Training in progress, step 2800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f64c952ff4641bec2d37ff0636478ddcef3aeab74df3cb91bdf2d91731b10b
+oid sha256:44b2ea87fb45896c5e64675c42319b0c800f3516393fd91fe6189f46278e1a6f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098244c9228db3ca4f33bfc03f5c37e53201eed99007476bf5913778733dceff
+oid sha256:2c31b10f100741c4ebc4d4250ad676d7b466307a2ea83cbc5ede244644ac015c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445326ce7e26cbb298d704930deb469af3b4dbb080300d78dea0eb9de43a243f
+oid sha256:197e645c69e01ac20ea12442834230672eb334b80f902f66c33a4b04dcb6f523
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cd491c49a484c01c1aacf0d928424ee5e848c8d84b507d694ada4aac6d7e95
-size 14567
+oid sha256:04efee40e70fc230d3d9de163b7a49660ca999141c4308e72ab88d3a1aa96df5
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c76b9e38a726eb71dd00d20ba43967966a0126810ffb458578fa60a50e49323
+oid sha256:3ae68370e6304e1d4db7600cca11df6aac88b08aee5cd9372946660cf6886038
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0945064197011156,
+  "epoch": 1.1786992212165859,
   "eval_steps": 100,
-  "global_step": 2600,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,6 +423,38 @@
       "eval_samples_per_second": 27.768,
       "eval_steps_per_second": 3.472,
       "step": 2600
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 9.61824893951416,
+      "learning_rate": 4.845017667844523e-05,
+      "loss": 2.7299,
+      "step": 2700
+    },
+    {
+      "epoch": 1.14,
+      "eval_cer": 0.5819702983848891,
+      "eval_loss": 1.7893775701522827,
+      "eval_runtime": 353.5497,
+      "eval_samples_per_second": 26.808,
+      "eval_steps_per_second": 3.352,
+      "step": 2700
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 2.6824772357940674,
+      "learning_rate": 4.8379505300353364e-05,
+      "loss": 2.934,
+      "step": 2800
+    },
+    {
+      "epoch": 1.18,
+      "eval_cer": 0.5119813460560791,
+      "eval_loss": 2.804206609725952,
+      "eval_runtime": 340.4666,
+      "eval_samples_per_second": 27.838,
+      "eval_steps_per_second": 3.481,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
@@ -430,7 +462,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.8602262072383316e+19,
+  "total_flos": 3.076610148872312e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null