Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5e1e80d83140c7757fb1cf95538f9adc1a835b71ae2bc6cdd25ad21f5c83eb
-size 893438545
+oid sha256:62aa43a334d172b6c92a9e86cddc4224139d388495104b8bc9cf342a33dbaa32
+size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a783dbb8208b6dab75ca1e5b6c4c6b4363cfff8389cb93c71226237c68df043f
+oid sha256:e7e85e1be18414fd56bd482ec51088607f1f3b26827e8774a78e7680201613c3
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45681d1c970d69cda2a460960e7c07fee7c56e72cca12ca172a8880f077eff6
+oid sha256:563f94766f626d38c33a896bb938f939d6c275e108ea7b534c0d209b4993de23
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec348f8a1d9a6c6129516533e874e560d467699c8a7f99dcd44876497482b2ff
+oid sha256:18896310f2ee7059609508aec0a182eb327bcb160c37b740bb26bfe558c18ac5
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c50dfb427053d9263e12ed412b9751c285281e62f366913d6f9bc9db0eddae39
+oid sha256:72eb753390b21928e56a04c9cc3484c55b2eccd5187fb0f52710f912f93a98d9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.659063207382901,
-  "global_step": 65000,
+  "epoch": 6.09437576179697,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -890,11 +890,79 @@
       "eval_samples_per_second": 301.422,
       "eval_steps_per_second": 4.762,
       "step": 65000
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 3.418251081369709e-05,
+      "loss": 0.4107,
+      "step": 65500
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 3.355602161294165e-05,
+      "loss": 0.4103,
+      "step": 66000
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 3.293365900004924e-05,
+      "loss": 0.4095,
+      "step": 66500
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 3.231683730748652e-05,
+      "loss": 0.41,
+      "step": 67000
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 3.170570872677642e-05,
+      "loss": 0.4084,
+      "step": 67500
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 3.110042404475174e-05,
+      "loss": 0.4091,
+      "step": 68000
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 3.050113260635069e-05,
+      "loss": 0.409,
+      "step": 68500
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 2.990798227776831e-05,
+      "loss": 0.4088,
+      "step": 69000
+    },
+    {
+      "epoch": 6.05,
+      "learning_rate": 2.9321119409972645e-05,
+      "loss": 0.4083,
+      "step": 69500
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 2.8740688802594957e-05,
+      "loss": 0.4079,
+      "step": 70000
+    },
+    {
+      "epoch": 6.09,
+      "eval_loss": 0.3888770639896393,
+      "eval_runtime": 17.0838,
+      "eval_samples_per_second": 292.674,
+      "eval_steps_per_second": 4.624,
+      "step": 70000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 3.0613167738315473e+21,
+  "total_flos": 3.296791220814238e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a783dbb8208b6dab75ca1e5b6c4c6b4363cfff8389cb93c71226237c68df043f
+oid sha256:e7e85e1be18414fd56bd482ec51088607f1f3b26827e8774a78e7680201613c3
 size 449471589