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:cdebd41089879f1f27e98e727b4d2cddd4377c577681e6df1aed9f2bcd6ded50
+oid sha256:48355b8970ec6ec4a11cfd85a2193b272fefb5d619eb7f880564f722df381cda
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1cef82ede0b60db11fda0e7fcd43fa39c2d3fda1ac78533fe749fbd3a0850ed
+oid sha256:2808793b39736d5d4ff8b37aa5bbfda6e5c03519be164383454b56ed50354db5
 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": 0.007355714824594493,
+  "epoch": 0.00943040362127499,
   "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": 2.3534,
       "step": 35
+    },
+    {
+      "epoch": 0.007544322897019992,
+      "grad_norm": 10.71760082244873,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1448,
+      "step": 40
+    },
+    {
+      "epoch": 0.007544322897019992,
+      "eval_loss": 0.546802818775177,
+      "eval_runtime": 143.9082,
+      "eval_samples_per_second": 15.517,
+      "eval_steps_per_second": 7.762,
+      "step": 40
+    },
+    {
+      "epoch": 0.008487363259147491,
+      "grad_norm": 12.253548622131348,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.272,
+      "step": 45
+    },
+    {
+      "epoch": 0.00943040362127499,
+      "grad_norm": 9.606593132019043,
+      "learning_rate": 0.0,
+      "loss": 2.2752,
+      "step": 50
+    },
+    {
+      "epoch": 0.00943040362127499,
+      "eval_loss": 0.5441392660140991,
+      "eval_runtime": 143.218,
+      "eval_samples_per_second": 15.592,
+      "eval_steps_per_second": 7.799,
+      "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": 6835420016934912.0,
+  "total_flos": 8763358996070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null