Training in progress, step 47100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfbe3fca61cc77c707b6d697b41387c813bc32fd6d32bd5c1c26762aa6213e5
+oid sha256:b23224f934a17dc506ef1427bbf8cfdde7e61c9bdb99bd40ce08a456d490987e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79ff95105c45438b111e350a13810a36dce99b6fcbea094936e85e5e0a2e3ab
+oid sha256:7371001d4ba61fec2f6a59fd465a7448ca595cd03c65ce64b593c30a44dfdc70
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fafe221adf68f53b28e28362f927e1c10f230fee3f19fb1f737d95674a280f
+oid sha256:07b8ed1471e9d069014988f3a9a12d0676eb5b06684acbd3950cb1c7d97542ef
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65da35c1d2659bcfb09a26ed28519b60a522956dd7f331870d788477aa1a474
+oid sha256:78799255d33f45caeb9e5437f76e75e8206e20b85f04c1c95d15dd5e461cdfad
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e7a17c080461acc65ee185f2f70c19263f58e165eb35d2d33f300ca2a7104a
+oid sha256:dc0e4855190486656b49bc2f9aa7a1bf13ae4f23b65ee19ad5630270c8d3910a
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.743211955377816,
+  "epoch": 19.827404756893287,
   "eval_steps": 100,
-  "global_step": 46900,
+  "global_step": 47100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7511,6 +7511,38 @@
       "eval_samples_per_second": 25.662,
       "eval_steps_per_second": 3.208,
       "step": 46900
+    },
+    {
+      "epoch": 19.79,
+      "grad_norm": 2.5223989486694336,
+      "learning_rate": 1.7153356890459365e-05,
+      "loss": 0.4852,
+      "step": 47000
+    },
+    {
+      "epoch": 19.79,
+      "eval_cer": 0.34921639748152206,
+      "eval_loss": 2.3917760848999023,
+      "eval_runtime": 383.3871,
+      "eval_samples_per_second": 24.722,
+      "eval_steps_per_second": 3.091,
+      "step": 47000
+    },
+    {
+      "epoch": 19.83,
+      "grad_norm": 13.549793243408203,
+      "learning_rate": 1.7082685512367493e-05,
+      "loss": 0.4983,
+      "step": 47100
+    },
+    {
+      "epoch": 19.83,
+      "eval_cer": 0.34820450901411754,
+      "eval_loss": 2.331942319869995,
+      "eval_runtime": 370.3076,
+      "eval_samples_per_second": 25.595,
+      "eval_steps_per_second": 3.2,
+      "step": 47100
     }
   ],
   "logging_steps": 100,
@@ -7518,7 +7550,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.13961492307041e+20,
+  "total_flos": 5.161374507685376e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null