Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8797b2ae6cafe262fdf5a2684baa0f3fbade7994c2adbe36d033cc1bc5885efc
+oid sha256:80a40dd231778f6014180dcaa42597ac1b0383338507b2959ba91f22fbb515ea
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc067a3491307a2c06513c35f68e0fcd4c76cfa41fbe80e0ab8a8567ecd5d7f
+oid sha256:45adb98e582f5a5f0c65b86674f3c578644cf69841fcc7107edd36c30433d3b4
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9c793d071e896d1051385592c277f6c68b0546d5f22bd7f54f2f1d99273487
+oid sha256:1822c0dc0f72f02e3ba85ffaa91ba669803faa3eff49b1b459e017a8e300cbb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.040880503144654086,
+  "epoch": 0.05241090146750524,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 4.0205,
       "step": 35
+    },
+    {
+      "epoch": 0.041928721174004195,
+      "grad_norm": 9.626282691955566,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.1107,
+      "step": 40
+    },
+    {
+      "epoch": 0.041928721174004195,
+      "eval_loss": 3.827591896057129,
+      "eval_runtime": 22.3983,
+      "eval_samples_per_second": 17.948,
+      "eval_steps_per_second": 8.974,
+      "step": 40
+    },
+    {
+      "epoch": 0.04716981132075472,
+      "grad_norm": 10.29463005065918,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.6606,
+      "step": 45
+    },
+    {
+      "epoch": 0.05241090146750524,
+      "grad_norm": 8.57344913482666,
+      "learning_rate": 0.0,
+      "loss": 3.7016,
+      "step": 50
+    },
+    {
+      "epoch": 0.05241090146750524,
+      "eval_loss": 3.7720212936401367,
+      "eval_runtime": 22.3365,
+      "eval_samples_per_second": 17.997,
+      "eval_steps_per_second": 8.999,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4017800588820480.0,
+  "total_flos": 5235315918766080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null