Training in progress, step 38100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020f93a158168205cca3915538c4ed9109b5ffc2b96fdeb0f1c4d79a07042c55
+oid sha256:ad0e4d057edfb8f7f24491b899369f7b93228a9e17e1354d5f644333b4e1576d
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3befc5d87f20164d7ddccdca6c81786e192784cb6ebe0faa3bf6a1782ef9e1bc
+oid sha256:bfe756275a5388124bc2228feeaaf7ef82b935e701eb728a6a11413b046929db
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3dc33eb709a480424a714d2444abb7f1cdabf9f95720d6a97f58d1827cb80e
+oid sha256:7d38f9132e2085616601917cca2b9dcaa50f30da1f10838a4c93930581540ab0
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc3db78812f5b1281be37cba1a96865a0e99afcb4f7c40d8dd207953ac5fefc5
+oid sha256:f87a00bf8137824c3bb0753019893bcf791dd44d13ce34dc225bf7f0963a1806
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc911d1c134d3a4e026e82aa7a427672312a8867cae577cfbbeccb41bd9874b
+oid sha256:fbe3a461b22634f6c029dd4cb55ac1a5510596e6da69170fbde554202a3b4b05
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.870343085666175,
+  "epoch": 16.038728688697116,
   "eval_steps": 100,
-  "global_step": 37700,
+  "global_step": 38100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6039,6 +6039,70 @@
       "eval_samples_per_second": 25.393,
       "eval_steps_per_second": 3.175,
       "step": 37700
+    },
+    {
+      "epoch": 15.91,
+      "grad_norm": 17.767349243164062,
+      "learning_rate": 2.3652296819787986e-05,
+      "loss": 0.8418,
+      "step": 37800
+    },
+    {
+      "epoch": 15.91,
+      "eval_cer": 0.37160748504164876,
+      "eval_loss": 1.7542308568954468,
+      "eval_runtime": 389.6677,
+      "eval_samples_per_second": 24.323,
+      "eval_steps_per_second": 3.041,
+      "step": 37800
+    },
+    {
+      "epoch": 15.95,
+      "grad_norm": 6.326321601867676,
+      "learning_rate": 2.3581625441696114e-05,
+      "loss": 0.8193,
+      "step": 37900
+    },
+    {
+      "epoch": 15.95,
+      "eval_cer": 0.3725704900082124,
+      "eval_loss": 2.059025764465332,
+      "eval_runtime": 377.283,
+      "eval_samples_per_second": 25.122,
+      "eval_steps_per_second": 3.141,
+      "step": 37900
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.2139954566955566,
+      "learning_rate": 2.351095406360424e-05,
+      "loss": 0.8378,
+      "step": 38000
+    },
+    {
+      "epoch": 16.0,
+      "eval_cer": 0.37425452661217784,
+      "eval_loss": 1.9064280986785889,
+      "eval_runtime": 411.9001,
+      "eval_samples_per_second": 23.01,
+      "eval_steps_per_second": 2.877,
+      "step": 38000
+    },
+    {
+      "epoch": 16.04,
+      "grad_norm": 2.1273019313812256,
+      "learning_rate": 2.3440282685512367e-05,
+      "loss": 0.7478,
+      "step": 38100
+    },
+    {
+      "epoch": 16.04,
+      "eval_cer": 0.3710159946814751,
+      "eval_loss": 1.7977242469787598,
+      "eval_runtime": 380.1262,
+      "eval_samples_per_second": 24.934,
+      "eval_steps_per_second": 3.117,
+      "step": 38100
     }
   ],
   "logging_steps": 100,
@@ -6046,7 +6110,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.1315834714403255e+20,
+  "total_flos": 4.175077130259511e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null