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:bdbac562e3e554af70d69e78e77ed35e42d66f0321afb4d7c28f6f2004bdc795
+oid sha256:22cf907d1317b22d8a34cc7e10d3d9e82c7cf2b55ccd181b5161caadd722e0e9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f920e81e926080dea96c5f8f0a4412e74963d5bc39cbcc1fb461251351126f56
+oid sha256:40350cb95ac55a36be20b89c7da443dbcc3e46d04f842e253620c4193311c238
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.143646408839779,
+  "epoch": 0.1841620626151013,
   "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": 3.2775,
       "step": 35
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "grad_norm": 3.0431721210479736,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2642,
+      "step": 40
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "eval_loss": 3.4098873138427734,
+      "eval_runtime": 7.9272,
+      "eval_samples_per_second": 14.507,
+      "eval_steps_per_second": 7.317,
+      "step": 40
+    },
+    {
+      "epoch": 0.16574585635359115,
+      "grad_norm": 3.3123347759246826,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.3549,
+      "step": 45
+    },
+    {
+      "epoch": 0.1841620626151013,
+      "grad_norm": 2.9409520626068115,
+      "learning_rate": 0.0,
+      "loss": 3.2574,
+      "step": 50
+    },
+    {
+      "epoch": 0.1841620626151013,
+      "eval_loss": 3.400886297225952,
+      "eval_runtime": 7.8511,
+      "eval_samples_per_second": 14.648,
+      "eval_steps_per_second": 7.387,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null