Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f00e2414db0d2f598e9262fe4dd94cc37c3ec78db2eee4606eb366cbb7e0bfd
+oid sha256:08d356d8ec239ba348a594f95ec7e5b568b1dea395247899cf772e568f5ee55e
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82eb6fcfaaf00d5a513fdd9943a67b6332a1a15509d4af863321e7914890455
+oid sha256:f96d6d6ee490b4c6545231744b4a326c3f584f77f7f598cd55060f94b04c5a51
 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": 0.022168537729145944,
+  "epoch": 0.028421202216853774,
   "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": 2.626,
       "step": 35
+    },
+    {
+      "epoch": 0.022736961773483017,
+      "grad_norm": 1.1897921562194824,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4745,
+      "step": 40
+    },
+    {
+      "epoch": 0.022736961773483017,
+      "eval_loss": 2.5388574600219727,
+      "eval_runtime": 23.4466,
+      "eval_samples_per_second": 31.604,
+      "eval_steps_per_second": 15.823,
+      "step": 40
+    },
+    {
+      "epoch": 0.025579081995168396,
+      "grad_norm": 1.4539854526519775,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.5339,
+      "step": 45
+    },
+    {
+      "epoch": 0.028421202216853774,
+      "grad_norm": 1.9134925603866577,
+      "learning_rate": 0.0,
+      "loss": 2.4908,
+      "step": 50
+    },
+    {
+      "epoch": 0.028421202216853774,
+      "eval_loss": 2.535639524459839,
+      "eval_runtime": 23.4513,
+      "eval_samples_per_second": 31.597,
+      "eval_steps_per_second": 15.82,
+      "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