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:efd90786665523d72aefb271173ee68d7ea5459b736c54499305aa5ad94aae92
+oid sha256:53022424ca2d4b1acd85585dcec0de66bfea88cc27ab2f28a0eded4c4b70bfeb
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee9db7a9a3bdf7463740109e586e2ed610ae0ba7831cb0bd42f320d3f1317c7
+oid sha256:3a2ad79265609ce5d047962fb7b8d755eba74368e87b59e8cd1b3f484d48e09f
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
+oid sha256:d6a9101315bed33e0f3a0fc84fd93cd1f88e425b915b76ec585cd3942cf27abe
 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": 0.10612244897959183,
+  "epoch": 0.1360544217687075,
   "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": 1.1499,
       "step": 35
+    },
+    {
+      "epoch": 0.10884353741496598,
+      "grad_norm": 5.287220001220703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0057,
+      "step": 40
+    },
+    {
+      "epoch": 0.10884353741496598,
+      "eval_loss": 0.746000349521637,
+      "eval_runtime": 5.032,
+      "eval_samples_per_second": 30.803,
+      "eval_steps_per_second": 15.501,
+      "step": 40
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 5.556825637817383,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6817,
+      "step": 45
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 5.234228610992432,
+      "learning_rate": 0.0,
+      "loss": 0.6707,
+      "step": 50
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "eval_loss": 0.6608397364616394,
+      "eval_runtime": 4.8185,
+      "eval_samples_per_second": 32.168,
+      "eval_steps_per_second": 16.188,
+      "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": 997588715175936.0,
+  "total_flos": 1278959891251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null