Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900980f951baa9f08b3a59450d472d3d8428c1f1cc22b2871c8ff3083906b7fc
+oid sha256:2d28bc1a7a7a244e028fbb3f2bd02d962ebe1b98feb0a8c9c3be428e169e8f4e
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e61e6cfb8d7d4991fbf5c2ae87c0a70b3c353bfb8dea085951b89128c33c4cb
+oid sha256:9788c917ba4b7c2c351debe18a68a77a09f4a8f5c14c0e22d46e5c406cbda31c
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 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": 0.0008461429981666902,
+  "epoch": 0.0010847987155983207,
   "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": 11.9282,
       "step": 35
+    },
+    {
+      "epoch": 0.0008678389724786566,
+      "grad_norm": 0.16440056264400482,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9269,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008678389724786566,
+      "eval_loss": 11.929020881652832,
+      "eval_runtime": 462.5274,
+      "eval_samples_per_second": 41.959,
+      "eval_steps_per_second": 20.98,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009763188440384886,
+      "grad_norm": 0.14115817844867706,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9306,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010847987155983207,
+      "grad_norm": 0.11909572035074234,
+      "learning_rate": 0.0,
+      "loss": 11.9283,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010847987155983207,
+      "eval_loss": 11.928845405578613,
+      "eval_runtime": 463.4681,
+      "eval_samples_per_second": 41.873,
+      "eval_steps_per_second": 20.938,
+      "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": 4912370417664.0,
+  "total_flos": 6320374677504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null