Training in progress, step 2000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a0fd87b6cd4c60d2b725529561edfd75c6f68224a482292ad2e288a0d4154c
+oid sha256:fc398ff23230c89e87f53312c3810b8834a5415fffe40e6ef729219393f73c22
 size 4992706480

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ba41e21ef42a953dcc925a126cdbb695eac994195babfac00dc60ea9f442d1
+oid sha256:72b287b59abaa725a86c71b140353928ec44f1cd87ea1e76e4dc750ebc139633
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19191339e6b35a9e6a4a92b44abe298ea6a0525f8d61ea6d570d0d97e78aec0
+oid sha256:cac754e5794fffa36628c4c731133d2ed01862775619d8c98510105de3861c53
 size 3137197104

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042f9e7198612cedfae5aaef319364d51155ef6dc06f7ca817c41c7ca9cfa633
+oid sha256:f3aa5344cc910cb75bd602d7ae0546f81de8bb0a34e38ddd9c75b43852cc2fb1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe074d34929494034056571926866a860bbbe76a70428ca226a890476501700
+oid sha256:ebff8515314a4035d1544b55fdb7220ba3b47a3cdfb089d81aa7ad4521721bf1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d531819700d9bb14ae1289f538dff3b3e1616ea0e6f66891c56854fe0f47143
+oid sha256:f578ea9cd0ec24d5b514079228f354d9a10658abb872dcacb65f11c70e45bbdb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2d7248de199ff767be2b24596a1eb9f82518a530463d67c329f96174629730
+oid sha256:4c176dce8f62927af169095f249d0f7e77d81886784fbc18e97614e26057c92f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d11a038b5f7d519edbdddfa7bea294584aafaf244ff06aeb48c83eeff24b653
+oid sha256:8e76828fe04659325cb09120e5b627eb9da0a73daa64f8d5208c6840bd1126fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 62.958386403817265,
-  "best_model_checkpoint": "./models/rootflo/fauna-v0.8/checkpoint-1000",
-  "epoch": 4.278074866310161,
+  "best_metric": 61.90141246696956,
+  "best_model_checkpoint": "./models/rootflo/fauna-v0.8/checkpoint-2000",
+  "epoch": 8.556149732620321,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,29 @@
       "eval_steps_per_second": 0.006,
       "eval_wer": 62.958386403817265,
       "step": 1000
+    },
+    {
+      "epoch": 6.4171122994652405,
+      "grad_norm": 0.5753424167633057,
+      "learning_rate": 3.745e-06,
+      "loss": 0.0391,
+      "step": 1500
+    },
+    {
+      "epoch": 8.556149732620321,
+      "grad_norm": 0.6431854963302612,
+      "learning_rate": 4.9950000000000005e-06,
+      "loss": 0.0287,
+      "step": 2000
+    },
+    {
+      "epoch": 8.556149732620321,
+      "eval_loss": 0.07155641168355942,
+      "eval_runtime": 1251.3824,
+      "eval_samples_per_second": 2.078,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 61.90141246696956,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -58,7 +81,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4458931356758945e+21,
+  "total_flos": 4.891786271351789e+21,
   "train_batch_size": 72,
   "trial_name": null,
   "trial_params": null