Training in progress, step 48, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6500cfe7d32af28293bf05699f3d4b4f782490370d2ed05a402742527e9f6baa
+oid sha256:f45da18ffe6a87eec948702c550eb89629bb19b370b9203cabcf65a1e7a0f995
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82dfd893e72a3b366be54002f0aec51818dc8e6d772c045f58cf343884ff501
+oid sha256:2d64953f2e9fcada48106b0ad051c6bb12e4e7fe1c3f5c7aceb52311967353d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34dfab98c5160f80b7ff1cb36a34b989f90aa42216044020c0a4eaefab609564
+oid sha256:66a2b95a554f478964b177ad3584df1edb2740b9bf0b38dfedd8dd3ec77bf608
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7618a07dd363e062b6c15c199ea34ed47223c82e5b79d5ecd903f82497276ab
+oid sha256:4e28956bcd22cce157bbc51b2792ecea0f5758f658ecdb7e2f6f44bf0a8eb437
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219f8ea81679636159b406422b11fb4c51db85f8c5ae7400647ded4df59425c1
+oid sha256:aa7369be71488b3930265a27fef5a0c7339be82a8750ca1eac7c1e8b9538cf4a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.31316725978647686,
+  "epoch": 0.3416370106761566,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 32.939,
       "eval_steps_per_second": 4.169,
       "step": 44
+    },
+    {
+      "epoch": 0.3202846975088968,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.3274021352313167,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.33451957295373663,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.3416370106761566,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.3416370106761566,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1954,
+      "eval_samples_per_second": 32.938,
+      "eval_steps_per_second": 4.169,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3057216190663885e+17,
+  "total_flos": 1.4244235844360602e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null