Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d05cc3154c0e12834f75a2dcc7a524a6c1513182ab87e7ab6d1b5cfc2161a37
+oid sha256:b2ae296b38710fe1327adf1ea6de50e0a9d0092dfe58ff06493196b0b13d9af2
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30169e64299076810f3e894f11766b2a069f17cb40955bfd96f71fc04b494a33
+oid sha256:d9a555a6a60bdef4a37512d4294f18b52872d5eef5f33ccf73a73556687eb8cf
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0910d44e52f9f1cc509a0d2206f90b9c42c8ab4231af3fd41c28aef85cb43e72
+oid sha256:ff21dd7c2b2e61f49a8ec74b626a9e3e3040b1da40e138b6c42f961acba34607
 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": 0.10386151797603196,
+  "epoch": 0.13315579227696406,
   "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": 1.3029,
       "step": 35
+    },
+    {
+      "epoch": 0.10652463382157124,
+      "grad_norm": 1.1248072385787964,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5697,
+      "step": 40
+    },
+    {
+      "epoch": 0.10652463382157124,
+      "eval_loss": 1.353584885597229,
+      "eval_runtime": 5.6635,
+      "eval_samples_per_second": 28.074,
+      "eval_steps_per_second": 14.126,
+      "step": 40
+    },
+    {
+      "epoch": 0.11984021304926765,
+      "grad_norm": 0.7022452354431152,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.117,
+      "step": 45
+    },
+    {
+      "epoch": 0.13315579227696406,
+      "grad_norm": 1.2095106840133667,
+      "learning_rate": 0.0,
+      "loss": 1.5038,
+      "step": 50
+    },
+    {
+      "epoch": 0.13315579227696406,
+      "eval_loss": 1.3367788791656494,
+      "eval_runtime": 5.6064,
+      "eval_samples_per_second": 28.36,
+      "eval_steps_per_second": 14.269,
+      "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": 1944019034701824.0,
+  "total_flos": 2487576988483584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null