Training in progress, step 36300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d3f4d3140e24d9a2d9d515b8e731fb422050a6d4777c3f3f41351c89e5a125
+oid sha256:212fd85a8f0771f83e70fda3fe36ae1286fc6ca154640d937c6b46050c337f8f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c34024a06fc4af618b6f6751f21e3b53d49f48981ef0d0d79f68ee6eff6a9b5
+oid sha256:705d5ee447293f9a70d2f66760196b2c46343eca0cdcd5524ec4f3b449b70b84
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c97f92419b82a234f5ed95c05e5eeea91614d5e9d89d45875d7e2fcc4d2634c
+oid sha256:67b3b70c810545bf21d9ddf057aebcb724eb6e9a8a7e6c91016e8f0e815ec023
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd61ea82574fa5aa908afe65ac4133feb6f83558ee3a2931d9b8b5b34f0e3f4
-size 14567
+oid sha256:8a5b2fbf1a12d8205cee3894c54223b35a4a80e438d87a963917ccf699aca0e2
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4e7346e819a03a37a4b1eb1e2725223d670f029e6e9ea037250603b481398f
+oid sha256:764ca9ef7fae34c6a8cba4f8df83adaaaca50ef1ca45f561d696e2b2507c6419
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.196800673542413,
+  "epoch": 15.280993475057883,
   "eval_steps": 100,
-  "global_step": 36100,
+  "global_step": 36300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5783,6 +5783,38 @@
       "eval_samples_per_second": 25.339,
       "eval_steps_per_second": 3.168,
       "step": 36100
+    },
+    {
+      "epoch": 15.24,
+      "grad_norm": 7.441462516784668,
+      "learning_rate": 2.478303886925795e-05,
+      "loss": 0.8271,
+      "step": 36200
+    },
+    {
+      "epoch": 15.24,
+      "eval_cer": 0.3848451370693364,
+      "eval_loss": 2.453676700592041,
+      "eval_runtime": 392.8332,
+      "eval_samples_per_second": 24.127,
+      "eval_steps_per_second": 3.017,
+      "step": 36200
+    },
+    {
+      "epoch": 15.28,
+      "grad_norm": 1.4820858240127563,
+      "learning_rate": 2.4712367491166082e-05,
+      "loss": 0.8265,
+      "step": 36300
+    },
+    {
+      "epoch": 15.28,
+      "eval_cer": 0.3837550350005866,
+      "eval_loss": 2.4253969192504883,
+      "eval_runtime": 373.2352,
+      "eval_samples_per_second": 25.394,
+      "eval_steps_per_second": 3.175,
+      "step": 36300
     }
   ],
   "logging_steps": 100,
@@ -5790,7 +5822,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.956666718927042e+20,
+  "total_flos": 3.9789875911390396e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null