Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa0eaee5cedb377fe1261e85d128185b90db08b38266c4efca995ed2dccaee7
+oid sha256:3c6c3b49517918f71b5a8df86ce64802524c101812f6310fcee02fef5d317af6
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1ed0d05f98b7f3f40accdab65ca1d1e070ed54fcbe788400dbc49cadd189e5
+oid sha256:cadd65cd84f71c9af827b83eda5019a7e53557ca55a0ba59402e7753460dc671
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012394645513138325,
+  "epoch": 0.02478929102627665,
   "eval_steps": 4,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,229 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.012890431333663858,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.013386217154189391,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.013882002974714923,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.013882002974714923,
+      "eval_loss": NaN,
+      "eval_runtime": 1218.6897,
+      "eval_samples_per_second": 2.091,
+      "eval_steps_per_second": 0.523,
+      "step": 28
+    },
+    {
+      "epoch": 0.014377788795240456,
+      "grad_norm": NaN,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.014873574615765989,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.015369360436291522,
+      "grad_norm": NaN,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.015865146256817054,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.015865146256817054,
+      "eval_loss": NaN,
+      "eval_runtime": 1218.7929,
+      "eval_samples_per_second": 2.091,
+      "eval_steps_per_second": 0.523,
+      "step": 32
+    },
+    {
+      "epoch": 0.01636093207734259,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.01685671789786812,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.017352503718393655,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.017848289538919187,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.017848289538919187,
+      "eval_loss": NaN,
+      "eval_runtime": 1218.8632,
+      "eval_samples_per_second": 2.09,
+      "eval_steps_per_second": 0.523,
+      "step": 36
+    },
+    {
+      "epoch": 0.01834407535944472,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.018839861179970253,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.019335647000495785,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.01983143282102132,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01983143282102132,
+      "eval_loss": NaN,
+      "eval_runtime": 1219.2297,
+      "eval_samples_per_second": 2.09,
+      "eval_steps_per_second": 0.522,
+      "step": 40
+    },
+    {
+      "epoch": 0.02032721864154685,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.020823004462072386,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.021318790282597918,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.02181457610312345,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.02181457610312345,
+      "eval_loss": NaN,
+      "eval_runtime": 1218.9478,
+      "eval_samples_per_second": 2.09,
+      "eval_steps_per_second": 0.523,
+      "step": 44
+    },
+    {
+      "epoch": 0.022310361923648984,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.022806147744174516,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.02330193356470005,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.023797719385225583,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.023797719385225583,
+      "eval_loss": NaN,
+      "eval_runtime": 1219.4358,
+      "eval_samples_per_second": 2.089,
+      "eval_steps_per_second": 0.522,
+      "step": 48
+    },
+    {
+      "epoch": 0.024293505205751114,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.02478929102627665,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -252,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.119015678246912e+17,
+  "total_flos": 2.238031356493824e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null