Training in progress, step 65000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcbb71ee6902820938fb7191246d8d93bb293cabd8d7e19570813e3bd71858fb
+oid sha256:3d5e1e80d83140c7757fb1cf95538f9adc1a835b71ae2bc6cdd25ad21f5c83eb
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:813c3bc201a3d6b8c1f9f27a12e5ae8d332dd8fa1dd981f77aaed37dd2821d1b
+oid sha256:a783dbb8208b6dab75ca1e5b6c4c6b4363cfff8389cb93c71226237c68df043f
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda46c45207c477583d8570015b878d6c2d34bc9f248ab28ce54748ea88ac403
+oid sha256:d45681d1c970d69cda2a460960e7c07fee7c56e72cca12ca172a8880f077eff6
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b567b22b755ea350861d319b375faafd7e69841d532b0cb359c63888848bb7a2
+oid sha256:ec348f8a1d9a6c6129516533e874e560d467699c8a7f99dcd44876497482b2ff
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621aa918e7d94e76e980dd52e6d602b019ed8ae919fe1ca65a5ac903747bec67
+oid sha256:c50dfb427053d9263e12ed412b9751c285281e62f366913d6f9bc9db0eddae39
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.223750652968832,
-  "global_step": 60000,
+  "epoch": 5.659063207382901,
+  "global_step": 65000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -822,11 +822,79 @@
       "eval_samples_per_second": 282.515,
       "eval_steps_per_second": 4.464,
       "step": 60000
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 4.071884423332296e-05,
+      "loss": 0.4123,
+      "step": 60500
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 4.00459618594495e-05,
+      "loss": 0.4122,
+      "step": 61000
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 3.937686555159882e-05,
+      "loss": 0.4123,
+      "step": 61500
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 3.8711720399273034e-05,
+      "loss": 0.4123,
+      "step": 62000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 3.805069051708565e-05,
+      "loss": 0.4118,
+      "step": 62500
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 3.739524812959698e-05,
+      "loss": 0.4118,
+      "step": 63000
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 3.6742927987935615e-05,
+      "loss": 0.4116,
+      "step": 63500
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 3.6095208886480486e-05,
+      "loss": 0.411,
+      "step": 64000
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 3.545225064022787e-05,
+      "loss": 0.4113,
+      "step": 64500
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 3.481548295250678e-05,
+      "loss": 0.4111,
+      "step": 65000
+    },
+    {
+      "epoch": 5.66,
+      "eval_loss": 0.3913000226020813,
+      "eval_runtime": 16.5881,
+      "eval_samples_per_second": 301.422,
+      "eval_steps_per_second": 4.762,
+      "step": 65000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.8258237064667857e+21,
+  "total_flos": 3.0613167738315473e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:813c3bc201a3d6b8c1f9f27a12e5ae8d332dd8fa1dd981f77aaed37dd2821d1b
+oid sha256:a783dbb8208b6dab75ca1e5b6c4c6b4363cfff8389cb93c71226237c68df043f
 size 449471589