Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a74638fb7fa62b725f1b426b679d55360a64572a4d2afa7fdc7008bee05c182
+oid sha256:c8e24ccafa7310e4e7da03118fd606348757cdf49edf8aef545b0958b117a7e2
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38e789b4ed0d9cc163501b446068637e22a65f5a1ff5fa9ab05c47c124a4461
+oid sha256:12647947c7fc99ffe9922bf0d620aafe3be63c07b59863069fddd9c92c760fed
 size 159641284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ebe6b98bfc0034ebb7d77910dc0cb274b47fec500ee6ddf50c5bda287747948
+oid sha256:f20f8fe014dd969738c735a1d6b57ae25ecd0689bafec5958f58918f299d0571
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7857142857142857,
+  "epoch": 0.8503401360544217,
   "eval_steps": 42,
-  "global_step": 462,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1181,6 +1181,90 @@
       "eval_samples_per_second": 28.135,
       "eval_steps_per_second": 3.524,
       "step": 462
+    },
+    {
+      "epoch": 0.7908163265306123,
+      "grad_norm": 1.4359699487686157,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 1.3433,
+      "step": 465
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": 1.4439855813980103,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 1.3676,
+      "step": 468
+    },
+    {
+      "epoch": 0.8010204081632653,
+      "grad_norm": 1.370235800743103,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 1.2855,
+      "step": 471
+    },
+    {
+      "epoch": 0.8061224489795918,
+      "grad_norm": 1.2090818881988525,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 1.3047,
+      "step": 474
+    },
+    {
+      "epoch": 0.8112244897959183,
+      "grad_norm": 1.3970741033554077,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 1.3344,
+      "step": 477
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 1.4051525592803955,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 1.3377,
+      "step": 480
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 1.4082175493240356,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 1.2679,
+      "step": 483
+    },
+    {
+      "epoch": 0.826530612244898,
+      "grad_norm": 1.3774138689041138,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 1.2442,
+      "step": 486
+    },
+    {
+      "epoch": 0.8316326530612245,
+      "grad_norm": 1.3718559741973877,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 1.3134,
+      "step": 489
+    },
+    {
+      "epoch": 0.8367346938775511,
+      "grad_norm": 1.3869266510009766,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 1.365,
+      "step": 492
+    },
+    {
+      "epoch": 0.8418367346938775,
+      "grad_norm": 1.3461697101593018,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 1.3113,
+      "step": 495
+    },
+    {
+      "epoch": 0.8469387755102041,
+      "grad_norm": 1.4545960426330566,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 1.3021,
+      "step": 498
     }
   ],
   "logging_steps": 3,
@@ -1195,12 +1279,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8714583217523917e+17,
+  "total_flos": 2.02538779410432e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null