707154cced0b42c63971
+oid sha256:5ab8c96d034a3c39633f65fbe492a96d5da8cdfe6fee8067059ab5aafb6a82ce
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21658050ca5e4cb30252f38794bee1237ad73dd0a3b8f773171a0b54127b38cf
+oid sha256:7bd64a777229dbef4bf82dff14d6cb53c591af1b557e7c7b175c65b32ceda7b5
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc19516f0bb6ebbb441d01c76bfbe40ffc86ac7def6317731979041e8f3b7ba
+oid sha256:d1e95b55e61f2a72e5e5389523fde8c9fb1a2902741a578a17a342a5d7a4df5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b50b4cb0394cc440ebb08a80906354e23421bb3a354d8e7082be158c31d13dc
+oid sha256:db3c07fb5d0875fffe56d0b893055e00ce55f7141ff11534660111c35e822163
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 99.84375,
-  "best_model_checkpoint": "./whisper-small-ha-v9/checkpoint-500",
-  "epoch": 3.1847133757961785,
+  "best_metric": 98.0078125,
+  "best_model_checkpoint": "./whisper-small-ha-v9/checkpoint-1000",
+  "epoch": 6.369426751592357,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,156 @@
       "eval_wer": 99.84375,
       "eval_wer_ortho": 99.55930254838091,
       "step": 500
+    },
+    {
+      "epoch": 3.343949044585987,
+      "grad_norm": 7.7201032638549805,
+      "learning_rate": 0.0005,
+      "loss": 1.7432,
+      "step": 525
+    },
+    {
+      "epoch": 3.5031847133757963,
+      "grad_norm": 7.00828742980957,
+      "learning_rate": 0.0005,
+      "loss": 1.8165,
+      "step": 550
+    },
+    {
+      "epoch": 3.662420382165605,
+      "grad_norm": 7.801667213439941,
+      "learning_rate": 0.0005,
+      "loss": 1.8769,
+      "step": 575
+    },
+    {
+      "epoch": 3.821656050955414,
+      "grad_norm": 6.696052074432373,
+      "learning_rate": 0.0005,
+      "loss": 1.9189,
+      "step": 600
+    },
+    {
+      "epoch": 3.980891719745223,
+      "grad_norm": 7.849315643310547,
+      "learning_rate": 0.0005,
+      "loss": 1.9248,
+      "step": 625
+    },
+    {
+      "epoch": 4.140127388535032,
+      "grad_norm": 6.837538719177246,
+      "learning_rate": 0.0005,
+      "loss": 1.3935,
+      "step": 650
+    },
+    {
+      "epoch": 4.2993630573248405,
+      "grad_norm": 6.533350944519043,
+      "learning_rate": 0.0005,
+      "loss": 1.3859,
+      "step": 675
+    },
+    {
+      "epoch": 4.45859872611465,
+      "grad_norm": 7.38162899017334,
+      "learning_rate": 0.0005,
+      "loss": 1.4676,
+      "step": 700
+    },
+    {
+      "epoch": 4.617834394904459,
+      "grad_norm": 7.072102069854736,
+      "learning_rate": 0.0005,
+      "loss": 1.5653,
+      "step": 725
+    },
+    {
+      "epoch": 4.777070063694268,
+      "grad_norm": 7.383370399475098,
+      "learning_rate": 0.0005,
+      "loss": 1.6075,
+      "step": 750
+    },
+    {
+      "epoch": 4.936305732484076,
+      "grad_norm": 6.835177898406982,
+      "learning_rate": 0.0005,
+      "loss": 1.6546,
+      "step": 775
+    },
+    {
+      "epoch": 5.095541401273885,
+      "grad_norm": 6.938526153564453,
+      "learning_rate": 0.0005,
+      "loss": 1.3298,
+      "step": 800
+    },
+    {
+      "epoch": 5.254777070063694,
+      "grad_norm": 7.478129863739014,
+      "learning_rate": 0.0005,
+      "loss": 1.2336,
+      "step": 825
+    },
+    {
+      "epoch": 5.414012738853503,
+      "grad_norm": 6.950467109680176,
+      "learning_rate": 0.0005,
+      "loss": 1.2652,
+      "step": 850
+    },
+    {
+      "epoch": 5.573248407643312,
+      "grad_norm": 8.092499732971191,
+      "learning_rate": 0.0005,
+      "loss": 1.4009,
+      "step": 875
+    },
+    {
+      "epoch": 5.732484076433121,
+      "grad_norm": 6.488431930541992,
+      "learning_rate": 0.0005,
+      "loss": 1.3538,
+      "step": 900
+    },
+    {
+      "epoch": 5.89171974522293,
+      "grad_norm": 6.798085689544678,
+      "learning_rate": 0.0005,
+      "loss": 1.4269,
+      "step": 925
+    },
+    {
+      "epoch": 6.050955414012739,
+      "grad_norm": 6.3589043617248535,
+      "learning_rate": 0.0005,
+      "loss": 1.2951,
+      "step": 950
+    },
+    {
+      "epoch": 6.210191082802548,
+      "grad_norm": 6.020321369171143,
+      "learning_rate": 0.0005,
+      "loss": 1.0916,
+      "step": 975
+    },
+    {
+      "epoch": 6.369426751592357,
+      "grad_norm": 6.381227493286133,
+      "learning_rate": 0.0005,
+      "loss": 1.1623,
+      "step": 1000
+    },
+    {
+      "epoch": 6.369426751592357,
+      "eval_loss": 4.484735488891602,
+      "eval_runtime": 243.1604,
+      "eval_samples_per_second": 2.714,
+      "eval_steps_per_second": 0.173,
+      "eval_wer": 98.0078125,
+      "eval_wer_ortho": 97.75819122437248,
+      "step": 1000
     }
   ],
   "logging_steps": 25,
@@ -176,7 +326,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.30522017775616e+18,
+  "total_flos": 4.61044035551232e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null