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:f095dd2b5594f4e895d9b15454aa464b69e06c2c3b0587fede2dd723016b4825
+oid sha256:fc976a8f5279c1449a09fcc7fc0514d622a12a83464f07e03e02e64254ae6746
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2afc787e4ce57dfd69125b9c3e5613343e9674d3f3267399d27213d4f5e6e0a
+oid sha256:c393f9609874100373ae045512d10a4b91085109c4dc620e04668ae31199c5a6
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da57a3a869ac100e03e854428cb96b9fe176c6ed5065d0878032c78bdd0f415e
+oid sha256:0f70044af2bf806d36eee202f06cd6fe1ee465e8a1d9f7ce321d93c2a261931e
 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": 0.0004980779300392076,
+  "epoch": 0.0006385614487682149,
   "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": 1.9742,
       "step": 35
+    },
+    {
+      "epoch": 0.000510849159014572,
+      "grad_norm": 0.7436493635177612,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9278,
+      "step": 40
+    },
+    {
+      "epoch": 0.000510849159014572,
+      "eval_loss": 1.9221231937408447,
+      "eval_runtime": 1209.3488,
+      "eval_samples_per_second": 27.262,
+      "eval_steps_per_second": 13.631,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005747053038913935,
+      "grad_norm": 0.8459659218788147,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9795,
+      "step": 45
+    },
+    {
+      "epoch": 0.0006385614487682149,
+      "grad_norm": 0.8609293699264526,
+      "learning_rate": 0.0,
+      "loss": 2.0347,
+      "step": 50
+    },
+    {
+      "epoch": 0.0006385614487682149,
+      "eval_loss": 1.9152170419692993,
+      "eval_runtime": 1207.7242,
+      "eval_samples_per_second": 27.298,
+      "eval_steps_per_second": 13.65,
+      "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": 3198189793443840.0,
+  "total_flos": 4100243324928000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null