Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a11476e6b71d0d9bec27bc23f595e9b11098c5d3dee78d4913bf7290c039283
+oid sha256:c25edc17a2ffb9aa870c573f7d422c5cc931dec9733820a9852e77e6b37fb828
 size 524761122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4dd9877895e45aae393182b1d9872a8f5847001b3eaf14d9de3ac7dd95caf2
+oid sha256:51cfc770648fe828b249093d78c7f8db4a25d27745d08a4bd05ea2b0549f8338
 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": 0.029904306220095694,
+  "epoch": 0.05980861244019139,
   "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": 5.682,
       "eval_steps_per_second": 0.71,
       "step": 25
+    },
+    {
+      "epoch": 0.03110047846889952,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.03229665071770335,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03349282296650718,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.034688995215311005,
+      "grad_norm": NaN,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03588516746411483,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03588516746411483,
+      "eval_loss": NaN,
+      "eval_runtime": 123.8957,
+      "eval_samples_per_second": 5.682,
+      "eval_steps_per_second": 0.71,
+      "step": 30
+    },
+    {
+      "epoch": 0.03708133971291866,
+      "grad_norm": NaN,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03827751196172249,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.04066985645933014,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.041866028708133975,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.041866028708133975,
+      "eval_loss": NaN,
+      "eval_runtime": 123.9099,
+      "eval_samples_per_second": 5.682,
+      "eval_steps_per_second": 0.71,
+      "step": 35
+    },
+    {
+      "epoch": 0.0430622009569378,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.04425837320574163,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04665071770334928,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04784688995215311,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04784688995215311,
+      "eval_loss": NaN,
+      "eval_runtime": 123.9341,
+      "eval_samples_per_second": 5.68,
+      "eval_steps_per_second": 0.71,
+      "step": 40
+    },
+    {
+      "epoch": 0.04904306220095694,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.050239234449760764,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.05143540669856459,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.05382775119617225,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05382775119617225,
+      "eval_loss": NaN,
+      "eval_runtime": 123.9347,
+      "eval_samples_per_second": 5.68,
+      "eval_steps_per_second": 0.71,
+      "step": 45
+    },
+    {
+      "epoch": 0.05502392344497608,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.056220095693779906,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.05741626794258373,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.05861244019138756,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05980861244019139,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05980861244019139,
+      "eval_loss": NaN,
+      "eval_runtime": 123.8994,
+      "eval_samples_per_second": 5.682,
+      "eval_steps_per_second": 0.71,
+      "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": 3.54289352441856e+16,
+  "total_flos": 7.08578704883712e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null