Training in progress, step 78, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146a208d3aa4db0b6797a0b23846578e21f54342fc2a9b6f797541c735af524f
+oid sha256:8d34e1b1858956956b2a4bc7d70576542147952fd58b8e3f1c7df21e7eecd1f0
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559fbbc77ee7bda4b9cb7dfb44f1f251410a918168a2aea24cbfbb3cb8bec867
+oid sha256:5ffb5552c62229403427efd349092fc35e09bedff55d8fb73712fa390452f3c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb438ab9499d5178d553290d304fad6bd105cd4f59f8f03d9657a249b7bd5f14
+oid sha256:a4d6e5f76805b36e4d76ee2a3b48ba3bedb1c2bda79be4f5c70f809dd0d57438
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6632653061224489,
+  "epoch": 0.7959183673469388,
   "eval_steps": 13,
-  "global_step": 65,
+  "global_step": 78,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,49 @@
       "eval_samples_per_second": 36.476,
       "eval_steps_per_second": 4.642,
       "step": 65
+    },
+    {
+      "epoch": 0.673469387755102,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.7040816326530612,
+      "grad_norm": NaN,
+      "learning_rate": 6.22170203068947e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": NaN,
+      "learning_rate": 5.8927844739931834e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.7653061224489796,
+      "grad_norm": NaN,
+      "learning_rate": 5.559822380516539e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": NaN,
+      "learning_rate": 5.2243241517525754e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "eval_loss": NaN,
+      "eval_runtime": 4.5322,
+      "eval_samples_per_second": 36.406,
+      "eval_steps_per_second": 4.634,
+      "step": 78
     }
   ],
   "logging_steps": 3,
@@ -221,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.76894074945536e+16,
+  "total_flos": 2.122728899346432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null