Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d30a51b79f45ed2228946b823303ec720b0124b08c27806aadbb6594e172634
+oid sha256:ba5aeda3197e956325b6cc5bff56dab286ee79f78a116fb173a92b920084caa0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f44f2cead9013a850a430851247facf1bb0c533d278e6b69596faa54aaf000
+oid sha256:51dd603cef886cf9776c032079f5dc15019c6af7422cf2684f8f76d741e966e3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5c24709107a16c4a366ef695fabf1bcf47b8db012ccbceb7d99c5d75c4b350
+oid sha256:65941554dfccfdcf0ed28341039200adb2012eef3c09ec7b1fbc4a815a622955
 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": 0.0703336339044184,
+  "epoch": 0.09017132551848513,
   "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": 3.9661,
       "step": 35
+    },
+    {
+      "epoch": 0.0721370604147881,
+      "grad_norm": 5.879969120025635,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.7932,
+      "step": 40
+    },
+    {
+      "epoch": 0.0721370604147881,
+      "eval_loss": 0.959617555141449,
+      "eval_runtime": 15.7241,
+      "eval_samples_per_second": 14.882,
+      "eval_steps_per_second": 7.441,
+      "step": 40
+    },
+    {
+      "epoch": 0.0811541929666366,
+      "grad_norm": 6.4072957038879395,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.7872,
+      "step": 45
+    },
+    {
+      "epoch": 0.09017132551848513,
+      "grad_norm": 6.380867958068848,
+      "learning_rate": 0.0,
+      "loss": 3.6417,
+      "step": 50
+    },
+    {
+      "epoch": 0.09017132551848513,
+      "eval_loss": 0.9541131258010864,
+      "eval_runtime": 15.5353,
+      "eval_samples_per_second": 15.062,
+      "eval_steps_per_second": 7.531,
+      "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": 6966870401875968.0,
+  "total_flos": 8894809381011456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null