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:b3457743154bf487a605b17ae1ca8ffa677506a228d2de5556e8a58ccfe3021f
+oid sha256:d9d480fcbaaa3ed0e742650bd241ab11b4d2c40f9a8ea1e610f18d13b8cd65dc
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850e3398e2d7223a85dd20ee485345b8d225137582b8621c64cd7348a66254fc
+oid sha256:8a31b9658b589bc9bbda66ea459925848975406d25d318848b7b17773397bd7f
 size 51613668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e44f8551f3c2c2d0e97d369427c4b2fc820d540a88b323a1fdeba466dacfd58
+oid sha256:529f56da08fa19bc3963a7bae803cd327972f3408baf1e460b5082a821c42ee1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a75ab01cc15879cd61ff8e586fb370a9b8a51bf7b319e44e27d87274e2e703
+oid sha256:2e87d47519e32af310d5ce258e0454d331221391a1b9ee9143859120658f7a9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.069210890977866,
+  "epoch": 0.07490356166435715,
   "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": 35.95,
       "eval_steps_per_second": 4.496,
       "step": 462
+    },
+    {
+      "epoch": 0.06966031234785214,
+      "grad_norm": 0.1783035695552826,
+      "learning_rate": 6.268021954544096e-07,
+      "loss": 0.9447,
+      "step": 465
+    },
+    {
+      "epoch": 0.07010973371783828,
+      "grad_norm": 0.18420618772506714,
+      "learning_rate": 5.243166291926782e-07,
+      "loss": 1.0047,
+      "step": 468
+    },
+    {
+      "epoch": 0.07055915508782443,
+      "grad_norm": 0.1890948861837387,
+      "learning_rate": 4.308857100999042e-07,
+      "loss": 1.0931,
+      "step": 471
+    },
+    {
+      "epoch": 0.07100857645781057,
+      "grad_norm": 0.1691729575395584,
+      "learning_rate": 3.465440024411265e-07,
+      "loss": 1.2112,
+      "step": 474
+    },
+    {
+      "epoch": 0.07145799782779672,
+      "grad_norm": 0.18461930751800537,
+      "learning_rate": 2.7132270797659563e-07,
+      "loss": 1.1025,
+      "step": 477
+    },
+    {
+      "epoch": 0.07190741919778286,
+      "grad_norm": 0.17638856172561646,
+      "learning_rate": 2.052496544188487e-07,
+      "loss": 1.0648,
+      "step": 480
+    },
+    {
+      "epoch": 0.072356840567769,
+      "grad_norm": 0.1779627501964569,
+      "learning_rate": 1.483492851379914e-07,
+      "loss": 1.0676,
+      "step": 483
+    },
+    {
+      "epoch": 0.07280626193775513,
+      "grad_norm": 0.17188026010990143,
+      "learning_rate": 1.006426501190233e-07,
+      "loss": 1.1089,
+      "step": 486
+    },
+    {
+      "epoch": 0.07325568330774128,
+      "grad_norm": 0.15544207394123077,
+      "learning_rate": 6.214739817448633e-08,
+      "loss": 1.0339,
+      "step": 489
+    },
+    {
+      "epoch": 0.07370510467772742,
+      "grad_norm": 0.18268367648124695,
+      "learning_rate": 3.287777041539042e-08,
+      "loss": 1.0709,
+      "step": 492
+    },
+    {
+      "epoch": 0.07415452604771357,
+      "grad_norm": 0.1663144826889038,
+      "learning_rate": 1.284459498280266e-08,
+      "loss": 0.9674,
+      "step": 495
+    },
+    {
+      "epoch": 0.07460394741769971,
+      "grad_norm": 0.14908315241336823,
+      "learning_rate": 2.055283042018408e-09,
+      "loss": 1.0267,
+      "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": 1.489210915600466e+17,
+  "total_flos": 1.6131816039225754e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null