Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77cab04f7c8e3c5ebeed8f9657eb3c676d86b31ccb90b338cc2b824dd048b34c
+oid sha256:1b76fb774cc29aa4a0237aa01ddb7ea6873e1ef742301d3319a8539c391b298b
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa4b008e1f405a9a60fcfe22aa1f72d89918323362bb1d4d225e8baad7203ce
+oid sha256:21bcfadb23132f558cbe3dd6f0525ef44f8fa5ac2d99bb640f93a5f508dc6d97
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963103910acf3003b8f4035e02dee57e8e13bbe04dcb03283c8c89f04827e98f
+oid sha256:76176b194774cb7a663950593f31d2e41cbb03e09a4aaaaf2425c3c4a43bad6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
+oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8486187845303867,
+  "epoch": 0.9546961325966851,
   "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": 5.921,
       "eval_steps_per_second": 2.96,
       "step": 72
+    },
+    {
+      "epoch": 0.8839779005524862,
+      "grad_norm": 27.09636116027832,
+      "learning_rate": 3.333223252352985e-05,
+      "loss": 51.9685,
+      "step": 75
+    },
+    {
+      "epoch": 0.9193370165745857,
+      "grad_norm": 34.2943000793457,
+      "learning_rate": 2.6291396375236232e-05,
+      "loss": 50.2621,
+      "step": 78
+    },
+    {
+      "epoch": 0.9546961325966851,
+      "grad_norm": 29.85685157775879,
+      "learning_rate": 1.99258117923236e-05,
+      "loss": 49.1029,
+      "step": 81
+    },
+    {
+      "epoch": 0.9546961325966851,
+      "eval_loss": 1.5639307498931885,
+      "eval_runtime": 48.3157,
+      "eval_samples_per_second": 5.919,
+      "eval_steps_per_second": 2.96,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.786592547116155e+17,
+  "total_flos": 4.259916615505674e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null