Training in progress, step 1400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b8021f9700ff5c5a17072304ab83458e600fd5cf520c83a2df81d3e12713b5
+oid sha256:8c92440fc3b9b45e7e0e4a9674fa19fce3f0fd3fe7cb24d9f6f901b47afe242b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a3cfa7b8112c854ad186de5515ccb58d7210b5499e8ba4ca4e74fe50b0c81e
+oid sha256:683c3f3779f4ddf18b57367326dc993b25b896ad4a4cbeefdf56cfcf9e7b0fa7
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0805474fc2a510c29c9124dcbdf181d2a422e2a187e2857f77d0cb12089454cf
+oid sha256:03e04da75fa32b96fe88ee2245cd789a7ab34640f3c20d52935f88c9d082271e
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33c7c0713cd434979900bbb76c769cb47e1c794cc69ae0ade79202acbe1ca24
+oid sha256:0e0150d5c1434dee8facf0d33346f4c9f38cdcf44d6e76bcb3fd3b20f9d35c64
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d39c2fe1b10580ca81da249157bc3c1421f568f4e7be1b465cf7546d04dffd
+oid sha256:f7b996914f3debd8e889aa6e874dd0cf4525660561cc81e5c6b8e85e3aadef0c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5051568090928226,
+  "epoch": 0.5893496106082929,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -199,6 +199,38 @@
       "eval_samples_per_second": 27.541,
       "eval_steps_per_second": 3.443,
       "step": 1200
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.366485118865967,
+      "learning_rate": 4.9438869257950535e-05,
+      "loss": 3.2578,
+      "step": 1300
+    },
+    {
+      "epoch": 0.55,
+      "eval_cer": 0.5734816784638849,
+      "eval_loss": 2.000699758529663,
+      "eval_runtime": 350.6902,
+      "eval_samples_per_second": 27.027,
+      "eval_steps_per_second": 3.379,
+      "step": 1300
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 81.67564392089844,
+      "learning_rate": 4.936819787985866e-05,
+      "loss": 1.9657,
+      "step": 1400
+    },
+    {
+      "epoch": 0.59,
+      "eval_cer": 0.6325427241797349,
+      "eval_loss": 3.403754472732544,
+      "eval_runtime": 340.0489,
+      "eval_samples_per_second": 27.872,
+      "eval_steps_per_second": 3.485,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -206,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.3170915279641096e+19,
+  "total_flos": 1.5334531543694647e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null