Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d72601fdc47120ba0a21293f05401c2170be5aa798f5ca14b8d005344bb112c
+oid sha256:b0ee3a9be2d50ffa903d2e4d505adb537b56e1c187abd8552e55749c02ef37dd
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1de62ab6fa9fade0448e6875150898ca9b81788053a9bdd6f2357010272a583
+oid sha256:1057f842b9784a8946497d47be13c954e955b552489cbd19d264a4185327a4a0
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d353d97d0b63c56a83db8404c27f273e2a2788441660a22b36acdc00febe2be4
+oid sha256:595709725f88363b1f4e17efd777f47bde496ce3d0078340b033985d508b4094
 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": 0.018105849582172703,
+  "epoch": 0.02321262766945218,
   "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": 12.8901,
       "step": 35
+    },
+    {
+      "epoch": 0.018570102135561744,
+      "grad_norm": 110.787841796875,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.8677,
+      "step": 40
+    },
+    {
+      "epoch": 0.018570102135561744,
+      "eval_loss": 3.076159954071045,
+      "eval_runtime": 18.4863,
+      "eval_samples_per_second": 49.063,
+      "eval_steps_per_second": 24.559,
+      "step": 40
+    },
+    {
+      "epoch": 0.020891364902506964,
+      "grad_norm": 124.56420135498047,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.2453,
+      "step": 45
+    },
+    {
+      "epoch": 0.02321262766945218,
+      "grad_norm": 124.69161224365234,
+      "learning_rate": 0.0,
+      "loss": 12.4255,
+      "step": 50
+    },
+    {
+      "epoch": 0.02321262766945218,
+      "eval_loss": 3.0605356693267822,
+      "eval_runtime": 18.4891,
+      "eval_samples_per_second": 49.056,
+      "eval_steps_per_second": 24.555,
+      "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": 344334620688384.0,
+  "total_flos": 440836043046912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null