Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0489ff5897762a9cc1b91b0fe04a47b8ba0d140b6c593d02082b5257ba623dbf
+oid sha256:2f24c3cfbb258d2bc717c08ad327df0af70fcc1a91839f617d146fde5842385d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261638ef2ebda5e7a2546c5a55206e5be82575d8e105053c1b5511cdef9ed4e6
+oid sha256:057b5f2a11de48a8e21286097ed5865bed1e9be2cce0353edae1f05693c00c95
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37adb5394c4804269d78dc27188509a76c73da44d7fd278481460ae8f3e8251
+oid sha256:f16b181bbe413099cfca1ccdbe07d5a9a6db31431c5d5e02c8e1ec9e64e7035a
 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": 0.0016437490121700648,
+  "epoch": 0.00210737052842316,
   "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": 2.0867,
       "step": 35
+    },
+    {
+      "epoch": 0.001685896422738528,
+      "grad_norm": 2.9631552696228027,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8087,
+      "step": 40
+    },
+    {
+      "epoch": 0.001685896422738528,
+      "eval_loss": 0.5086004734039307,
+      "eval_runtime": 1133.9336,
+      "eval_samples_per_second": 8.81,
+      "eval_steps_per_second": 4.405,
+      "step": 40
+    },
+    {
+      "epoch": 0.001896633475580844,
+      "grad_norm": 3.090548038482666,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2553,
+      "step": 45
+    },
+    {
+      "epoch": 0.00210737052842316,
+      "grad_norm": 3.1793596744537354,
+      "learning_rate": 0.0,
+      "loss": 1.9481,
+      "step": 50
+    },
+    {
+      "epoch": 0.00210737052842316,
+      "eval_loss": 0.5075772404670715,
+      "eval_runtime": 1131.3867,
+      "eval_samples_per_second": 8.83,
+      "eval_steps_per_second": 4.415,
+      "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": 1.3407923862503424e+16,
+  "total_flos": 1.708853041299456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null