Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0407431add305c44a9c034f733a910207225c308ced08c249fb0b020b8d92fa5
+oid sha256:716bd86ed29a378d1943b0d86806d8b70967f9cb8a0dfb316189f44858f55b93
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1158deeb82825dc9134ec81b873391a0de1dcf5738314d7d0cd60d264dcb3a81
+oid sha256:474c9587089ea1cef0466f948272707507bb2a9d5e97a7e233755d0e3cb771a5
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4e3a63ff432f0070f016a4fba7d15b41ae3139da5c92fc0c7a44016f2d48d3
+oid sha256:ba0750105cea24637f142150154f3509baa6321ca673d9ab5c6ef20532c6ce9a
 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": 0.022190611664295874,
+  "epoch": 0.02844950213371266,
   "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": 1.9256,
       "step": 35
+    },
+    {
+      "epoch": 0.02275960170697013,
+      "grad_norm": 1.7803326845169067,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3078,
+      "step": 40
+    },
+    {
+      "epoch": 0.02275960170697013,
+      "eval_loss": 2.1224875450134277,
+      "eval_runtime": 24.6578,
+      "eval_samples_per_second": 30.011,
+      "eval_steps_per_second": 15.005,
+      "step": 40
+    },
+    {
+      "epoch": 0.025604551920341393,
+      "grad_norm": 1.49332594871521,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8645,
+      "step": 45
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "grad_norm": 1.537865400314331,
+      "learning_rate": 0.0,
+      "loss": 2.118,
+      "step": 50
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "eval_loss": 2.120621681213379,
+      "eval_runtime": 24.5138,
+      "eval_samples_per_second": 30.187,
+      "eval_steps_per_second": 15.094,
+      "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": 362830517501952.0,
+  "total_flos": 462998451781632.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null