Training in progress, step 462, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94171cecd33e76d6d8459a3fb63548959eb0685692b6a15cc318d297f2bd4ed
+oid sha256:2f8d0c376cd6589d5b11a8f79cee03f674e63829a2290155bc1ede6fbec8d765
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebc1a322d1d003f0fa9b55767eb496276a9ff94588981aca8850a402da80a00
+oid sha256:ed8b70b8a342812192d5c3b7c9978254f5ffabf514448203b80e1686d5fdc13b
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301cc041eab7eb674260bf30ff0c9951da0d11395a56034569eaa0cb29a55e7b
+oid sha256:d31defcd29d743f2c19de79a505fa9f79f745600b1ccfe976120a3783f910551
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
+oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0817843866171004,
+  "epoch": 2.2899628252788102,
   "eval_steps": 42,
-  "global_step": 420,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,6 +1075,112 @@
       "eval_samples_per_second": 190.476,
       "eval_steps_per_second": 24.09,
       "step": 420
+    },
+    {
+      "epoch": 2.096654275092937,
+      "grad_norm": 0.044985052198171616,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 12.1785,
+      "step": 423
+    },
+    {
+      "epoch": 2.1115241635687734,
+      "grad_norm": 0.04410139098763466,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 12.1236,
+      "step": 426
+    },
+    {
+      "epoch": 2.12639405204461,
+      "grad_norm": 0.05194435641169548,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 11.6732,
+      "step": 429
+    },
+    {
+      "epoch": 2.141263940520446,
+      "grad_norm": 0.05501653999090195,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 12.3777,
+      "step": 432
+    },
+    {
+      "epoch": 2.1561338289962824,
+      "grad_norm": 0.04983314871788025,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 11.8892,
+      "step": 435
+    },
+    {
+      "epoch": 2.171003717472119,
+      "grad_norm": 0.03725075721740723,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 11.2909,
+      "step": 438
+    },
+    {
+      "epoch": 2.1858736059479553,
+      "grad_norm": 0.05022915452718735,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 12.1708,
+      "step": 441
+    },
+    {
+      "epoch": 2.200743494423792,
+      "grad_norm": 0.04059191420674324,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 12.0311,
+      "step": 444
+    },
+    {
+      "epoch": 2.2156133828996283,
+      "grad_norm": 0.056071698665618896,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 11.767,
+      "step": 447
+    },
+    {
+      "epoch": 2.2304832713754648,
+      "grad_norm": 0.0420910008251667,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 11.9581,
+      "step": 450
+    },
+    {
+      "epoch": 2.2453531598513012,
+      "grad_norm": 0.05278888717293739,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 12.2002,
+      "step": 453
+    },
+    {
+      "epoch": 2.2602230483271377,
+      "grad_norm": 0.05625374615192413,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 11.4997,
+      "step": 456
+    },
+    {
+      "epoch": 2.2750929368029738,
+      "grad_norm": 0.03911924734711647,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 11.6504,
+      "step": 459
+    },
+    {
+      "epoch": 2.2899628252788102,
+      "grad_norm": 0.054204318672418594,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 12.3732,
+      "step": 462
+    },
+    {
+      "epoch": 2.2899628252788102,
+      "eval_loss": 11.911750793457031,
+      "eval_runtime": 1.7787,
+      "eval_samples_per_second": 191.152,
+      "eval_steps_per_second": 24.175,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2024747827200.0,
+  "total_flos": 2227222609920.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null