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:edaff7825cdbe6b0fdb39696cf2b7cd66d5f90ad6d25445e43f5ef7ee3340029
+oid sha256:a3713ff8b77c83ba29cfaeb8d16937c25c823b3c939bc36a5731c62c7bc0bd91
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d42cdf0549644c2e41d727772a5c59e41e49be61fd4c13178c5d354ef644fc
+oid sha256:5a7c0e64527c54ea3d64ae948893f26b9f78304066fe2bfee9f7a5bc61323260
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfcf362697f9cf020341e74d8b51e99e167f40c11f2909e2bf8b9ea96351aec8
+oid sha256:bfbf6021e3e81f4c9b4a471ebfa9809e3f0b65c69ac87b4db7d3e0b2bd4cb7e1
 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": 0.10875386199794027,
+  "epoch": 0.1176989848462557,
   "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": 26.622,
       "eval_steps_per_second": 6.657,
       "step": 462
+    },
+    {
+      "epoch": 0.10946005590701781,
+      "grad_norm": 0.890392005443573,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 1.0834,
+      "step": 465
+    },
+    {
+      "epoch": 0.11016624981609534,
+      "grad_norm": 0.8814263939857483,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 1.0303,
+      "step": 468
+    },
+    {
+      "epoch": 0.11087244372517287,
+      "grad_norm": 0.8813495635986328,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 1.0092,
+      "step": 471
+    },
+    {
+      "epoch": 0.11157863763425041,
+      "grad_norm": 0.8011179566383362,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 1.0072,
+      "step": 474
+    },
+    {
+      "epoch": 0.11228483154332794,
+      "grad_norm": 0.9191976189613342,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 1.0898,
+      "step": 477
+    },
+    {
+      "epoch": 0.11299102545240547,
+      "grad_norm": 0.9359084963798523,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 1.0413,
+      "step": 480
+    },
+    {
+      "epoch": 0.11369721936148301,
+      "grad_norm": 0.8636139035224915,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 1.0287,
+      "step": 483
+    },
+    {
+      "epoch": 0.11440341327056054,
+      "grad_norm": 0.9202425479888916,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 1.1024,
+      "step": 486
+    },
+    {
+      "epoch": 0.11510960717963807,
+      "grad_norm": 0.928870677947998,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 1.0219,
+      "step": 489
+    },
+    {
+      "epoch": 0.11581580108871561,
+      "grad_norm": 0.8760671019554138,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 1.034,
+      "step": 492
+    },
+    {
+      "epoch": 0.11652199499779314,
+      "grad_norm": 0.8538545966148376,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 1.0029,
+      "step": 495
+    },
+    {
+      "epoch": 0.11722818890687067,
+      "grad_norm": 0.8800035119056702,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 1.0125,
+      "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": 3.284562863141683e+17,
+  "total_flos": 3.5547217133568e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null