Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcd672e213b45a4c3cebe115d9eb2de935f3a84ba028dc354c343a3375e7fd7
+oid sha256:1d7b8dac7881c8955e49bf165a9f43d461f09d66c3f8d57b76203f6d6522e661
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e342a1e44d97d3984f76e74fcba74ebbadc76305126cccdd06427118936359
+oid sha256:a6064365fef2bbc24b2b876ac5db776e2cb6ef89777a64de14bc69098528dcb6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee089b8eda3d2f03579660229909140f9bb3bc7af0a9129bb3775da6328a203
+oid sha256:a0479216c8f38ae371ed9c9b3c28ea66f432853117f0b942d3e916e877b23f84
 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": 0.0019685536178482193,
+  "epoch": 0.002523786689548999,
   "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": 2.181,
       "step": 35
+    },
+    {
+      "epoch": 0.0020190293516391994,
+      "grad_norm": 0.3889245092868805,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1946,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020190293516391994,
+      "eval_loss": 2.188227891921997,
+      "eval_runtime": 1060.6208,
+      "eval_samples_per_second": 7.865,
+      "eval_steps_per_second": 3.933,
+      "step": 40
+    },
+    {
+      "epoch": 0.0022714080205940993,
+      "grad_norm": 0.3309444785118103,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1812,
+      "step": 45
+    },
+    {
+      "epoch": 0.002523786689548999,
+      "grad_norm": 0.3746071457862854,
+      "learning_rate": 0.0,
+      "loss": 2.1949,
+      "step": 50
+    },
+    {
+      "epoch": 0.002523786689548999,
+      "eval_loss": 2.1861822605133057,
+      "eval_runtime": 1060.0281,
+      "eval_samples_per_second": 7.87,
+      "eval_steps_per_second": 3.935,
+      "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": 1.3964453276024832e+16,
+  "total_flos": 1.7987325577396224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null