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:c20f30a2c0c78492fec83f06e7fd7addba582f6f51c0d7f285f7254720ba6c00
+oid sha256:6407203804f487f7f6db196c2b358c508d2117ac0d4d6b903b6e6c277fef8239
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aaea64f6ee71759413489bb681caddb2a8c5eb87536bd2b51cc1d90c9b5012c
+oid sha256:6f98106b49e5c68e45b7a14ec4f02618c651af85ef83cb949c6b05db4ddfddb5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae8d4065d911ba11f2f51fe3d3db409db35e37fa178d3f4d6e23c646987dad6
+oid sha256:bca5e8f66f82364c7b07117907de83b853ab06b688dc0a31bd5fe343675f7115
 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": 0.026698613725825774,
+  "epoch": 0.03422899195618689,
   "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": 0.6943,
       "step": 35
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "grad_norm": 0.5501211881637573,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7182,
+      "step": 40
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "eval_loss": 0.752651035785675,
+      "eval_runtime": 51.09,
+      "eval_samples_per_second": 12.038,
+      "eval_steps_per_second": 6.029,
+      "step": 40
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": 0.6212546229362488,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7155,
+      "step": 45
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "grad_norm": 0.5869794487953186,
+      "learning_rate": 0.0,
+      "loss": 0.6951,
+      "step": 50
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "eval_loss": 0.7515175342559814,
+      "eval_runtime": 50.7626,
+      "eval_samples_per_second": 12.115,
+      "eval_steps_per_second": 6.067,
+      "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": 9247821240729600.0,
+  "total_flos": 1.1929689400541184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null