Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8e26300947ec589d65e0dfa3931e41f689901ec2188e5adb11d226a6b633f1
+oid sha256:11009d2194b52ba6fd9eb34c094b518a0d93ef5131031793c57b9d8b531eac78
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848971db7f7758fb5a57f232f96e186d288b8e668b7b1c24c8aa01de2ba752e1
+oid sha256:d14fbf3c4b309af400d3d236aa2915f5e825b26c0678df00b64f3e2d4dab3a50
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c4c1885b8e7707f58a988157cfa3928be7c688eb8d4791782f94eef4fa8dd0
+oid sha256:f0e2be3421e9c217b5150263bfb4d4fc41f97c4ecac79dc6eac449e54cabd49f
 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": 0.04834211341803533,
+  "epoch": 0.061977068484660676,
   "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": 1.0063,
       "step": 35
+    },
+    {
+      "epoch": 0.04958165478772854,
+      "grad_norm": 3.558058500289917,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.005,
+      "step": 40
+    },
+    {
+      "epoch": 0.04958165478772854,
+      "eval_loss": 1.1022478342056274,
+      "eval_runtime": 51.7123,
+      "eval_samples_per_second": 6.575,
+      "eval_steps_per_second": 3.287,
+      "step": 40
+    },
+    {
+      "epoch": 0.05577936163619461,
+      "grad_norm": 3.6791601181030273,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9918,
+      "step": 45
+    },
+    {
+      "epoch": 0.061977068484660676,
+      "grad_norm": 3.8350329399108887,
+      "learning_rate": 0.0,
+      "loss": 1.0825,
+      "step": 50
+    },
+    {
+      "epoch": 0.061977068484660676,
+      "eval_loss": 1.0853497982025146,
+      "eval_runtime": 52.0729,
+      "eval_samples_per_second": 6.529,
+      "eval_steps_per_second": 3.265,
+      "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": 1.423763105120256e+16,
+  "total_flos": 1.825092302536704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null