Training in progress, step 153, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16dfef8d2f27178a4d1f4edab1fa39d16a60f03abb441761d33f24ee556f18e
+oid sha256:b06fefafb99b72eb9a89a4f22d4957163eefd15702bb61db525be3f17d1edf9c
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ed09c79b26c5877cb26e4ced9f9a10914f152b078ea4dd8bdd5fffdeeaad84
+oid sha256:9fcdf6ad7bcb0673e059b6db1cf40c1b430a276d46df182e42ba7b0335dbf78a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aeb1fbb5e964bbc83fa43b049054867ad1faca8f43271132d241ae074069d5d
+oid sha256:e76ff8614026ec7c5c2d9793615ca4e2f707e550ce0b5a4376af475431afe3f1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14944028569466383,
+  "epoch": 0.1681203214064968,
   "eval_steps": 50,
-  "global_step": 136,
+  "global_step": 153,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -983,6 +983,133 @@
       "learning_rate": 4.212216399081918e-05,
       "loss": 0.0,
       "step": 136
+    },
+    {
+      "epoch": 0.15053911132477166,
+      "grad_norm": NaN,
+      "learning_rate": 4.095071251953399e-05,
+      "loss": 0.0,
+      "step": 137
+    },
+    {
+      "epoch": 0.15163793695487948,
+      "grad_norm": NaN,
+      "learning_rate": 3.978963279105821e-05,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.1527367625849873,
+      "grad_norm": NaN,
+      "learning_rate": 3.863927848152472e-05,
+      "loss": 0.0,
+      "step": 139
+    },
+    {
+      "epoch": 0.1538355882150951,
+      "grad_norm": NaN,
+      "learning_rate": 3.750000000000001e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.15493441384520293,
+      "grad_norm": NaN,
+      "learning_rate": 3.637214438174593e-05,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.15603323947531075,
+      "grad_norm": NaN,
+      "learning_rate": 3.525605518250964e-05,
+      "loss": 0.0,
+      "step": 142
+    },
+    {
+      "epoch": 0.15713206510541858,
+      "grad_norm": NaN,
+      "learning_rate": 3.415207237387297e-05,
+      "loss": 0.0,
+      "step": 143
+    },
+    {
+      "epoch": 0.1582308907355264,
+      "grad_norm": NaN,
+      "learning_rate": 3.3060532239693994e-05,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.15932971636563423,
+      "grad_norm": NaN,
+      "learning_rate": 3.198176727367156e-05,
+      "loss": 0.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.16042854199574205,
+      "grad_norm": NaN,
+      "learning_rate": 3.091610607806452e-05,
+      "loss": 0.0,
+      "step": 146
+    },
+    {
+      "epoch": 0.16152736762584988,
+      "grad_norm": NaN,
+      "learning_rate": 2.986387326359637e-05,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.1626261932559577,
+      "grad_norm": NaN,
+      "learning_rate": 2.8825389350575624e-05,
+      "loss": 0.0,
+      "step": 148
+    },
+    {
+      "epoch": 0.16372501888606553,
+      "grad_norm": NaN,
+      "learning_rate": 2.78009706712622e-05,
+      "loss": 0.0,
+      "step": 149
+    },
+    {
+      "epoch": 0.16482384451617335,
+      "grad_norm": NaN,
+      "learning_rate": 2.6790929273509545e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.16482384451617335,
+      "eval_loss": NaN,
+      "eval_runtime": 585.8565,
+      "eval_samples_per_second": 5.233,
+      "eval_steps_per_second": 2.617,
+      "step": 150
+    },
+    {
+      "epoch": 0.16592267014628115,
+      "grad_norm": NaN,
+      "learning_rate": 2.579557282571196e-05,
+      "loss": 0.0,
+      "step": 151
+    },
+    {
+      "epoch": 0.16702149577638897,
+      "grad_norm": NaN,
+      "learning_rate": 2.4815204523085654e-05,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 0.1681203214064968,
+      "grad_norm": NaN,
+      "learning_rate": 2.385012299531262e-05,
+      "loss": 0.0,
+      "step": 153
     }
   ],
   "logging_steps": 1,
@@ -1002,7 +1129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.965978331541668e+17,
+  "total_flos": 8.953713627035075e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null