Training in progress, step 4600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed94b7d4fd42216fd390d328de3f151a13b33b430c74ab44fd10d269e21255f
+oid sha256:2a389c3f77e972b9ad2c3598a897a595d740c11eef3134fc3913b671d5c4aa98
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114e0d1544f075ef1319771189365fc113997893216e4ea0068921b7c565ab65
+oid sha256:4cf523156e6cfba18fe652208aa23b347ae9fa03eb5a27cf6ee2de9b87e0b018
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66847a5e03866b474e266e8d744ea25e9bff8591fdc6492a9f466e6f006cf3e0
+oid sha256:972ad41e162646ea15a0a97c616a6a668482e5a2db3e8f5673ee3c315481e243
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2866e2329d94cbbc60d5487c4e462b71b5c661406207215119e66ed7e27271b9
+oid sha256:0965352267660a565504fd8fd4be8deea39448c1829b29947da55924c359a90b
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297bafaeae03f2ece08ad43e10bf1c267d31323b128e711289b3291e220124fe
+oid sha256:dd64d58f0ca1f8e908f6d74c38fec76a5c8bd2eba7e4b0c0c52260244cc0f23b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8522416333403493,
+  "epoch": 1.9364344348558198,
   "eval_steps": 100,
-  "global_step": 4400,
+  "global_step": 4600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -711,6 +711,38 @@
       "eval_samples_per_second": 27.526,
       "eval_steps_per_second": 3.442,
       "step": 4400
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 3.823211908340454,
+      "learning_rate": 4.717809187279153e-05,
+      "loss": 2.3919,
+      "step": 4500
+    },
+    {
+      "epoch": 1.89,
+      "eval_cer": 0.5331259043447656,
+      "eval_loss": 2.41994571685791,
+      "eval_runtime": 353.9416,
+      "eval_samples_per_second": 26.778,
+      "eval_steps_per_second": 3.348,
+      "step": 4500
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.0702412128448486,
+      "learning_rate": 4.710742049469965e-05,
+      "loss": 2.4842,
+      "step": 4600
+    },
+    {
+      "epoch": 1.94,
+      "eval_cer": 0.5329523679167807,
+      "eval_loss": 3.652872085571289,
+      "eval_runtime": 339.8921,
+      "eval_samples_per_second": 27.885,
+      "eval_steps_per_second": 3.486,
+      "step": 4600
     }
   ],
   "logging_steps": 100,
@@ -718,7 +750,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.831887475809752e+19,
+  "total_flos": 5.048556716553413e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null