Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94daaa81313414471ef260ec6da1597f210aaccbc54b9ca8745cfeb053672fd1
+oid sha256:fc312bf9a5312fb6d601aaf47f85325871bfc3e19423145f86a6fcdeed591317
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92c10e366afcbcffbf7fb3788d000f390fe9414d276045b803bbab02ade5f53
+oid sha256:6872d979959ada51f7a7cc998553e6500b41a0a29bbbb4ed6f42373ead76da55
 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": 0.016217969510217322,
+  "epoch": 0.032435939020434644,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 3.261,
       "eval_steps_per_second": 0.41,
       "step": 25
+    },
+    {
+      "epoch": 0.016866688290626014,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.017515407071034706,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.018164125851443398,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.018812844631852094,
+      "grad_norm": NaN,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.019461563412260786,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.019461563412260786,
+      "eval_loss": NaN,
+      "eval_runtime": 397.9393,
+      "eval_samples_per_second": 3.262,
+      "eval_steps_per_second": 0.41,
+      "step": 30
+    },
+    {
+      "epoch": 0.020110282192669478,
+      "grad_norm": NaN,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.02075900097307817,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.021407719753486862,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.022056438533895557,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.02270515731430425,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.02270515731430425,
+      "eval_loss": NaN,
+      "eval_runtime": 397.9751,
+      "eval_samples_per_second": 3.262,
+      "eval_steps_per_second": 0.41,
+      "step": 35
+    },
+    {
+      "epoch": 0.02335387609471294,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.024002594875121634,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.02465131365553033,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.02530003243593902,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.025948751216347713,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.025948751216347713,
+      "eval_loss": NaN,
+      "eval_runtime": 397.9816,
+      "eval_samples_per_second": 3.261,
+      "eval_steps_per_second": 0.41,
+      "step": 40
+    },
+    {
+      "epoch": 0.026597469996756405,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.027246188777165097,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.027894907557573793,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.028543626337982485,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.029192345118391177,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.029192345118391177,
+      "eval_loss": NaN,
+      "eval_runtime": 398.009,
+      "eval_samples_per_second": 3.261,
+      "eval_steps_per_second": 0.41,
+      "step": 45
+    },
+    {
+      "epoch": 0.02984106389879987,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.030489782679208564,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.031138501459617256,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.03178722024002595,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.032435939020434644,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.032435939020434644,
+      "eval_loss": NaN,
+      "eval_runtime": 398.0006,
+      "eval_samples_per_second": 3.261,
+      "eval_steps_per_second": 0.41,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.24125797875712e+16,
+  "total_flos": 1.048251595751424e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null