Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87ff750b2563de1bed372f2f1a7ffb3464ec8b47477794ea58dc54ffeec26d43
+oid sha256:0787505b5d986f5d33fd3da0de2c720848ea3a0e11bc168219adc886f5c312c6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c88801ed1af63c84d48cc7e4e85d7f05d36ff61f06a69171ea25c537fc8b47e
+oid sha256:90dd56ccd9657e8b01b012900d179c2c883064db2f0c3fec56c6de8e2e95742a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.0014875702066387587,
+  "epoch": 0.0019071412905625113,
   "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": 1.4156,
       "step": 35
+    },
+    {
+      "epoch": 0.001525713032450009,
+      "grad_norm": 2.802304983139038,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4285,
+      "step": 40
+    },
+    {
+      "epoch": 0.001525713032450009,
+      "eval_loss": 0.33043166995048523,
+      "eval_runtime": 2022.564,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 2.729,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017164271615062602,
+      "grad_norm": 2.6940152645111084,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3441,
+      "step": 45
+    },
+    {
+      "epoch": 0.0019071412905625113,
+      "grad_norm": 2.4607455730438232,
+      "learning_rate": 0.0,
+      "loss": 1.2691,
+      "step": 50
+    },
+    {
+      "epoch": 0.0019071412905625113,
+      "eval_loss": 0.32941845059394836,
+      "eval_runtime": 2023.4915,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 2.728,
+      "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": 1.3670824330395648e+16,
+  "total_flos": 1.75266978594816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null