Training in progress, step 22500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175f57d07b0e91adc9c8055925891211b504a9b48270f592db96ead8512d7c7b
+oid sha256:8a6f6fa04efb391c7b9fbd08481c3254f51e8b2441232585f62a46a10bf14603
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04cb8514703cca78500164b993eb886d31669612d415ba232a911b523bfd3313
+oid sha256:d778a8ad947e1c4d0ef5534ea92304b2cc11141de4fb34b0cf684c5c48ad306b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2b5b20edfc5f9195de76f747ceab8b43d46ecd014a55d7485a62a63fcd76d6
+oid sha256:bc91affcdb5daa6221794d9599eeb12bcba1f681e61698d0b5225d19c1246f0d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182d9406686494df886f6cec38ea8c8d1bbeb433cd5dfa0f6ee519db21afd2c9
+oid sha256:275755e5f99f71b688f2ecd5a64a5f85d430b909b06bf279b4dfbdc41ff3aab1
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062c50ab1af8e6690bf17da280baa79f2a4e74793c5216941d3596cf5fbc6a4b
+oid sha256:b142e6816a019f0e45a0c6af01127180a64accf85a0b47c2b9c58feab018eef9
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.387497368974953,
+  "epoch": 9.471690170490422,
   "eval_steps": 100,
-  "global_step": 22300,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3575,6 +3575,38 @@
       "eval_samples_per_second": 25.697,
       "eval_steps_per_second": 3.213,
       "step": 22300
+    },
+    {
+      "epoch": 9.43,
+      "grad_norm": 10.591804504394531,
+      "learning_rate": 3.4532862190812723e-05,
+      "loss": 1.4811,
+      "step": 22400
+    },
+    {
+      "epoch": 9.43,
+      "eval_cer": 0.44453922412107466,
+      "eval_loss": 2.3979556560516357,
+      "eval_runtime": 383.7637,
+      "eval_samples_per_second": 24.697,
+      "eval_steps_per_second": 3.088,
+      "step": 22400
+    },
+    {
+      "epoch": 9.47,
+      "grad_norm": 7.108492374420166,
+      "learning_rate": 3.446219081272085e-05,
+      "loss": 1.5169,
+      "step": 22500
+    },
+    {
+      "epoch": 9.47,
+      "eval_cer": 0.4425838840874428,
+      "eval_loss": 1.763051152229309,
+      "eval_runtime": 371.2126,
+      "eval_samples_per_second": 25.533,
+      "eval_steps_per_second": 3.192,
+      "step": 22500
     }
   ],
   "logging_steps": 100,
@@ -3582,7 +3614,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.4437274203205743e+20,
+  "total_flos": 2.4656325068595944e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null