Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36369ca4fcebb046f012b2c38065061c0dbcc197ea02533d23d69a4cb3a08296
+oid sha256:046f4dd49efc478c91f3afc826b2f3ad7e585c3da6806f1c7f49748abc08202d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca784afa662e7382dd839289567429925dfdc7bc73d13c00b8d6bfb1566ae29
+oid sha256:34fda3e929aa4e7b1b8e312bb7098d31d5baa26f4c9fcd226575768508913959
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8311729536aebb3f7c37c9f4f6b8414ba95b49789c2765866d4643fc033869b3
+oid sha256:b81c1d1a084115aff5fefd3d508fbb6313dc258d0abeccdb9a0ea9cdcdee21a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.045335658238884045,
+  "epoch": 0.05812263876780006,
   "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": 19.531,
       "eval_steps_per_second": 9.792,
       "step": 39
+    },
+    {
+      "epoch": 0.04649811101424005,
+      "grad_norm": 1.3496054410934448,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.3177,
+      "step": 40
+    },
+    {
+      "epoch": 0.047660563789596044,
+      "grad_norm": 1.4967939853668213,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 2.5048,
+      "step": 41
+    },
+    {
+      "epoch": 0.04882301656495205,
+      "grad_norm": 1.4733471870422363,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 2.2494,
+      "step": 42
+    },
+    {
+      "epoch": 0.04998546934030805,
+      "grad_norm": 1.2914958000183105,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 2.0449,
+      "step": 43
+    },
+    {
+      "epoch": 0.05114792211566405,
+      "grad_norm": 1.4443607330322266,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 2.2681,
+      "step": 44
+    },
+    {
+      "epoch": 0.05231037489102005,
+      "grad_norm": 1.3686310052871704,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 2.5226,
+      "step": 45
+    },
+    {
+      "epoch": 0.05347282766637605,
+      "grad_norm": 1.6216455698013306,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 2.3361,
+      "step": 46
+    },
+    {
+      "epoch": 0.054635280441732055,
+      "grad_norm": 2.076577663421631,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 2.9312,
+      "step": 47
+    },
+    {
+      "epoch": 0.05579773321708806,
+      "grad_norm": 1.4256387948989868,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 2.2066,
+      "step": 48
+    },
+    {
+      "epoch": 0.056960185992444054,
+      "grad_norm": 1.4510419368743896,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 2.1987,
+      "step": 49
+    },
+    {
+      "epoch": 0.05812263876780006,
+      "grad_norm": 1.2870044708251953,
+      "learning_rate": 0.0,
+      "loss": 2.4237,
+      "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": 1.0749638697025536e+16,
+  "total_flos": 1.3803513326862336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null