Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5c8e90157800800810742119da6df94b2ac588dea70a3cc81b74764d5ce2d0
+oid sha256:5fc6dd70651add99ed7978f4a1a498c9cf9f5df4a513779e562baacfc10bfeba
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f840942c031022bad1c4d3d5f86d7af9fe204a1446a4108ca9d4b212ed8d4aeb
+oid sha256:c12130ff78953a4ce0a1257bf758342a5e77a9de46862aa3e4e418c97f59cd24
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7f9b299fba2544fcedfb299949c018ac6fda10a5718c64ae86eeb9017fefab
+oid sha256:07d039bc3fdc4b6313d1e6e6a91532f954d6b9332fea72a7271f539a91baf227
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c0ae6a6836b9f1cff7f37594b49b4f593a2c9ec51fb43d28d45c3186fbd4ab
+oid sha256:7efbf80617c96c78286826ce59d9a12c86da62d7631874b3d6364a8e993ada60
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 96.06429012981661,
   "best_model_checkpoint": "./another_local/checkpoint-1500",
-  "epoch": 11.182108626198083,
+  "epoch": 12.779552715654953,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -910,6 +910,135 @@
       "eval_steps_per_second": 0.109,
       "eval_wer": 137.85802596332167,
       "step": 3500
+    },
+    {
+      "epoch": 11.26,
+      "learning_rate": 1.3685714285714286e-06,
+      "loss": 0.0018,
+      "step": 3525
+    },
+    {
+      "epoch": 11.34,
+      "learning_rate": 1.2971428571428574e-06,
+      "loss": 0.0012,
+      "step": 3550
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 1.2257142857142857e-06,
+      "loss": 0.0018,
+      "step": 3575
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 1.1542857142857143e-06,
+      "loss": 0.0025,
+      "step": 3600
+    },
+    {
+      "epoch": 11.58,
+      "learning_rate": 1.082857142857143e-06,
+      "loss": 0.0024,
+      "step": 3625
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 1.0114285714285715e-06,
+      "loss": 0.003,
+      "step": 3650
+    },
+    {
+      "epoch": 11.74,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 0.001,
+      "step": 3675
+    },
+    {
+      "epoch": 11.82,
+      "learning_rate": 8.685714285714286e-07,
+      "loss": 0.0023,
+      "step": 3700
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 7.971428571428572e-07,
+      "loss": 0.0024,
+      "step": 3725
+    },
+    {
+      "epoch": 11.98,
+      "learning_rate": 7.257142857142857e-07,
+      "loss": 0.0034,
+      "step": 3750
+    },
+    {
+      "epoch": 12.06,
+      "learning_rate": 6.542857142857144e-07,
+      "loss": 0.003,
+      "step": 3775
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 5.82857142857143e-07,
+      "loss": 0.0012,
+      "step": 3800
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 5.114285714285714e-07,
+      "loss": 0.0023,
+      "step": 3825
+    },
+    {
+      "epoch": 12.3,
+      "learning_rate": 4.4e-07,
+      "loss": 0.0017,
+      "step": 3850
+    },
+    {
+      "epoch": 12.38,
+      "learning_rate": 3.685714285714286e-07,
+      "loss": 0.0022,
+      "step": 3875
+    },
+    {
+      "epoch": 12.46,
+      "learning_rate": 2.9714285714285715e-07,
+      "loss": 0.0033,
+      "step": 3900
+    },
+    {
+      "epoch": 12.54,
+      "learning_rate": 2.2571428571428574e-07,
+      "loss": 0.0019,
+      "step": 3925
+    },
+    {
+      "epoch": 12.62,
+      "learning_rate": 1.542857142857143e-07,
+      "loss": 0.001,
+      "step": 3950
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 8.285714285714285e-08,
+      "loss": 0.0019,
+      "step": 3975
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 1.142857142857143e-08,
+      "loss": 0.0026,
+      "step": 4000
+    },
+    {
+      "epoch": 12.78,
+      "eval_loss": 0.5372153520584106,
+      "eval_runtime": 2322.1625,
+      "eval_samples_per_second": 0.861,
+      "eval_steps_per_second": 0.108,
+      "eval_wer": 130.3266021017927,
+      "step": 4000
     }
   ],
   "logging_steps": 25,
@@ -917,7 +1046,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 13,
   "save_steps": 500,
-  "total_flos": 1.613538690269184e+19,
+  "total_flos": 1.844176142204928e+19,
   "trial_name": null,
   "trial_params": null
 }