Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf240eed9e8208c7286897280d42b252096e23bca8816bf42dd7a9b15200c4e7
+oid sha256:6b3edb0adadd334561a36e43a4212a4e9514b0b74e249ccb77a9f1a398e42f35
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ebdee98f56d146a65b33bc3c6a0ae4cbe41eedc20fc4c696b591b455b690b3
+oid sha256:0f22bc3eca0ebb0e03246c1e1c410976b12328cb4244ff48da993896225bf4a8
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88004fc539503ca7b97859aa1d0c5a82fcb7f351b44fb5ff1b5865391c2b3cde
+oid sha256:8c26ad211585233ad2dccb9325976cb7e71ced6080ea69e9468119115e0c0050
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa578981512791e6849bdb4bf6d0c6a452082d1d9f87c0e1fc7d58cb03cb03e
+oid sha256:0ae036049be18d3db0b069d7cdee2136b0e955af29d02ba238e8d63ec3de1819
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5d370370c39c42f0150b3734d1138af727c24530d2b404ccc308de87353353
+oid sha256:6f97d2f076eca9f1526fcbf8cced9c57bd3414f3b9c7f6f76f9126f17c819f1a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05,
-  "global_step": 160000,
+  "epoch": 0.1,
+  "global_step": 170000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2182,11 +2182,147 @@
       "eval_samples_per_second": 144.224,
       "eval_steps_per_second": 2.254,
       "step": 160000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.848573312159415e-05,
+      "loss": 0.378,
+      "step": 160500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8279734067715378e-05,
+      "loss": 0.3769,
+      "step": 161000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8075609083923823e-05,
+      "loss": 0.3772,
+      "step": 161500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.7873785866083376e-05,
+      "loss": 0.3761,
+      "step": 162000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.7674276863600826e-05,
+      "loss": 0.3754,
+      "step": 162500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.747709438313117e-05,
+      "loss": 0.3761,
+      "step": 163000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.728225058781864e-05,
+      "loss": 0.3757,
+      "step": 163500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7089757496546325e-05,
+      "loss": 0.3764,
+      "step": 164000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6899626983194823e-05,
+      "loss": 0.3746,
+      "step": 164500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6712243911044467e-05,
+      "loss": 0.375,
+      "step": 165000
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.34934455156326294,
+      "eval_runtime": 286.3366,
+      "eval_samples_per_second": 150.173,
+      "eval_steps_per_second": 2.347,
+      "step": 165000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6526868808276845e-05,
+      "loss": 0.3763,
+      "step": 165500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6344254560630497e-05,
+      "loss": 0.3733,
+      "step": 166000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.616368051555008e-05,
+      "loss": 0.3749,
+      "step": 166500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5985526173180873e-05,
+      "loss": 0.3755,
+      "step": 167000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.580980252292188e-05,
+      "loss": 0.3754,
+      "step": 167500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.563652040423561e-05,
+      "loss": 0.3747,
+      "step": 168000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.546569050597935e-05,
+      "loss": 0.3758,
+      "step": 168500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.5297657635265495e-05,
+      "loss": 0.3756,
+      "step": 169000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.5131758682182151e-05,
+      "loss": 0.375,
+      "step": 169500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.49683430856095e-05,
+      "loss": 0.3759,
+      "step": 170000
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.3487904369831085,
+      "eval_runtime": 298.7435,
+      "eval_samples_per_second": 143.936,
+      "eval_steps_per_second": 2.249,
+      "step": 170000
     }
   ],
   "max_steps": 200000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 3.7678890778361856e+21,
+  "total_flos": 4.003382145200947e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ebdee98f56d146a65b33bc3c6a0ae4cbe41eedc20fc4c696b591b455b690b3
+oid sha256:0f22bc3eca0ebb0e03246c1e1c410976b12328cb4244ff48da993896225bf4a8
 size 449471589