Training in progress, step 470000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cab0feaeec9b0df081531b11134d4a07974f3e8871469ef1e5978a3fdf4513c
+oid sha256:f95151b405ff6e9b28a316b89062144bf559aa926a03528da9726a9f12203ab4
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06627b0adf71aa49d708b0fe02640f869165ee333039e8785ac4790ed4b7e03
+oid sha256:80220a02bd1bb4effc31eeb67a63bc1bc002600ac88d646d6d240817c138de29
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f85b1d724a0d5eeb70a8d3d8c6161d3e8829e289f2cc9ca11e46d533504766
+oid sha256:5f20101388fa6eb1fe545871d1e9e63a9edfa1ca0004720ab71ea7f1eab3f9aa
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.891182877166399,
-  "global_step": 460000,
+  "epoch": 11.12794772232219,
+  "global_step": 470000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5900,11 +5900,139 @@
       "eval_samples_per_second": 166.297,
       "eval_steps_per_second": 20.792,
       "step": 460000
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 0.0,
+      "loss": 2.4369,
+      "step": 460500
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 0.0,
+      "loss": 2.431,
+      "step": 461000
+    },
+    {
+      "epoch": 10.93,
+      "learning_rate": 0.0,
+      "loss": 2.4349,
+      "step": 461500
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 0.0,
+      "loss": 2.4178,
+      "step": 462000
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 0.0,
+      "loss": 2.4334,
+      "step": 462500
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 0.0,
+      "loss": 2.4253,
+      "step": 463000
+    },
+    {
+      "epoch": 10.97,
+      "learning_rate": 0.0,
+      "loss": 2.437,
+      "step": 463500
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 0.0,
+      "loss": 2.4155,
+      "step": 464000
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0,
+      "loss": 2.4418,
+      "step": 464500
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 0.0,
+      "loss": 2.4177,
+      "step": 465000
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 0.0,
+      "loss": 2.4494,
+      "step": 465500
+    },
+    {
+      "epoch": 11.03,
+      "learning_rate": 0.0,
+      "loss": 2.4259,
+      "step": 466000
+    },
+    {
+      "epoch": 11.05,
+      "learning_rate": 0.0,
+      "loss": 2.4245,
+      "step": 466500
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 0.0,
+      "loss": 2.4343,
+      "step": 467000
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 0.0,
+      "loss": 2.4279,
+      "step": 467500
+    },
+    {
+      "epoch": 11.08,
+      "learning_rate": 0.0,
+      "loss": 2.4222,
+      "step": 468000
+    },
+    {
+      "epoch": 11.09,
+      "learning_rate": 0.0,
+      "loss": 2.4216,
+      "step": 468500
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 0.0,
+      "loss": 2.432,
+      "step": 469000
+    },
+    {
+      "epoch": 11.12,
+      "learning_rate": 0.0,
+      "loss": 2.4287,
+      "step": 469500
+    },
+    {
+      "epoch": 11.13,
+      "learning_rate": 0.0,
+      "loss": 2.4275,
+      "step": 470000
+    },
+    {
+      "epoch": 11.13,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.9503,
+      "eval_samples_per_second": 166.197,
+      "eval_steps_per_second": 20.779,
+      "step": 470000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 9.7069628570112e+16,
+  "total_flos": 9.9180941677056e+16,
   "trial_name": null,
   "trial_params": null
 }