Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3712cec134156d96ca7843df53700c85575be5ecf48a4623a67e324d79f87c7a
+oid sha256:b9127d7fa466fe2619aac386b88414f7f0e5046b46ff8e6555e21d5495342b81
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e5b693fcf6feade1a413f6819457710305ca0b772501b15b98a7ab45316329
+oid sha256:6a293a836f4ac8bcbff568649c93e3e29ec5b38ea7661bec89aed71bf37b1141
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf325e952cc97e8bdef934cc4049226988f1dcf6ba8f7edaadb370b11b7895e
+oid sha256:883df6617b9d273fe9c69664d9c482db65f3fa4c11e97f2738c6cca1a9f5330a
 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": 0.0006459627329192546,
+  "epoch": 0.0008281573498964803,
   "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": 1.6012,
       "step": 35
+    },
+    {
+      "epoch": 0.0006625258799171842,
+      "grad_norm": 0.2549556493759155,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4636,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006625258799171842,
+      "eval_loss": 1.5705076456069946,
+      "eval_runtime": 1474.4224,
+      "eval_samples_per_second": 17.241,
+      "eval_steps_per_second": 8.621,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007453416149068323,
+      "grad_norm": 0.2807498276233673,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6128,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008281573498964803,
+      "grad_norm": 0.28640541434288025,
+      "learning_rate": 0.0,
+      "loss": 1.5338,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008281573498964803,
+      "eval_loss": 1.5688624382019043,
+      "eval_runtime": 1490.9548,
+      "eval_samples_per_second": 17.05,
+      "eval_steps_per_second": 8.525,
+      "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": 5576330921902080.0,
+  "total_flos": 7175425818624000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null