Training in progress, step 22300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2effce087c71e7b4f5411ac336511daf6bbbe1e3ecbac9348a8792a025918d9
+oid sha256:175f57d07b0e91adc9c8055925891211b504a9b48270f592db96ead8512d7c7b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a22c61a8979b9f44e4c8c22f66fbed3c19bc88f463a4f974eac0e1c4d0de281
+oid sha256:04cb8514703cca78500164b993eb886d31669612d415ba232a911b523bfd3313
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112820ec059ab52f61273d81ee9a8ae1d15140adca820a8935a7074524ca4d69
+oid sha256:8a2b5b20edfc5f9195de76f747ceab8b43d46ecd014a55d7485a62a63fcd76d6
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699594f94310cf08af521c6d50d89fc54dec73b61991d34be34e9fc33928c3be
-size 14503
+oid sha256:182d9406686494df886f6cec38ea8c8d1bbeb433cd5dfa0f6ee519db21afd2c9
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e6b1f4714aff0d0b0d7f3c9208419cd1fd98d5d42618c80a7c7b656aa11290a
+oid sha256:062c50ab1af8e6690bf17da280baa79f2a4e74793c5216941d3596cf5fbc6a4b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.303304567459483,
+  "epoch": 9.387497368974953,
   "eval_steps": 100,
-  "global_step": 22100,
+  "global_step": 22300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3543,6 +3543,38 @@
       "eval_samples_per_second": 26.125,
       "eval_steps_per_second": 3.266,
       "step": 22100
+    },
+    {
+      "epoch": 9.35,
+      "grad_norm": 4.20334005355835,
+      "learning_rate": 3.467420494699647e-05,
+      "loss": 1.239,
+      "step": 22200
+    },
+    {
+      "epoch": 9.35,
+      "eval_cer": 0.44948623440616325,
+      "eval_loss": 3.0320708751678467,
+      "eval_runtime": 386.6159,
+      "eval_samples_per_second": 24.515,
+      "eval_steps_per_second": 3.065,
+      "step": 22200
+    },
+    {
+      "epoch": 9.39,
+      "grad_norm": 12.748970985412598,
+      "learning_rate": 3.4603533568904595e-05,
+      "loss": 1.622,
+      "step": 22300
+    },
+    {
+      "epoch": 9.39,
+      "eval_cer": 0.4492564819522115,
+      "eval_loss": 2.2297956943511963,
+      "eval_runtime": 368.8399,
+      "eval_samples_per_second": 25.697,
+      "eval_steps_per_second": 3.213,
+      "step": 22300
     }
   ],
   "logging_steps": 100,
@@ -3550,7 +3582,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.4217119796381745e+20,
+  "total_flos": 2.4437274203205743e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null