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:f068d5669c53449fe332da5c94685d42f988385554047ad6da79b7fb04240c31
+oid sha256:a25cfbf4f256249f5bfebb8b4997092e0c4bdf6c67de2bb971da851cbf5895b0
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ab9ae395827a859cb1db4f69453e1384fd0031f9c3f4004890f548573f92b5
+oid sha256:9a7a916ef745f67347e93fe7458390117d7750f9a3aae70eef61c4fc55396490
 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": 0.03547066848567531,
+  "epoch": 0.04547521600727603,
   "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": 2.1482,
       "step": 35
+    },
+    {
+      "epoch": 0.03638017280582083,
+      "grad_norm": 1.552095651626587,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7002,
+      "step": 40
+    },
+    {
+      "epoch": 0.03638017280582083,
+      "eval_loss": 1.860257625579834,
+      "eval_runtime": 18.0583,
+      "eval_samples_per_second": 25.639,
+      "eval_steps_per_second": 12.847,
+      "step": 40
+    },
+    {
+      "epoch": 0.040927694406548434,
+      "grad_norm": 1.3981469869613647,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5404,
+      "step": 45
+    },
+    {
+      "epoch": 0.04547521600727603,
+      "grad_norm": 2.001523494720459,
+      "learning_rate": 0.0,
+      "loss": 1.7515,
+      "step": 50
+    },
+    {
+      "epoch": 0.04547521600727603,
+      "eval_loss": 1.853514552116394,
+      "eval_runtime": 17.853,
+      "eval_samples_per_second": 25.934,
+      "eval_steps_per_second": 12.995,
+      "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