Training in progress, step 330000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2757a06bce48fa87bf9e9478c26cfbf215c50d2f68265f3a5f1369e2325144f9
+oid sha256:3af69497cd7909d18e142fdb28af685d5fd4b6d1152a10069e6f9547b752a3d5
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33bd9e5a65135e04092c64ff67287c6b50f9ca7261884c1aeef47ab5ae22ab5
+oid sha256:926d62aa8c0e8eb933d167c471771b77e84d87c1ca180d71a4153e846dcaa5bc
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb25646b1703a274e33c829bedb7366b8ef3f96c2bb36d8789415b3f642f877
+oid sha256:dac0a7c6aeb1853f8f712f2c9f2553cbe98523717c3c148ee76debf888894532
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.576475044985321,
-  "global_step": 320000,
+  "epoch": 7.813239890141112,
+  "global_step": 330000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4108,11 +4108,139 @@
       "eval_samples_per_second": 166.315,
       "eval_steps_per_second": 20.794,
       "step": 320000
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 0.0,
+      "loss": 2.4285,
+      "step": 320500
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 0.0,
+      "loss": 2.4267,
+      "step": 321000
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 0.0,
+      "loss": 2.4389,
+      "step": 321500
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 0.0,
+      "loss": 2.4277,
+      "step": 322000
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 0.0,
+      "loss": 2.4349,
+      "step": 322500
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 0.0,
+      "loss": 2.4376,
+      "step": 323000
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 0.0,
+      "loss": 2.4453,
+      "step": 323500
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 0.0,
+      "loss": 2.4331,
+      "step": 324000
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 0.0,
+      "loss": 2.4418,
+      "step": 324500
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 0.0,
+      "loss": 2.4342,
+      "step": 325000
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 0.0,
+      "loss": 2.4216,
+      "step": 325500
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 0.0,
+      "loss": 2.4335,
+      "step": 326000
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 0.0,
+      "loss": 2.4472,
+      "step": 326500
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 0.0,
+      "loss": 2.4415,
+      "step": 327000
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 0.0,
+      "loss": 2.4462,
+      "step": 327500
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 0.0,
+      "loss": 2.4519,
+      "step": 328000
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 0.0,
+      "loss": 2.3932,
+      "step": 328500
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 0.0,
+      "loss": 2.425,
+      "step": 329000
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 0.0,
+      "loss": 2.4297,
+      "step": 329500
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 0.0,
+      "loss": 2.4363,
+      "step": 330000
+    },
+    {
+      "epoch": 7.81,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.8083,
+      "eval_samples_per_second": 166.406,
+      "eval_steps_per_second": 20.805,
+      "step": 330000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 6.760424309184e+16,
+  "total_flos": 6.971360467392e+16,
   "trial_name": null,
   "trial_params": null
 }