Training in progress, step 17100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bc7c877cdfbe54847b102871e2d4073e1e3b3e77f4628403c62609d4215ee0
+oid sha256:9b9e8f1cd682c600b8cb11187fc1ab5ae248a9db42188a27ec84ab8dd6b176e3
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa0adf8ce583fad0205dd992aeb22f4bb05366efc58cf6b0feae933acf7733a
+oid sha256:e55ffbe26a558cd4d44bf377902f7de44a99d96212bf6909a06d0b6c973855f0
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1057f87e50786d1aca543245abd8aa5218ae3920b5ed10328f1cc6e8d05b8fb8
+oid sha256:d85e4e6b570f463ab7d57a8eb340d363fee4aedfddaa988b4c8532024ed27e4d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70bc272cae15954849873b08592843a4166415a3756dbd7282f8116aed448377
-size 14567
+oid sha256:9edfa95c867c886482be8a9997b5cdbca3a08cde04092b0ac7f65fec6704c015
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e32e74e7ac82af1d3f98e8ce057551c88fd1fff091ef003d7c5821593146b8
+oid sha256:5c97c09909b76b35ea84168af91d3198272a70d988945ee6a69678b1b1242e4e
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.1142917280572515,
+  "epoch": 7.198484529572721,
   "eval_steps": 100,
-  "global_step": 16900,
+  "global_step": 17100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2711,6 +2711,38 @@
       "eval_samples_per_second": 25.986,
       "eval_steps_per_second": 3.249,
       "step": 16900
+    },
+    {
+      "epoch": 7.16,
+      "grad_norm": 4.391873359680176,
+      "learning_rate": 3.834699646643109e-05,
+      "loss": 1.3334,
+      "step": 17000
+    },
+    {
+      "epoch": 7.16,
+      "eval_cer": 0.4652682726526143,
+      "eval_loss": 2.7629072666168213,
+      "eval_runtime": 380.8752,
+      "eval_samples_per_second": 24.885,
+      "eval_steps_per_second": 3.111,
+      "step": 17000
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 7.738865375518799,
+      "learning_rate": 3.827632508833923e-05,
+      "loss": 1.4858,
+      "step": 17100
+    },
+    {
+      "epoch": 7.2,
+      "eval_cer": 0.4701737319619882,
+      "eval_loss": 2.189877986907959,
+      "eval_runtime": 363.6078,
+      "eval_samples_per_second": 26.067,
+      "eval_steps_per_second": 3.259,
+      "step": 17100
     }
   ],
   "logging_steps": 100,
@@ -2718,7 +2750,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.8525968673735387e+20,
+  "total_flos": 1.8747010341512125e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null