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:d005406902fd72b39bcfbe102889e1953e95c8c84b53ca99a0b8cc8e245fa252
+oid sha256:84f34ee6baa4a10e57fb185fa3cff9248d5d571a2c34ad5d53c0645a18d6842f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63331fce59cb10ad9d589a90ef80161f922c99b957ae78f04fe0c082624b85d8
+oid sha256:d08f196eb404225919e638004d35996e0050695844dd57d2d73686ae7f43c69c
 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": 0.005314980750229975,
+  "epoch": 0.006814077884910225,
   "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": 12.2151,
       "step": 35
+    },
+    {
+      "epoch": 0.00545126230792818,
+      "grad_norm": 7.0431671142578125,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 12.2395,
+      "step": 40
+    },
+    {
+      "epoch": 0.00545126230792818,
+      "eval_loss": 3.022294282913208,
+      "eval_runtime": 359.7414,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 4.295,
+      "step": 40
+    },
+    {
+      "epoch": 0.006132670096419202,
+      "grad_norm": 4.540308475494385,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.2358,
+      "step": 45
+    },
+    {
+      "epoch": 0.006814077884910225,
+      "grad_norm": 12.071662902832031,
+      "learning_rate": 0.0,
+      "loss": 12.1334,
+      "step": 50
+    },
+    {
+      "epoch": 0.006814077884910225,
+      "eval_loss": 3.0158936977386475,
+      "eval_runtime": 359.7398,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 4.295,
+      "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": 1.3676854464479232e+16,
+  "total_flos": 1.75344288006144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null