Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f41d5c06d50086b5efe497741cd95cc7fc3c8de2e46e381549867da187d3556
+oid sha256:b9477f1fcec80e81867c80bf1609d9f1f864229be57f2a41525057208f7277c1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfbcaca367e773fd8b91cbeeafd871a746710966e24a6f7b0f9a669e39f9daa5
+oid sha256:a61b632e9a8de1a527d7944d601f74ce5fc7e6e0eeda3a46ce639e07d2edac67
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4325384574b557ba2e4faf25095f3b9b60df77b957aa84188dda4d6420c950
+oid sha256:0488189f0906e870cc7f3b99981823d2012134691e1603db85b956f58ad4bd38
 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": 0.0025356370788160525,
+  "epoch": 0.0032508167677128877,
   "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": 2.1988,
       "step": 35
+    },
+    {
+      "epoch": 0.00260065341417031,
+      "grad_norm": 1.474457025527954,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0655,
+      "step": 40
+    },
+    {
+      "epoch": 0.00260065341417031,
+      "eval_loss": 2.1556448936462402,
+      "eval_runtime": 999.6273,
+      "eval_samples_per_second": 6.479,
+      "eval_steps_per_second": 3.24,
+      "step": 40
+    },
+    {
+      "epoch": 0.002925735090941599,
+      "grad_norm": 1.442267894744873,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0189,
+      "step": 45
+    },
+    {
+      "epoch": 0.0032508167677128877,
+      "grad_norm": 1.5506565570831299,
+      "learning_rate": 0.0,
+      "loss": 2.2706,
+      "step": 50
+    },
+    {
+      "epoch": 0.0032508167677128877,
+      "eval_loss": 2.1504440307617188,
+      "eval_runtime": 1001.5404,
+      "eval_samples_per_second": 6.467,
+      "eval_steps_per_second": 3.234,
+      "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": 1.2570206329110528e+16,
+  "total_flos": 1.6144088520720384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null