Training in progress, step 770000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b007e5fd244b5729ff8cacaa57b1c785d03d898d5343c77b7ff241a5f8a33380
+oid sha256:9cd115a94124bab2069eaa28cc8b9048cd539d53dac292919b3e0c103db4c72e
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e44d1153c2511a74df34714d54a3a947742b99b6eae06df301cfffab1c1eeb6
+oid sha256:ca7fa82eacf1e8434be7ded7b8c684db48c7eb8a95a9938e56bd64eca327a5df
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120630248e0966968ea30af6ab08315c5a7b742e34d05df0eaea1327acea70ef
-size 14503
+oid sha256:c7d3b820a136ad2a4ba7c86024ef116cb8408b724ca033611384f2431449421e
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac732455f777abd748b7734f32cb802da48d17d36fc1f892d1c7b8c265c6c8d
+oid sha256:9edcea991831f16f231bcb3a9b5fa5ff10be4f8fa58a6379f44531e869bdb54a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6effa5b718ae036f8fdfe02790dba13a4eddf18e987e06715606a6733b193f
-size 14567
+oid sha256:8d7420c489d698358bef68e17228256f66ae1823918a8b52fcc13ba74d224c70
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fd70086a62614811003e1691a71dc1a1851fe2a8de8e368309da1203a65b12
+oid sha256:682c61168677972229ed1e1a9e1518def3be9c6cebcff3c8dc65ade2edc13840
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e175165a3eac134d38f788fbf76210f5cf20ad100371de72779cc7de9da4b86f
+oid sha256:c87245ad3a3a643f81f3f2450a9b83d6c09d17eda4b9f8dcf29bf1d0ea618777
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.60535678837021,
-  "global_step": 760000,
+  "epoch": 11.758058851375083,
+  "global_step": 770000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5630,11 +5630,85 @@
       "eval_samples_per_second": 1390.499,
       "eval_steps_per_second": 22.248,
       "step": 760000
+    },
+    {
+      "epoch": 11.62,
+      "learning_rate": 3.0748661009182616e-05,
+      "loss": 0.2396,
+      "step": 761000
+    },
+    {
+      "epoch": 11.64,
+      "learning_rate": 3.0584435522191896e-05,
+      "loss": 0.2395,
+      "step": 762000
+    },
+    {
+      "epoch": 11.65,
+      "learning_rate": 3.0420750435897183e-05,
+      "loss": 0.2393,
+      "step": 763000
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 3.025760754033246e-05,
+      "loss": 0.239,
+      "step": 764000
+    },
+    {
+      "epoch": 11.68,
+      "learning_rate": 3.0095008619602206e-05,
+      "loss": 0.2392,
+      "step": 765000
+    },
+    {
+      "epoch": 11.68,
+      "eval_runtime": 0.7905,
+      "eval_samples_per_second": 1264.968,
+      "eval_steps_per_second": 20.239,
+      "step": 765000
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 2.993295545186223e-05,
+      "loss": 0.2393,
+      "step": 766000
+    },
+    {
+      "epoch": 11.71,
+      "learning_rate": 2.977144980929996e-05,
+      "loss": 0.2392,
+      "step": 767000
+    },
+    {
+      "epoch": 11.73,
+      "learning_rate": 2.961049345811523e-05,
+      "loss": 0.2388,
+      "step": 768000
+    },
+    {
+      "epoch": 11.74,
+      "learning_rate": 2.945008815850097e-05,
+      "loss": 0.2392,
+      "step": 769000
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 2.929023566462377e-05,
+      "loss": 0.2391,
+      "step": 770000
+    },
+    {
+      "epoch": 11.76,
+      "eval_runtime": 0.8418,
+      "eval_samples_per_second": 1187.898,
+      "eval_steps_per_second": 19.006,
+      "step": 770000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.327612610556747e+22,
+  "total_flos": 5.397712871587094e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e44d1153c2511a74df34714d54a3a947742b99b6eae06df301cfffab1c1eeb6
+oid sha256:ca7fa82eacf1e8434be7ded7b8c684db48c7eb8a95a9938e56bd64eca327a5df
 size 449471589