Training in progress, step 15500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e3b409ae9269874d0dd07332eaabd922261fe01cec899b7c68b52edc3ad9fd
+oid sha256:c8d9f8936035594d661114b781a4eb14f9085f107b414f8cdb04fae2af1f5af1
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1863c52a91cc2b8af17921581add7d3bdb0649beb55c88accdc1808b8887921
+oid sha256:e4e230029c183533b0b9fe6b84165574a15e9c485917cb915f98f6e96e5f4e98
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b49ad51dac0d37607816c8facfc0a5fc8fab9c0432f13fc416fe9a10708dbf
+oid sha256:4e7906e6327d11d85d338ea4339351ae9c0034f62b94b4da68358eaacc6ab527
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa352733c862d27845c9026dc711e2ed499a1cad4d9c2f6e899513e4bf06feaf
-size 14567
+oid sha256:a9b0b65f0420889adb98f67d37d7d10f35fcca76dcf8679e43243891e5dcf6a5
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3eed1d7dd9c8188a0bfa480abfdd7fb182d631c9cffcad33cd5ac2b85611af8
+oid sha256:d310350e2d89a95e16a26ae72f1a3c391fc38d88fcd18e2b9a8d9e4038006a55
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.440749315933488,
+  "epoch": 6.524942117448958,
   "eval_steps": 100,
-  "global_step": 15300,
+  "global_step": 15500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2455,6 +2455,38 @@
       "eval_samples_per_second": 26.066,
       "eval_steps_per_second": 3.259,
       "step": 15300
+    },
+    {
+      "epoch": 6.48,
+      "grad_norm": 32.08698654174805,
+      "learning_rate": 3.947773851590106e-05,
+      "loss": 2.0638,
+      "step": 15400
+    },
+    {
+      "epoch": 6.48,
+      "eval_cer": 0.4723588244495718,
+      "eval_loss": 2.9272561073303223,
+      "eval_runtime": 386.8412,
+      "eval_samples_per_second": 24.501,
+      "eval_steps_per_second": 3.063,
+      "step": 15400
+    },
+    {
+      "epoch": 6.52,
+      "grad_norm": 1.8787578344345093,
+      "learning_rate": 3.940706713780919e-05,
+      "loss": 1.3608,
+      "step": 15500
+    },
+    {
+      "epoch": 6.52,
+      "eval_cer": 0.4626187869070431,
+      "eval_loss": 3.0016987323760986,
+      "eval_runtime": 353.2265,
+      "eval_samples_per_second": 26.833,
+      "eval_steps_per_second": 3.355,
+      "step": 15500
     }
   ],
   "logging_steps": 100,
@@ -2462,7 +2494,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.6764322951864136e+20,
+  "total_flos": 1.6980516265683495e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null