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:dc23af3af8edcc2583c76cb038ee0ab1273481f1095d522d5ff88300c3a43e6e
+oid sha256:9cdc1eeab977f17ce9a25f13bec48d0f21608f1ffe2f146d02ee0e875bdb100b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a929084f8855f23eecffeb3d9d0956a22b85f6197464dbd1cdb30385c3448a
+oid sha256:ce88be89d26d64285e1c018f8579d17787dc57588d47f7e493e2d9551bf754e5
 size 43122580

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c69b1cab68eedeb20a7a2f6dae4bcafb8fd3614223404432fa886a8349b124
+oid sha256:045de0da72ad961fe3bc9567990b6d2af33931f1f215316d68c3a58bdb504487
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c1c66f8dfc333ab8909acd4d3d3424ff4614f1cc0a55da45ce3aac978468d7
+oid sha256:cabdb84c1d4dd2cd6bfd65caa3a027d9737ffbd84e1f5cd20dcae98f7e2b5032
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e983f405a1a428731c9fb2cfa9409d89f047a5632780bbd7fa48429b301a9db
+oid sha256:25cd1afc4df00932d149f330c9473d401104bcd9ef9ec5bb3fa39d888175c652
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32aeb81637fab6301be2e2247e68aac5f94e8605d06512d35276a41135901979
+oid sha256:668570a9ba40876e5a78cf613ed02369737920179e37ee5bec448d8201203822
 size 15024

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": 0.006584501097416849,
+  "epoch": 0.008441668073611346,
   "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": 3.4898,
       "step": 35
+    },
+    {
+      "epoch": 0.006753334458889077,
+      "grad_norm": 18.379047393798828,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.8394,
+      "step": 40
+    },
+    {
+      "epoch": 0.006753334458889077,
+      "eval_loss": 0.9370124936103821,
+      "eval_runtime": 110.0748,
+      "eval_samples_per_second": 90.629,
+      "eval_steps_per_second": 11.329,
+      "step": 40
+    },
+    {
+      "epoch": 0.007597501266250211,
+      "grad_norm": 25.660686492919922,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.5916,
+      "step": 45
+    },
+    {
+      "epoch": 0.008441668073611346,
+      "grad_norm": 29.074373245239258,
+      "learning_rate": 0.0,
+      "loss": 3.7459,
+      "step": 50
+    },
+    {
+      "epoch": 0.008441668073611346,
+      "eval_loss": 0.9260633587837219,
+      "eval_runtime": 110.0826,
+      "eval_samples_per_second": 90.623,
+      "eval_steps_per_second": 11.328,
+      "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": 5.174757577405235e+16,
+  "total_flos": 6.625091824438477e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null