Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b063f794e8d905c44caa125b66183707a1dde48973e3276ff28d2c4c531785f
+oid sha256:b20b2dc837e17518add160d67e3d149f018557e8175d883f697756651376cb4b
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c8ea1ef0d1661206fbbce0145f1e033d65e42959edba13fa92aec62fc39809
+oid sha256:dd5919952010ae3dc551c14abb965ce0b21a381ef9a2625c06d69f1d2853ebf7
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 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": 0.10535201755866959,
+  "epoch": 0.13506668917778153,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 28.996,
       "eval_steps_per_second": 14.498,
       "step": 39
+    },
+    {
+      "epoch": 0.10805335134222523,
+      "grad_norm": 0.22584712505340576,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.18,
+      "step": 40
+    },
+    {
+      "epoch": 0.11075468512578085,
+      "grad_norm": 0.22953017055988312,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.2876,
+      "step": 41
+    },
+    {
+      "epoch": 0.11345601890933649,
+      "grad_norm": 0.22218628227710724,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2246,
+      "step": 42
+    },
+    {
+      "epoch": 0.11615735269289211,
+      "grad_norm": 0.228598952293396,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.2262,
+      "step": 43
+    },
+    {
+      "epoch": 0.11885868647644775,
+      "grad_norm": 0.2286594957113266,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.1715,
+      "step": 44
+    },
+    {
+      "epoch": 0.12156002026000337,
+      "grad_norm": 0.2573833465576172,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2798,
+      "step": 45
+    },
+    {
+      "epoch": 0.12426135404355901,
+      "grad_norm": 0.19452853500843048,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.3053,
+      "step": 46
+    },
+    {
+      "epoch": 0.12696268782711465,
+      "grad_norm": 0.18400336802005768,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.215,
+      "step": 47
+    },
+    {
+      "epoch": 0.12966402161067025,
+      "grad_norm": 0.20695160329341888,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.1684,
+      "step": 48
+    },
+    {
+      "epoch": 0.1323653553942259,
+      "grad_norm": 0.2696451246738434,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.2025,
+      "step": 49
+    },
+    {
+      "epoch": 0.13506668917778153,
+      "grad_norm": 0.18349821865558624,
+      "learning_rate": 0.0,
+      "loss": 1.1954,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.487287818682368e+16,
+  "total_flos": 5.73327259163689e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null