Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b1c2533249bd83cd4dc058e8c9ac7a86cb809728991da29e3e26d9567e4925
+oid sha256:1ce4b8b5a646a747bf1c54d4e55c15da75e5472d5f29c289eff679a65ba3d219
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b92ccd1bf0adff93fc0579be75a0b6901f7257675e1c39f5344bc054c1bfcab5
+oid sha256:415af2ff1829c3edaf1a17ba6db5d45417fa3e84cc95554423a2869871551398
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad752088b229d78039d00fa98cec499de1d448da781bc7460fcfe8880b39ae1
+oid sha256:979cd4e52f730e90cd87d98931f6627f47d79df2a678fcfc674113ffa4af0794
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f181a0117afba799e29e5c923c7c87a52316143822f05b0b57dfd50707300da
+oid sha256:1ff56efc76c16a3b9a712527179ae61c8d6dfccc7e3a53f8c421d6329adacfbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 96.06429012981661,
   "best_model_checkpoint": "./another_local/checkpoint-1500",
-  "epoch": 7.987220447284345,
+  "epoch": 9.584664536741213,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -652,6 +652,135 @@
       "eval_steps_per_second": 0.104,
       "eval_wer": 126.81331135380178,
       "step": 2500
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 4.225714285714286e-06,
+      "loss": 0.0036,
+      "step": 2525
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 4.154285714285714e-06,
+      "loss": 0.0037,
+      "step": 2550
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 4.082857142857143e-06,
+      "loss": 0.0025,
+      "step": 2575
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 4.011428571428571e-06,
+      "loss": 0.0031,
+      "step": 2600
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 3.94e-06,
+      "loss": 0.0022,
+      "step": 2625
+    },
+    {
+      "epoch": 8.47,
+      "learning_rate": 3.8685714285714286e-06,
+      "loss": 0.0034,
+      "step": 2650
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 3.7971428571428576e-06,
+      "loss": 0.0021,
+      "step": 2675
+    },
+    {
+      "epoch": 8.63,
+      "learning_rate": 3.7257142857142857e-06,
+      "loss": 0.0032,
+      "step": 2700
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 3.6542857142857148e-06,
+      "loss": 0.0028,
+      "step": 2725
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 3.582857142857143e-06,
+      "loss": 0.0032,
+      "step": 2750
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 3.511428571428572e-06,
+      "loss": 0.0035,
+      "step": 2775
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 3.44e-06,
+      "loss": 0.0023,
+      "step": 2800
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 3.3685714285714287e-06,
+      "loss": 0.0029,
+      "step": 2825
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 3.2971428571428577e-06,
+      "loss": 0.0021,
+      "step": 2850
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 3.225714285714286e-06,
+      "loss": 0.0022,
+      "step": 2875
+    },
+    {
+      "epoch": 9.27,
+      "learning_rate": 3.154285714285715e-06,
+      "loss": 0.0057,
+      "step": 2900
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 3.082857142857143e-06,
+      "loss": 0.0026,
+      "step": 2925
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 3.0114285714285716e-06,
+      "loss": 0.0019,
+      "step": 2950
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 0.0017,
+      "step": 2975
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 2.868571428571429e-06,
+      "loss": 0.0047,
+      "step": 3000
+    },
+    {
+      "epoch": 9.58,
+      "eval_loss": 0.5272812247276306,
+      "eval_runtime": 2446.9046,
+      "eval_samples_per_second": 0.817,
+      "eval_steps_per_second": 0.102,
+      "eval_wer": 133.89655882958996,
+      "step": 3000
     }
   ],
   "logging_steps": 25,
@@ -659,7 +788,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 13,
   "save_steps": 500,
-  "total_flos": 1.152725523038208e+19,
+  "total_flos": 1.383132106653696e+19,
   "trial_name": null,
   "trial_params": null
 }