Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7014f2301f834485a93dc5cc5fe2b0c4c3adcbb557d4a9aba7119f0e7372a93d
+oid sha256:a61d49b825c4e33e07a7470021c47880fe30b8a7e3bda21bf784b54f3ea7208d
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa43006c9de1e5d22f404b9ba58739d11bdf9a5f967e27733ab8f580cddefa3
+oid sha256:fdd96c38ed9d417cc05eb56147047f51e84ef788f3f25c168a7f5d3859e1b220
 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": 0.030848329048843187,
+  "epoch": 0.039549139806209214,
   "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": 2.1545,
       "step": 35
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 1.8912897109985352,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9199,
+      "step": 40
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "eval_loss": 1.9353423118591309,
+      "eval_runtime": 20.9572,
+      "eval_samples_per_second": 25.433,
+      "eval_steps_per_second": 12.74,
+      "step": 40
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 1.6303040981292725,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8151,
+      "step": 45
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 1.13103449344635,
+      "learning_rate": 0.0,
+      "loss": 1.8428,
+      "step": 50
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "eval_loss": 1.9145872592926025,
+      "eval_runtime": 20.8724,
+      "eval_samples_per_second": 25.536,
+      "eval_steps_per_second": 12.792,
+      "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