Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21780b42c596a15f5a5de38e67cb7166bacc5441b900679cc9a865217d3f8a58
+oid sha256:912107a1fb7aee555dc6450252562471041dc70268673f8e2107b79dd71c7169
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1a7299cfdebe3ccd4699adb5dd19a5640a76910ae61dc5333cf09d735ae1a8
+oid sha256:4fb061fb6da529ae5d104a14f5758cb757e10fe0fbe0e61206e6c9589f10ec92
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7ff02a3ba65bc0f4396d37fe9891ed66a876a0ae373a7997caad06f687d13c
+oid sha256:a2ad84d94a2796a1a93d56347de938179df5891b007749857b1d75a23b92ed7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012332145793368046,
+  "epoch": 0.02466429158673609,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0002,
       "loss": 0.9082,
       "step": 15
+    },
+    {
+      "epoch": 0.013154288846259249,
+      "eval_loss": 0.9790562987327576,
+      "eval_runtime": 37.6183,
+      "eval_samples_per_second": 10.234,
+      "eval_steps_per_second": 5.13,
+      "step": 16
+    },
+    {
+      "epoch": 0.014798574952041656,
+      "grad_norm": 0.850883960723877,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0487,
+      "step": 18
+    },
+    {
+      "epoch": 0.017265004110715264,
+      "grad_norm": 1.029070258140564,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7977,
+      "step": 21
+    },
+    {
+      "epoch": 0.019731433269388872,
+      "grad_norm": 0.9382264614105225,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0269,
+      "step": 24
+    },
+    {
+      "epoch": 0.019731433269388872,
+      "eval_loss": 0.8650409579277039,
+      "eval_runtime": 37.6256,
+      "eval_samples_per_second": 10.232,
+      "eval_steps_per_second": 5.129,
+      "step": 24
+    },
+    {
+      "epoch": 0.022197862428062484,
+      "grad_norm": 0.9006747007369995,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9504,
+      "step": 27
+    },
+    {
+      "epoch": 0.02466429158673609,
+      "grad_norm": 2.2493369579315186,
+      "learning_rate": 0.0,
+      "loss": 0.9416,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5193210984923136.0,
+  "total_flos": 1.020095014895616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null