Training in progress, step 215, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f506ea0a27d11213698935b80e6dfa359af22d511da08e50f3ed93d6008677f
+oid sha256:586914a78337401433634dbbd9c870308821b572d35a39c898f8ecf5be706902
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd844c79c32a67c4550bd5927f49b90e4581c3c63626897db1d09f6feb6e7fd
+oid sha256:b7b7326b0752b10dc170d56e4b2868eb46ec52848d311d8176b99ee46df5e325
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a626c58c869c9d1ca23eb9446f33bde15a185ae71e9f7e32d182b1648304b3
+oid sha256:11409aa0c673614697faa75e0d05b97eaa43eb229b5e5efff9823b555bbc8d3c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19375151368370067,
+  "epoch": 0.26035359651247275,
   "eval_steps": 55,
-  "global_step": 160,
+  "global_step": 215,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,140 @@
       "learning_rate": 1.6543469682057106e-05,
       "loss": 0.0,
       "step": 159
+    },
+    {
+      "epoch": 0.1961734076047469,
+      "grad_norm": NaN,
+      "learning_rate": 1.4910104855800427e-05,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.1998062484863163,
+      "grad_norm": NaN,
+      "learning_rate": 1.3347406408508695e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.1998062484863163,
+      "eval_loss": NaN,
+      "eval_runtime": 72.7309,
+      "eval_samples_per_second": 5.981,
+      "eval_steps_per_second": 2.997,
+      "step": 165
+    },
+    {
+      "epoch": 0.20343908936788568,
+      "grad_norm": NaN,
+      "learning_rate": 1.1858521406886675e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.20707193024945508,
+      "grad_norm": NaN,
+      "learning_rate": 1.0446448267182952e-05,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 0.21070477113102445,
+      "grad_norm": NaN,
+      "learning_rate": 9.114030716778433e-06,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 0.21433761201259385,
+      "grad_norm": NaN,
+      "learning_rate": 7.863952067298042e-06,
+      "loss": 0.0,
+      "step": 177
+    },
+    {
+      "epoch": 0.21797045289416322,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.22160329377573262,
+      "grad_norm": NaN,
+      "learning_rate": 5.620710549772295e-06,
+      "loss": 0.0,
+      "step": 183
+    },
+    {
+      "epoch": 0.22523613465730202,
+      "grad_norm": NaN,
+      "learning_rate": 4.632065271606756e-06,
+      "loss": 0.0,
+      "step": 186
+    },
+    {
+      "epoch": 0.2288689755388714,
+      "grad_norm": NaN,
+      "learning_rate": 3.734784976300165e-06,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 0.2325018164204408,
+      "grad_norm": NaN,
+      "learning_rate": 2.930676666954846e-06,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 0.23613465730201016,
+      "grad_norm": NaN,
+      "learning_rate": 2.221359710692961e-06,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.23976749818357956,
+      "grad_norm": NaN,
+      "learning_rate": 1.6082625774666794e-06,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 0.24340033906514894,
+      "grad_norm": NaN,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 201
+    },
+    {
+      "epoch": 0.24703317994671833,
+      "grad_norm": NaN,
+      "learning_rate": 6.75470303823933e-07,
+      "loss": 0.0,
+      "step": 204
+    },
+    {
+      "epoch": 0.2506660208282877,
+      "grad_norm": NaN,
+      "learning_rate": 3.576536829081323e-07,
+      "loss": 0.0,
+      "step": 207
+    },
+    {
+      "epoch": 0.2542988617098571,
+      "grad_norm": NaN,
+      "learning_rate": 1.3981014094099353e-07,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.2579317025914265,
+      "grad_norm": NaN,
+      "learning_rate": 2.237838582483387e-08,
+      "loss": 0.0,
+      "step": 213
     }
   ],
   "logging_steps": 3,
@@ -416,12 +550,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.09330809693143e+16,
+  "total_flos": 9.54324119275438e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null