Training in progress, step 153, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d357909dba959fc25a9df85f0556aa115af78e55ff31a0347e9d6dc9086669be
+oid sha256:0c079d645762a6059f2de7010f66b05a0ffbfa9f07f4149749e599a52925580e
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c985768cd88156b279865b4af398ed65c42e2eb474c28476bc122fd2d648fd1
+oid sha256:afb210574debeca01beef086494f1b0da6d8ee8853b3831ec7094b554157981c
 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": 0.027135722257901597,
+  "epoch": 0.030527687540139296,
   "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": 0.02733524962744499,
+      "grad_norm": NaN,
+      "learning_rate": 4.095071251953399e-05,
+      "loss": 0.0,
+      "step": 137
+    },
+    {
+      "epoch": 0.027534776996988385,
+      "grad_norm": NaN,
+      "learning_rate": 3.978963279105821e-05,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.02773430436653178,
+      "grad_norm": NaN,
+      "learning_rate": 3.863927848152472e-05,
+      "loss": 0.0,
+      "step": 139
+    },
+    {
+      "epoch": 0.027933831736075172,
+      "grad_norm": NaN,
+      "learning_rate": 3.750000000000001e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.028133359105618566,
+      "grad_norm": NaN,
+      "learning_rate": 3.637214438174593e-05,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.02833288647516196,
+      "grad_norm": NaN,
+      "learning_rate": 3.525605518250964e-05,
+      "loss": 0.0,
+      "step": 142
+    },
+    {
+      "epoch": 0.028532413844705354,
+      "grad_norm": NaN,
+      "learning_rate": 3.415207237387297e-05,
+      "loss": 0.0,
+      "step": 143
+    },
+    {
+      "epoch": 0.028731941214248748,
+      "grad_norm": NaN,
+      "learning_rate": 3.3060532239693994e-05,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.02893146858379214,
+      "grad_norm": NaN,
+      "learning_rate": 3.198176727367156e-05,
+      "loss": 0.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.029130995953335535,
+      "grad_norm": NaN,
+      "learning_rate": 3.091610607806452e-05,
+      "loss": 0.0,
+      "step": 146
+    },
+    {
+      "epoch": 0.02933052332287893,
+      "grad_norm": NaN,
+      "learning_rate": 2.986387326359637e-05,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.029530050692422323,
+      "grad_norm": NaN,
+      "learning_rate": 2.8825389350575624e-05,
+      "loss": 0.0,
+      "step": 148
+    },
+    {
+      "epoch": 0.02972957806196572,
+      "grad_norm": NaN,
+      "learning_rate": 2.78009706712622e-05,
+      "loss": 0.0,
+      "step": 149
+    },
+    {
+      "epoch": 0.029929105431509114,
+      "grad_norm": NaN,
+      "learning_rate": 2.6790929273509545e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.029929105431509114,
+      "eval_loss": NaN,
+      "eval_runtime": 3233.9846,
+      "eval_samples_per_second": 5.22,
+      "eval_steps_per_second": 2.61,
+      "step": 150
+    },
+    {
+      "epoch": 0.030128632801052508,
+      "grad_norm": NaN,
+      "learning_rate": 2.579557282571196e-05,
+      "loss": 0.0,
+      "step": 151
+    },
+    {
+      "epoch": 0.030328160170595902,
+      "grad_norm": NaN,
+      "learning_rate": 2.4815204523085654e-05,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 0.030527687540139296,
+      "grad_norm": NaN,
+      "learning_rate": 2.385012299531262e-05,
+      "loss": 0.0,
+      "step": 153
     }
   ],
   "logging_steps": 1,
@@ -1002,7 +1129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.116593719550935e+17,
+  "total_flos": 9.131167934494802e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null