Training in progress, step 390000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2310ccd274183453ec41297ed5b4fbe0708a6ec9bca366b103dfcf65aeab3e97
+oid sha256:cdba09a21a6fe137d8ba359aac9297fdf4dbf33d9b301f28af9c14375f6817c1
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070b24fba265a1068a427c0c24eff65c5db228aea33e6a3f577c8ae63bc979f8
+oid sha256:45c2d59896d59a19db4a7827a3260af1e2736fb9670920d9776b8ffe7675ce78
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf8d2b73d4b0feab91274f36ef211767933c8e416500bcbb275242b4c476138
+oid sha256:b771a1fe99a5de1f25e62006cef44ab6aa7ae84aa666df6010f762208efae301
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.997064115920068,
-  "global_step": 380000,
+  "epoch": 9.23382896107586,
+  "global_step": 390000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4876,11 +4876,139 @@
       "eval_samples_per_second": 166.019,
       "eval_steps_per_second": 20.757,
       "step": 380000
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0,
+      "loss": 2.4446,
+      "step": 380500
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.0,
+      "loss": 2.4163,
+      "step": 381000
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 0.0,
+      "loss": 2.4384,
+      "step": 381500
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 0.0,
+      "loss": 2.4467,
+      "step": 382000
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 0.0,
+      "loss": 2.4226,
+      "step": 382500
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 0.0,
+      "loss": 2.4246,
+      "step": 383000
+    },
+    {
+      "epoch": 9.08,
+      "learning_rate": 0.0,
+      "loss": 2.4276,
+      "step": 383500
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 0.0,
+      "loss": 2.4267,
+      "step": 384000
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 0.0,
+      "loss": 2.4246,
+      "step": 384500
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 0.0,
+      "loss": 2.4199,
+      "step": 385000
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 0.0,
+      "loss": 2.4252,
+      "step": 385500
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 0.0,
+      "loss": 2.4306,
+      "step": 386000
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 0.0,
+      "loss": 2.4269,
+      "step": 386500
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 0.0,
+      "loss": 2.4259,
+      "step": 387000
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 0.0,
+      "loss": 2.423,
+      "step": 387500
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 0.0,
+      "loss": 2.4288,
+      "step": 388000
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 0.0,
+      "loss": 2.446,
+      "step": 388500
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 0.0,
+      "loss": 2.4166,
+      "step": 389000
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 0.0,
+      "loss": 2.4268,
+      "step": 389500
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 0.0,
+      "loss": 2.4334,
+      "step": 390000
+    },
+    {
+      "epoch": 9.23,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 113.0688,
+      "eval_samples_per_second": 166.023,
+      "eval_steps_per_second": 20.757,
+      "step": 390000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 8.0235708749568e+16,
+  "total_flos": 8.2348841714688e+16,
   "trial_name": null,
   "trial_params": null
 }