Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3868621092066d9c24b3bc273ddea38df384e76d5cc80b400d81d8d89f73e69c
+oid sha256:eb403a535ad09ffb3db18e28ff22ca7321ac24112f1b0ebd5fb7b126d132cfcf
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecd6d321346303115578fc2fa2d3c6f5a5eb4de026a90d83e95de5f74d3fe57
+oid sha256:2573f15e6026935d052bcf5fa43428dc713f2b549578e1cb7be368b8a7e0c68f
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc19516f0bb6ebbb441d01c76bfbe40ffc86ac7def6317731979041e8f3b7ba
+oid sha256:6877a86255d479aa07a4b83c14c41508bcfadb2d86e9dfcacd37452785832d95
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c4a1cd4c8fefc9d743dd5f12e4bfb7db165516749e36aa376f6a985fe0db25
+oid sha256:e0ab494ff3562316b4fb78dd7ef9c324bf8d9779393051ef5dd2d7639681801b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 105.19266433134145,
   "best_model_checkpoint": "./another_local/checkpoint-500",
-  "epoch": 1.5974440894568689,
+  "epoch": 3.194888178913738,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -136,6 +136,135 @@
       "eval_steps_per_second": 0.1,
       "eval_wer": 105.19266433134145,
       "step": 500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 0.1983,
+      "step": 525
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 9.86857142857143e-06,
+      "loss": 0.2248,
+      "step": 550
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 9.797142857142858e-06,
+      "loss": 0.1991,
+      "step": 575
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.725714285714287e-06,
+      "loss": 0.2179,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.654285714285716e-06,
+      "loss": 0.2157,
+      "step": 625
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.582857142857143e-06,
+      "loss": 0.0822,
+      "step": 650
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.511428571428572e-06,
+      "loss": 0.0778,
+      "step": 675
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 0.0879,
+      "step": 700
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 9.368571428571428e-06,
+      "loss": 0.0868,
+      "step": 725
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.297142857142857e-06,
+      "loss": 0.0785,
+      "step": 750
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 9.225714285714286e-06,
+      "loss": 0.075,
+      "step": 775
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 9.154285714285715e-06,
+      "loss": 0.0804,
+      "step": 800
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 9.082857142857143e-06,
+      "loss": 0.0794,
+      "step": 825
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 9.011428571428572e-06,
+      "loss": 0.0797,
+      "step": 850
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.94e-06,
+      "loss": 0.076,
+      "step": 875
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.86857142857143e-06,
+      "loss": 0.0802,
+      "step": 900
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.797142857142857e-06,
+      "loss": 0.0755,
+      "step": 925
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 8.725714285714286e-06,
+      "loss": 0.0619,
+      "step": 950
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 8.654285714285715e-06,
+      "loss": 0.0327,
+      "step": 975
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.582857142857144e-06,
+      "loss": 0.033,
+      "step": 1000
+    },
+    {
+      "epoch": 3.19,
+      "eval_loss": 0.45066991448402405,
+      "eval_runtime": 2606.2897,
+      "eval_samples_per_second": 0.767,
+      "eval_steps_per_second": 0.096,
+      "eval_wer": 209.08201112713786,
+      "step": 1000
     }
   ],
   "logging_steps": 25,
@@ -143,7 +272,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 13,
   "save_steps": 500,
-  "total_flos": 2.30637451935744e+18,
+  "total_flos": 4.61044035551232e+18,
   "trial_name": null,
   "trial_params": null
 }