Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d898d6ea104f17cbbf27e7461b1d6144bf9fe1ae55eea4068e53eb3839da02a
-size 995605189
+oid sha256:9b1476fc7f63764e7c906982b1b12a6daf7ebe1a4c9eabc5fef44fc57fcc9502
+size 995605445

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a99a09048543fe282b50b60bfea4bb009b9decd582e348ad2d38001d140d18
+oid sha256:06dbc8237a227289c2c378d392e11aa4349c38612caeca6588a0593a85dc6327
 size 510398013

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6359c6c031dbde530d264752810896a8f9d4957f508f18193732bd65efe52d
+oid sha256:238fcc56614b79437ea498441742d1361699701d7545b2165136d90ba11cb014
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9bb18d023d349a9a0f7837b4603b5fafaa2d673ffb5da28ae0fb78b43c6d7e
+oid sha256:07b2728bb8093f11b5a52109cc3872bbd75c6945624640e5b69917df439310bd
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1838242257789564,
-  "global_step": 50000,
+  "epoch": 1.4205890709347475,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -652,11 +652,139 @@
       "eval_samples_per_second": 165.853,
       "eval_steps_per_second": 20.736,
       "step": 50000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.275726868074628e-05,
+      "loss": 3.0453,
+      "step": 50500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.269413138870474e-05,
+      "loss": 3.014,
+      "step": 51000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.26309940966632e-05,
+      "loss": 3.0549,
+      "step": 51500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 3.256785680462165e-05,
+      "loss": 3.0268,
+      "step": 52000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.250471951258011e-05,
+      "loss": 3.0389,
+      "step": 52500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.244158222053857e-05,
+      "loss": 3.0315,
+      "step": 53000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 3.237844492849702e-05,
+      "loss": 3.0363,
+      "step": 53500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.231530763645547e-05,
+      "loss": 3.0291,
+      "step": 54000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.225217034441393e-05,
+      "loss": 3.0257,
+      "step": 54500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.218903305237238e-05,
+      "loss": 3.0457,
+      "step": 55000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.212589576033084e-05,
+      "loss": 3.0431,
+      "step": 55500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.20627584682893e-05,
+      "loss": 3.0591,
+      "step": 56000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.199962117624775e-05,
+      "loss": 3.0525,
+      "step": 56500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.193648388420621e-05,
+      "loss": 3.0479,
+      "step": 57000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.187334659216466e-05,
+      "loss": 3.019,
+      "step": 57500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 3.181020930012312e-05,
+      "loss": 3.0356,
+      "step": 58000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 3.174707200808158e-05,
+      "loss": 3.0549,
+      "step": 58500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.168393471604003e-05,
+      "loss": 3.0439,
+      "step": 59000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.162079742399849e-05,
+      "loss": 3.0491,
+      "step": 59500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.155766013195695e-05,
+      "loss": 3.0409,
+      "step": 60000
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 3.1459972858428955,
+      "eval_runtime": 113.0693,
+      "eval_samples_per_second": 166.022,
+      "eval_steps_per_second": 20.757,
+      "step": 60000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 1.0692746654976e+16,
+  "total_flos": 1.2788110741248e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a99a09048543fe282b50b60bfea4bb009b9decd582e348ad2d38001d140d18
+oid sha256:06dbc8237a227289c2c378d392e11aa4349c38612caeca6588a0593a85dc6327
 size 510398013