Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e8353f285987537967e91f621c33df281cd46bd0a3e6dffd5c502b194c4323
+oid sha256:2d623fcb7175d09ac35508f3e5a5b9b3c7a7558d609d80833b4f07624cf629ee
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61502500b36fa82f547e9b786537b05017f08d910b93d3b62467e02321f3fb32
+oid sha256:62ef88863de492e69eef8adafb3a25975f2a13a4c04198e12ac6a8f505697b56
 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": 0.002798005524267317,
+  "epoch": 0.0035871865695734835,
   "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": 0.3364,
       "step": 35
+    },
+    {
+      "epoch": 0.0028697492556587867,
+      "grad_norm": 3.595264434814453,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.385,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028697492556587867,
+      "eval_loss": 0.08297457545995712,
+      "eval_runtime": 1126.3993,
+      "eval_samples_per_second": 5.21,
+      "eval_steps_per_second": 2.606,
+      "step": 40
+    },
+    {
+      "epoch": 0.003228467912616135,
+      "grad_norm": 1.4879796504974365,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3122,
+      "step": 45
+    },
+    {
+      "epoch": 0.0035871865695734835,
+      "grad_norm": 1.9949724674224854,
+      "learning_rate": 0.0,
+      "loss": 0.3348,
+      "step": 50
+    },
+    {
+      "epoch": 0.0035871865695734835,
+      "eval_loss": 0.08217484503984451,
+      "eval_runtime": 1119.4208,
+      "eval_samples_per_second": 5.243,
+      "eval_steps_per_second": 2.622,
+      "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": 1.3670840033869824e+16,
+  "total_flos": 1.75267179921408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null