Training in progress, step 2600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d55abe18136649fb6def532385b4b394d9e108fdf8f4ca57578d416c9b41ef
+oid sha256:f3f64c952ff4641bec2d37ff0636478ddcef3aeab74df3cb91bdf2d91731b10b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c33bc16a6ad0497f092d4c75ded33c7dd30729c9f35a49f646bce7c9c01ac4
+oid sha256:098244c9228db3ca4f33bfc03f5c37e53201eed99007476bf5913778733dceff
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c02ba7f38d49e33dc88cf95e4ccb546c08b6fd6a7dddb75eaf0aad68dc9620
+oid sha256:445326ce7e26cbb298d704930deb469af3b4dbb080300d78dea0eb9de43a243f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84eac669e63d3ebd7cbfdaf89ff43149b8b9e94f7d0e66c6ee43cd90c3b778d
+oid sha256:b7cd491c49a484c01c1aacf0d928424ee5e848c8d84b507d694ada4aac6d7e95
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5894c6573565c6328682bcc690a51bee32ff4f44e9c1aa3c075cea5a25453a5
+oid sha256:7c76b9e38a726eb71dd00d20ba43967966a0126810ffb458578fa60a50e49323
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0103136181856451,
+  "epoch": 1.0945064197011156,
   "eval_steps": 100,
-  "global_step": 2400,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -391,6 +391,38 @@
       "eval_samples_per_second": 27.576,
       "eval_steps_per_second": 3.448,
       "step": 2400
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 2.40964937210083,
+      "learning_rate": 4.859081272084806e-05,
+      "loss": 2.3368,
+      "step": 2500
+    },
+    {
+      "epoch": 1.05,
+      "eval_cer": 0.5851746118650033,
+      "eval_loss": 1.9030027389526367,
+      "eval_runtime": 352.7743,
+      "eval_samples_per_second": 26.867,
+      "eval_steps_per_second": 3.359,
+      "step": 2500
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 3.7618064880371094,
+      "learning_rate": 4.852084805653711e-05,
+      "loss": 2.4157,
+      "step": 2600
+    },
+    {
+      "epoch": 1.09,
+      "eval_cer": 0.5566339798991045,
+      "eval_loss": 3.213930368423462,
+      "eval_runtime": 341.3273,
+      "eval_samples_per_second": 27.768,
+      "eval_steps_per_second": 3.472,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
@@ -398,7 +430,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.6422344601189564e+19,
+  "total_flos": 2.8602262072383316e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null