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:c12e5cb489ed32dcd4821db7bdaec744f9b4e8a997f01b5f1328794c04ec82a3
+oid sha256:5b6c3f80731522af0460440a871bcd398d7a6ede89f40d4e1a335bba9b90353c
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb18316fa812d07cc98d5e7abffb877c6262f20c4ddd961b54531b512ac35932
+oid sha256:6cba09c711b648d8aebf99e2e759a2e97e1005c2ccf9f206908286ac8cb9bf9f
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7ad2bea73e5c92bf130e200713bfabfcca6509d64bd5d7e25387ae390c0ce2
+oid sha256:a609c16ab60b700b0e2b40086f3b2905d38606b8ae9db201b28d73231c68124e
 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": 0.00228277093271679,
+  "epoch": 0.0029266294009189617,
   "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": 2.3071,
       "step": 35
+    },
+    {
+      "epoch": 0.0023413035207351693,
+      "grad_norm": 1.4352751970291138,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6541,
+      "step": 40
+    },
+    {
+      "epoch": 0.0023413035207351693,
+      "eval_loss": 2.4152517318725586,
+      "eval_runtime": 784.6728,
+      "eval_samples_per_second": 9.168,
+      "eval_steps_per_second": 4.584,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026339664608270655,
+      "grad_norm": 1.5534476041793823,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.406,
+      "step": 45
+    },
+    {
+      "epoch": 0.0029266294009189617,
+      "grad_norm": 1.7215681076049805,
+      "learning_rate": 0.0,
+      "loss": 2.4092,
+      "step": 50
+    },
+    {
+      "epoch": 0.0029266294009189617,
+      "eval_loss": 2.4109411239624023,
+      "eval_runtime": 789.4098,
+      "eval_samples_per_second": 9.113,
+      "eval_steps_per_second": 4.557,
+      "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": 9889898079191040.0,
+  "total_flos": 1.261320334737408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null