Training in progress, step 17300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9e8f1cd682c600b8cb11187fc1ab5ae248a9db42188a27ec84ab8dd6b176e3
+oid sha256:c9915848c279a32e634c469b0cd49c641ab6e19d1f12ab63586b15141e71e2ff
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55ffbe26a558cd4d44bf377902f7de44a99d96212bf6909a06d0b6c973855f0
+oid sha256:f68a28b7e883abd00c6a38b16ebfd97e5dbc91456ae2135fbf6f28e8d925b88f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85e4e6b570f463ab7d57a8eb340d363fee4aedfddaa988b4c8532024ed27e4d
+oid sha256:f7df9b4087f5ce2cea1f800e25a7466947cb6d1214cdffaffc25123e1bb0bb13
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edfa95c867c886482be8a9997b5cdbca3a08cde04092b0ac7f65fec6704c015
-size 14503
+oid sha256:f19a2b3d5b09e84e1a35bc5f845262cba53dc3c05a02dcd9cba7de0d91a8a4f5
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c97c09909b76b35ea84168af91d3198272a70d988945ee6a69678b1b1242e4e
+oid sha256:b9ba2f276f83843e2fa9769f7226e4efaa28337fe59f7a213254e795359656f2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.198484529572721,
+  "epoch": 7.282677331088192,
   "eval_steps": 100,
-  "global_step": 17100,
+  "global_step": 17300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2743,6 +2743,38 @@
       "eval_samples_per_second": 26.067,
       "eval_steps_per_second": 3.259,
       "step": 17100
+    },
+    {
+      "epoch": 7.24,
+      "grad_norm": Infinity,
+      "learning_rate": 3.820636042402827e-05,
+      "loss": 1.5317,
+      "step": 17200
+    },
+    {
+      "epoch": 7.24,
+      "eval_cer": 0.47163290446208594,
+      "eval_loss": 1.9506334066390991,
+      "eval_runtime": 380.9688,
+      "eval_samples_per_second": 24.879,
+      "eval_steps_per_second": 3.11,
+      "step": 17200
+    },
+    {
+      "epoch": 7.28,
+      "grad_norm": 19.556819915771484,
+      "learning_rate": 3.81356890459364e-05,
+      "loss": 1.3515,
+      "step": 17300
+    },
+    {
+      "epoch": 7.28,
+      "eval_cer": 0.45843191506002895,
+      "eval_loss": 2.2836623191833496,
+      "eval_runtime": 361.9084,
+      "eval_samples_per_second": 26.189,
+      "eval_steps_per_second": 3.274,
+      "step": 17300
     }
   ],
   "logging_steps": 100,
@@ -2750,7 +2782,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.8747010341512125e+20,
+  "total_flos": 1.896270263543528e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null