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:d68454e11227e50dbc7de4024f57a9bbbdcc2a9166609d67ccef3604b5ed3dbd
+oid sha256:f4433ad6cf019679e62efbe788522b91c37458129c1067a4580ae9b02ccd4112
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07967ed18aa28ce2af89217d1797599036a8df26bdd3c9f2287c7fd64d02f753
+oid sha256:766883cf96619f8dd359b441512cec68417e427045a983edad62fced6cbc90b0
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0d2f7bca4df87f095e98f9f19f227720806cce48a2846ae3b7e49a4b418ee9
+oid sha256:c7ea8262840a122cf727761fa8ac9dd15f3d9b85715f03be8d5dc6ff7641222c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03237046195346746,
+  "epoch": 0.0364167696976509,
   "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": 10.13,
       "eval_steps_per_second": 1.268,
       "step": 72
+    },
+    {
+      "epoch": 0.03371923120152861,
+      "grad_norm": 6.54693078994751,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 7.0502,
+      "step": 75
+    },
+    {
+      "epoch": 0.03506800044958975,
+      "grad_norm": 3.6234800815582275,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 7.1019,
+      "step": 78
+    },
+    {
+      "epoch": 0.0364167696976509,
+      "grad_norm": 2.8791348934173584,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 7.0355,
+      "step": 81
+    },
+    {
+      "epoch": 0.0364167696976509,
+      "eval_loss": 1.7774608135223389,
+      "eval_runtime": 369.8032,
+      "eval_samples_per_second": 10.132,
+      "eval_steps_per_second": 1.268,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4906353908291994e+17,
+  "total_flos": 1.69102741270954e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null