Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed8519bcaf890fae8081cd58f6c996883ae79208d6315cbb3f5449e5c61925d
+oid sha256:68d56787f820ba2c9451fcaf120554619cf086381826f9b55f6c4ead221c2100
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ba46e35587d52846c549700745d71d625c59dbb77b681ef7abde15d4756290
+oid sha256:d6b243615523b454b114c4bd890ba971677a8849b256fa39e0e4158b1e8765bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
+oid sha256:2188426f4adaa3a6124c181a61860e824dc2136981845a9e9c4162d0d3700af6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20548039283016276,
+  "epoch": 0.21976512602156445,
   "eval_steps": 50,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1348,6 +1348,105 @@
       "learning_rate": 1.9222451411073645e-06,
       "loss": 0.0,
       "step": 187
+    },
+    {
+      "epoch": 0.20657921846027058,
+      "grad_norm": NaN,
+      "learning_rate": 1.6389299449645733e-06,
+      "loss": 0.0,
+      "step": 188
+    },
+    {
+      "epoch": 0.2076780440903784,
+      "grad_norm": NaN,
+      "learning_rate": 1.3779612414252017e-06,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 0.20877686972048623,
+      "grad_norm": NaN,
+      "learning_rate": 1.1394185240843983e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.20987569535059405,
+      "grad_norm": NaN,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.0,
+      "step": 191
+    },
+    {
+      "epoch": 0.21097452098070188,
+      "grad_norm": NaN,
+      "learning_rate": 7.298948443822228e-07,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 0.2120733466108097,
+      "grad_norm": NaN,
+      "learning_rate": 5.590386269008512e-07,
+      "loss": 0.0,
+      "step": 193
+    },
+    {
+      "epoch": 0.21317217224091753,
+      "grad_norm": NaN,
+      "learning_rate": 4.108578473795032e-07,
+      "loss": 0.0,
+      "step": 194
+    },
+    {
+      "epoch": 0.21427099787102535,
+      "grad_norm": NaN,
+      "learning_rate": 2.8539764311908407e-07,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.21536982350113315,
+      "grad_norm": NaN,
+      "learning_rate": 1.8269623051318515e-07,
+      "loss": 0.0,
+      "step": 196
+    },
+    {
+      "epoch": 0.21646864913124098,
+      "grad_norm": NaN,
+      "learning_rate": 1.027848934069625e-07,
+      "loss": 0.0,
+      "step": 197
+    },
+    {
+      "epoch": 0.2175674747613488,
+      "grad_norm": NaN,
+      "learning_rate": 4.568797356781784e-08,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 0.21866630039145663,
+      "grad_norm": NaN,
+      "learning_rate": 1.142286327065478e-08,
+      "loss": 0.0,
+      "step": 199
+    },
+    {
+      "epoch": 0.21976512602156445,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.21976512602156445,
+      "eval_loss": NaN,
+      "eval_runtime": 585.7642,
+      "eval_samples_per_second": 5.234,
+      "eval_steps_per_second": 2.617,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1362,12 +1461,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0929184218021888e+18,
+  "total_flos": 1.168190096566911e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null