Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce4b8b5a646a747bf1c54d4e55c15da75e5472d5f29c289eff679a65ba3d219
+oid sha256:7b5c8e90157800800810742119da6df94b2ac588dea70a3cc81b74764d5ce2d0
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415af2ff1829c3edaf1a17ba6db5d45417fa3e84cc95554423a2869871551398
+oid sha256:f840942c031022bad1c4d3d5f86d7af9fe204a1446a4108ca9d4b212ed8d4aeb
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979cd4e52f730e90cd87d98931f6627f47d79df2a678fcfc674113ffa4af0794
+oid sha256:4c7f9b299fba2544fcedfb299949c018ac6fda10a5718c64ae86eeb9017fefab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff56efc76c16a3b9a712527179ae61c8d6dfccc7e3a53f8c421d6329adacfbb
+oid sha256:75c0ae6a6836b9f1cff7f37594b49b4f593a2c9ec51fb43d28d45c3186fbd4ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 96.06429012981661,
   "best_model_checkpoint": "./another_local/checkpoint-1500",
-  "epoch": 9.584664536741213,
+  "epoch": 11.182108626198083,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -781,6 +781,135 @@
       "eval_steps_per_second": 0.102,
       "eval_wer": 133.89655882958996,
       "step": 3000
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 2.797142857142857e-06,
+      "loss": 0.0027,
+      "step": 3025
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 2.725714285714286e-06,
+      "loss": 0.0014,
+      "step": 3050
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 2.654285714285714e-06,
+      "loss": 0.0026,
+      "step": 3075
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 2.582857142857143e-06,
+      "loss": 0.0017,
+      "step": 3100
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 2.5114285714285718e-06,
+      "loss": 0.0016,
+      "step": 3125
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 0.0022,
+      "step": 3150
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 2.3685714285714285e-06,
+      "loss": 0.0023,
+      "step": 3175
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 2.297142857142857e-06,
+      "loss": 0.0021,
+      "step": 3200
+    },
+    {
+      "epoch": 10.3,
+      "learning_rate": 2.2257142857142857e-06,
+      "loss": 0.0016,
+      "step": 3225
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 2.1542857142857147e-06,
+      "loss": 0.0024,
+      "step": 3250
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 2.0828571428571433e-06,
+      "loss": 0.0035,
+      "step": 3275
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 2.0114285714285715e-06,
+      "loss": 0.0029,
+      "step": 3300
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 1.94e-06,
+      "loss": 0.0013,
+      "step": 3325
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 1.8685714285714289e-06,
+      "loss": 0.0034,
+      "step": 3350
+    },
+    {
+      "epoch": 10.78,
+      "learning_rate": 1.7971428571428572e-06,
+      "loss": 0.0021,
+      "step": 3375
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 1.7257142857142858e-06,
+      "loss": 0.0017,
+      "step": 3400
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.6542857142857144e-06,
+      "loss": 0.0023,
+      "step": 3425
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 1.582857142857143e-06,
+      "loss": 0.0016,
+      "step": 3450
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 1.5114285714285714e-06,
+      "loss": 0.0018,
+      "step": 3475
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 1.44e-06,
+      "loss": 0.0033,
+      "step": 3500
+    },
+    {
+      "epoch": 11.18,
+      "eval_loss": 0.5348898768424988,
+      "eval_runtime": 2303.5501,
+      "eval_samples_per_second": 0.868,
+      "eval_steps_per_second": 0.109,
+      "eval_wer": 137.85802596332167,
+      "step": 3500
     }
   ],
   "logging_steps": 25,
@@ -788,7 +917,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 13,
   "save_steps": 500,
-  "total_flos": 1.383132106653696e+19,
+  "total_flos": 1.613538690269184e+19,
   "trial_name": null,
   "trial_params": null
 }