Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f801add4c0d2e08fe2b55e70f53bea6aef21a176c0657a3e820c530d88b29ca
+oid sha256:4e4b409903b918c6df7d1cf23cdf0ef713e7f8f395ecf3d8b59468d0342b1e21
 size 90365754

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a607a89f29f579bb7e3b03d01051406f784e1383419ed5b710137e9d12493e
+oid sha256:1dc4928675a55c735fd8b40848204aeb479d0a3c4cb847cd8b779245fffeab2c
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec16933bc3b62330056ce3e53e0d229a8971f7e3969b0b72440ffdd637e6216
+oid sha256:8bec9259f8861eb32b9f9ceb9f92b307a160be2011844e232460a52b5467663d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a73e1ff9beffc13aa54f4adf4df9ed4ad8819cc503c53ddfd100ef74e91d520
+oid sha256:cd1931e4016bf28b07346e79413c71e240f12f43909f7431de607b5c05407707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5095541401273885,
+  "epoch": 0.7643312101910829,
   "eval_steps": 15,
-  "global_step": 30,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,119 @@
       "eval_samples_per_second": 23.727,
       "eval_steps_per_second": 5.932,
       "step": 30
+    },
+    {
+      "epoch": 0.5265392781316348,
+      "grad_norm": NaN,
+      "learning_rate": 6.2e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.5435244161358811,
+      "grad_norm": NaN,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.5605095541401274,
+      "grad_norm": NaN,
+      "learning_rate": 6.6e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.5774946921443737,
+      "grad_norm": NaN,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.5944798301486199,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.6114649681528662,
+      "grad_norm": NaN,
+      "learning_rate": 7.2e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.6284501061571125,
+      "grad_norm": NaN,
+      "learning_rate": 7.4e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.6454352441613588,
+      "grad_norm": NaN,
+      "learning_rate": 7.6e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.6624203821656051,
+      "grad_norm": NaN,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.6794055201698513,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.6963906581740976,
+      "grad_norm": NaN,
+      "learning_rate": 8.2e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.7133757961783439,
+      "grad_norm": NaN,
+      "learning_rate": 8.4e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.7303609341825902,
+      "grad_norm": NaN,
+      "learning_rate": 8.6e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.7473460721868365,
+      "grad_norm": NaN,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "eval_loss": NaN,
+      "eval_runtime": 4.2395,
+      "eval_samples_per_second": 23.588,
+      "eval_steps_per_second": 5.897,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -260,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.161267083476992e+16,
+  "total_flos": 1.741900625215488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null