Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b4d31956f026751b7d57641b9fd1c2dd91cac3b6a8dfdc40461921f3ffe64c
+oid sha256:662e8240fcc8125ee212a998f444a99fcb0584a529faab6cba36c8c0124ed12f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12be1ad8deede594320aae6b84265d8bce1fd0f5a4c1cfc7aba0dda623199a5d
+oid sha256:94679983a837ebe8099bd03c71b3601567757298dfa8dc794ea7fce417dd7ba3
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f03fbef729f64ddf68b55e06f01e7bb1d8bf0494ed9ac87477f34ab984a1d9b
+oid sha256:a6ab9b9869e601adf44834e3a12d4a18fbed8343468019356d2f3491dc62e15c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03936039360393604,
+  "epoch": 0.04428044280442804,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 7.221,
       "eval_steps_per_second": 0.905,
       "step": 72
+    },
+    {
+      "epoch": 0.04100041000410004,
+      "grad_norm": 0.2209480255842209,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.5878,
+      "step": 75
+    },
+    {
+      "epoch": 0.04264042640426404,
+      "grad_norm": 0.21654435992240906,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.6279,
+      "step": 78
+    },
+    {
+      "epoch": 0.04428044280442804,
+      "grad_norm": 0.1880025714635849,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 0.6035,
+      "step": 81
+    },
+    {
+      "epoch": 0.04428044280442804,
+      "eval_loss": 0.6215988993644714,
+      "eval_runtime": 426.4354,
+      "eval_samples_per_second": 7.225,
+      "eval_steps_per_second": 0.905,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8808127625363456e+17,
+  "total_flos": 2.1188066446147584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null