Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22fd646964f7141c8e110ca73e687d637ac5908b5938b0a42a9af0bcbf299f16
+oid sha256:6fb1ac3363635a3b0090068f8794f7a3fff0ed98d9564aa75664f20978996f6a
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d40b56fa86399430acdee58a523d5e295b660277e1c6794d579ae6a32135e4d8
+oid sha256:44cc8995b543f42db2626d1ca4565368b0ca96d47a236ece7b6e6f2efb38e27c
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0987ff7a6cbc2809c803560f955306ddcf16489adf408fc06355caaa080ce5
+oid sha256:b7964ea9b27b8ec2d253f8e37dd1b85f1110775e8fe1122f0a165ddc0fdee12d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7daf508bc85526f69b8f3b71377a6a6256f8d93d4aaf541b8c9a6b631bc6c8
+oid sha256:863cf4a7956086b9fd348589f422e8af87ea5d78b5c7d0e595c32a5aaf7e77e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9972065305108946,
+  "epoch": 2.9972065305108946,
   "eval_steps": 50,
-  "global_step": 502,
+  "global_step": 753,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,81 @@
       "eval_samples_per_second": 31.354,
       "eval_steps_per_second": 15.677,
       "step": 500
+    },
+    {
+      "epoch": 2.190700850456267,
+      "grad_norm": 0.20531371235847473,
+      "learning_rate": 7.808764940239044e-05,
+      "loss": 0.1764,
+      "step": 550
+    },
+    {
+      "epoch": 2.190700850456267,
+      "eval_loss": 0.20692695677280426,
+      "eval_runtime": 27.0503,
+      "eval_samples_per_second": 31.349,
+      "eval_steps_per_second": 15.675,
+      "step": 550
+    },
+    {
+      "epoch": 2.3893475696815445,
+      "grad_norm": 0.20478622615337372,
+      "learning_rate": 7.609561752988048e-05,
+      "loss": 0.1489,
+      "step": 600
+    },
+    {
+      "epoch": 2.3893475696815445,
+      "eval_loss": 0.19011318683624268,
+      "eval_runtime": 27.0394,
+      "eval_samples_per_second": 31.362,
+      "eval_steps_per_second": 15.681,
+      "step": 600
+    },
+    {
+      "epoch": 2.587994288906822,
+      "grad_norm": 0.20455621182918549,
+      "learning_rate": 7.410358565737052e-05,
+      "loss": 0.1389,
+      "step": 650
+    },
+    {
+      "epoch": 2.587994288906822,
+      "eval_loss": 0.17714831233024597,
+      "eval_runtime": 27.0003,
+      "eval_samples_per_second": 31.407,
+      "eval_steps_per_second": 15.704,
+      "step": 650
+    },
+    {
+      "epoch": 2.7866410081321,
+      "grad_norm": 0.2362823486328125,
+      "learning_rate": 7.211155378486057e-05,
+      "loss": 0.1276,
+      "step": 700
+    },
+    {
+      "epoch": 2.7866410081321,
+      "eval_loss": 0.16439422965049744,
+      "eval_runtime": 27.0429,
+      "eval_samples_per_second": 31.358,
+      "eval_steps_per_second": 15.679,
+      "step": 700
+    },
+    {
+      "epoch": 2.985287727357378,
+      "grad_norm": 0.19321954250335693,
+      "learning_rate": 7.01195219123506e-05,
+      "loss": 0.1208,
+      "step": 750
+    },
+    {
+      "epoch": 2.985287727357378,
+      "eval_loss": 0.15227381885051727,
+      "eval_runtime": 27.0597,
+      "eval_samples_per_second": 31.338,
+      "eval_steps_per_second": 15.669,
+      "step": 750
     }
   ],
   "logging_steps": 50,