Training in progress, step 2355, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511578a0d482675e3ff17b4d731393ce3c283abd8d16f8a85a3f15d02a56e39f
+oid sha256:9f1338dfd6f18752b4013e43c300716a64bf71b503d43f1c8bbbfc90371d4bd2
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ed9b6da13b19371de47f3a2b44715717ead8b5eeed3a91c863518d2a661a22
+oid sha256:eee60cb97d325b98f6bb5681ff52f9706d140347a9459d3b7c365c4b570b64f5
 size 1925070764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811d52f8a469bde4a4138f47efe6e2b676d318980b3df9610e6fcc5abea00325
+oid sha256:9526eb78c9d5120112457d446047c713782319439e09b5cb1a2c5b9b035bb069
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ea9d13baff2282d300ceb3c3984a3388d1450303ffc8640c73967fa3325903
+oid sha256:617bb927196c8fc850b17a9f4bc1faa1c723902215e41b7b836f9d3bc37475b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 78.86568308105001,
   "best_model_checkpoint": "./whisper-small-ha-adam-v4/checkpoint-2000",
-  "epoch": 12.738853503184714,
+  "epoch": 15.0,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2355,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,6 +607,104 @@
       "eval_wer": 78.86568308105001,
       "eval_wer_ortho": 81.0546875,
       "step": 2000
+    },
+    {
+      "epoch": 12.898089171974522,
+      "grad_norm": 2.6695284843444824,
+      "learning_rate": 5e-05,
+      "loss": 0.0364,
+      "step": 2025
+    },
+    {
+      "epoch": 13.05732484076433,
+      "grad_norm": 1.3920303583145142,
+      "learning_rate": 5e-05,
+      "loss": 0.0314,
+      "step": 2050
+    },
+    {
+      "epoch": 13.21656050955414,
+      "grad_norm": 2.2318477630615234,
+      "learning_rate": 5e-05,
+      "loss": 0.0226,
+      "step": 2075
+    },
+    {
+      "epoch": 13.375796178343949,
+      "grad_norm": 2.457688093185425,
+      "learning_rate": 5e-05,
+      "loss": 0.0374,
+      "step": 2100
+    },
+    {
+      "epoch": 13.535031847133759,
+      "grad_norm": 3.3562824726104736,
+      "learning_rate": 5e-05,
+      "loss": 0.0263,
+      "step": 2125
+    },
+    {
+      "epoch": 13.694267515923567,
+      "grad_norm": 2.763430118560791,
+      "learning_rate": 5e-05,
+      "loss": 0.0359,
+      "step": 2150
+    },
+    {
+      "epoch": 13.853503184713375,
+      "grad_norm": 5.378473281860352,
+      "learning_rate": 5e-05,
+      "loss": 0.039,
+      "step": 2175
+    },
+    {
+      "epoch": 14.012738853503185,
+      "grad_norm": 2.072021007537842,
+      "learning_rate": 5e-05,
+      "loss": 0.0373,
+      "step": 2200
+    },
+    {
+      "epoch": 14.171974522292993,
+      "grad_norm": 1.6606969833374023,
+      "learning_rate": 5e-05,
+      "loss": 0.0263,
+      "step": 2225
+    },
+    {
+      "epoch": 14.331210191082803,
+      "grad_norm": 3.090102195739746,
+      "learning_rate": 5e-05,
+      "loss": 0.0257,
+      "step": 2250
+    },
+    {
+      "epoch": 14.490445859872612,
+      "grad_norm": 6.045629024505615,
+      "learning_rate": 5e-05,
+      "loss": 0.0232,
+      "step": 2275
+    },
+    {
+      "epoch": 14.64968152866242,
+      "grad_norm": 0.8971702456474304,
+      "learning_rate": 5e-05,
+      "loss": 0.0263,
+      "step": 2300
+    },
+    {
+      "epoch": 14.80891719745223,
+      "grad_norm": 0.5613566637039185,
+      "learning_rate": 5e-05,
+      "loss": 0.0295,
+      "step": 2325
+    },
+    {
+      "epoch": 14.968152866242038,
+      "grad_norm": 3.578268051147461,
+      "learning_rate": 5e-05,
+      "loss": 0.0246,
+      "step": 2350
     }
   ],
   "logging_steps": 25,
@@ -621,12 +719,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.22088071102464e+18,
+  "total_flos": 1.08565827600384e+19,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null