Training in progress, step 60, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b0162c125dace0461332123e8c7d602462e84e158ad2d3f071bbc125b34b8d
+oid sha256:132c6ad2f0e6ca9cbafb4299d39bae52bde8b115fc570cfa83951b10df31dc73
 size 239452242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e0b4692f0d79aa027250daa798b9b99aa2daab99fce81150537a9623556468
+oid sha256:98f27784cc712643b6f32c7b360c776b909647ee0e557d8667bfc0fed90886b9
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c19a532ddf743881461eea886de51a0451550ba062c994babb62565733b22d
+oid sha256:3b4164ec2060cabb2b939eb68c0aa306cca823c2d53027e782ea1488cef57ea8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e94f4caf902c120d48372da3bb1cf8d147f3ddef7262ea875dbd118eb698ece
+oid sha256:7ee9289e194488fcfb7c8a56f41078ad0cbfc6c87530ed9f3e7891e3005bdd0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7468879668049793,
+  "epoch": 0.995850622406639,
   "eval_steps": 15,
-  "global_step": 45,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -354,6 +354,119 @@
       "eval_samples_per_second": 6.039,
       "eval_steps_per_second": 1.539,
       "step": 45
+    },
+    {
+      "epoch": 0.7634854771784232,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.7800829875518672,
+      "grad_norm": NaN,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.7966804979253111,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.8132780082987552,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.8298755186721992,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.8464730290456431,
+      "grad_norm": NaN,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.8630705394190872,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.8796680497925311,
+      "grad_norm": NaN,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.8962655601659751,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.9128630705394191,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.9294605809128631,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.946058091286307,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.9626556016597511,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.979253112033195,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.995850622406639,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.995850622406639,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7744,
+      "eval_samples_per_second": 6.081,
+      "eval_steps_per_second": 1.55,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -368,12 +481,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.327975769309184e+17,
+  "total_flos": 1.770634359078912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null