Training in progress, step 3000, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc398ff23230c89e87f53312c3810b8834a5415fffe40e6ef729219393f73c22
+oid sha256:d81aae13b365443a745dea31dcf4f13d22c1eac1ec4d4f06dc77b395dda29b3f
 size 4992706480

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b287b59abaa725a86c71b140353928ec44f1cd87ea1e76e4dc750ebc139633
+oid sha256:ebde8228af7642dd6dfec59b6ee669f9c738ffc2cb54f68eaf5fe19ea5d09975
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac754e5794fffa36628c4c731133d2ed01862775619d8c98510105de3861c53
+oid sha256:b2af879b349b89c34400a40fe61b42c7d7c2a258e413f47d598d3ebb1ce21ea7
 size 3137197104

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3aa5344cc910cb75bd602d7ae0546f81de8bb0a34e38ddd9c75b43852cc2fb1
+oid sha256:5cb0e5d7eac7bab014dfe230c97572d40dd037e6b861e418de5eed60e974a907
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebff8515314a4035d1544b55fdb7220ba3b47a3cdfb089d81aa7ad4521721bf1
+oid sha256:d5255fca8f83e8feb8880071c964cae2f5bef65ca62e68ed9f0d6bd2d1911f6d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f578ea9cd0ec24d5b514079228f354d9a10658abb872dcacb65f11c70e45bbdb
+oid sha256:218871e03b7d78375a25b70f9ef3febcabfec1769a42e28471683d6151386b5b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c176dce8f62927af169095f249d0f7e77d81886784fbc18e97614e26057c92f
+oid sha256:1628673420e2e6d6a338ba86a5c2c3b21604b8baee88654e5ab8e9a27ccf6e7c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e76828fe04659325cb09120e5b627eb9da0a73daa64f8d5208c6840bd1126fa
+oid sha256:53499bcc0ec9de57d4bade260f2fda08d6da0c79d24e43479c1eeca46b224d98
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 61.90141246696956,
   "best_model_checkpoint": "./models/rootflo/fauna-v0.8/checkpoint-2000",
-  "epoch": 8.556149732620321,
+  "epoch": 12.834224598930481,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -53,6 +53,29 @@
       "eval_steps_per_second": 0.006,
       "eval_wer": 61.90141246696956,
       "step": 2000
+    },
+    {
+      "epoch": 10.695187165775401,
+      "grad_norm": 0.6504905819892883,
+      "learning_rate": 4.952345503673166e-06,
+      "loss": 0.0183,
+      "step": 2500
+    },
+    {
+      "epoch": 12.834224598930481,
+      "grad_norm": 0.8102747201919556,
+      "learning_rate": 4.810824323930563e-06,
+      "loss": 0.0115,
+      "step": 3000
+    },
+    {
+      "epoch": 12.834224598930481,
+      "eval_loss": 0.08655478060245514,
+      "eval_runtime": 1264.8967,
+      "eval_samples_per_second": 2.056,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 62.38047259661996,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -67,7 +90,7 @@
         "early_stopping_threshold": 0.25
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -81,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.891786271351789e+21,
+  "total_flos": 7.337679407027684e+21,
   "train_batch_size": 72,
   "trial_name": null,
   "trial_params": null