Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285ef7d844df91bcbe3f44bf76ca306bed6dc48ab536abb11e669b0cf7f5ab6f
+oid sha256:3ab767649278e543b6896e02bc54289f0555fff95024e5424eacd8f2277e9a92
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c12f844e83b270eca953a432b58a5975e7bf1e77981563496963bf60a80cb89
+oid sha256:cc8ca6b3ee7fe8364da32720301af35daf5036c1611078d7c0594d109709eda8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba1e30e28aa45cf44ce5d51d23b6a01a5f4515c33ee5cd42abcbcc581e0b1cf
+oid sha256:22201c714f7852304d11d30fcad683634f81c2934973037d35502874efb66351
 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": 0.13793103448275862,
+  "epoch": 0.1768346595932803,
   "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": 0.6784,
       "step": 35
+    },
+    {
+      "epoch": 0.14146772767462423,
+      "grad_norm": 2.1522183418273926,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7385,
+      "step": 40
+    },
+    {
+      "epoch": 0.14146772767462423,
+      "eval_loss": 0.8148200511932373,
+      "eval_runtime": 14.3401,
+      "eval_samples_per_second": 8.368,
+      "eval_steps_per_second": 4.184,
+      "step": 40
+    },
+    {
+      "epoch": 0.15915119363395225,
+      "grad_norm": 1.3055857419967651,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7619,
+      "step": 45
+    },
+    {
+      "epoch": 0.1768346595932803,
+      "grad_norm": 2.882671356201172,
+      "learning_rate": 0.0,
+      "loss": 0.855,
+      "step": 50
+    },
+    {
+      "epoch": 0.1768346595932803,
+      "eval_loss": 0.8008769154548645,
+      "eval_runtime": 14.0692,
+      "eval_samples_per_second": 8.529,
+      "eval_steps_per_second": 4.265,
+      "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": 6550096120381440.0,
+  "total_flos": 8362701336084480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null