Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bea6feba4d2c450b3e5d39292a5e79b94fbfbe5c0d2238544a602d9ef40e433
+oid sha256:b0a4307d5a6957ee61f4b43285037f94ffe5233b5b369156f4a6932cffa000aa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea0aee52ae6fd4cf146bc568dc395b124069f8a2d6d7b304bf6a7a696a46c99
+oid sha256:a23976df9c34d1cbf25fb531e3cbd791275afa94d0bd341dceb59c8e1c9f3f7d
 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": 0.9839,
       "step": 35
+    },
+    {
+      "epoch": 0.0028697492556587867,
+      "grad_norm": 2.7434425354003906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9432,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028697492556587867,
+      "eval_loss": 0.24171976745128632,
+      "eval_runtime": 696.2566,
+      "eval_samples_per_second": 8.429,
+      "eval_steps_per_second": 4.215,
+      "step": 40
+    },
+    {
+      "epoch": 0.003228467912616135,
+      "grad_norm": 3.149109363555908,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9522,
+      "step": 45
+    },
+    {
+      "epoch": 0.0035871865695734835,
+      "grad_norm": 5.350485801696777,
+      "learning_rate": 0.0,
+      "loss": 1.016,
+      "step": 50
+    },
+    {
+      "epoch": 0.0035871865695734835,
+      "eval_loss": 0.23809517920017242,
+      "eval_runtime": 696.328,
+      "eval_samples_per_second": 8.428,
+      "eval_steps_per_second": 4.215,
+      "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