Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01aed95f9a41651276b23c2e3d1abdbe8927fd6936688ead0d3f77cea9a8fbb4
+oid sha256:f95dfae199aa47927f1a59accff7fc4e81d8a647d5dbdfb4132701d0b6b7a175
 size 159712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7b9dba2d7caf1a2ce6e770cc7997244c21d6508f3d19721083e7ba2791d410
+oid sha256:de0989224c08496531b791eb1c06ea3e051f8bbec030e8ed045ffaefdeb56844
 size 336202

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0023963575365444525,
+  "epoch": 0.0035945363048166786,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 250.698,
       "eval_steps_per_second": 125.384,
       "step": 20
+    },
+    {
+      "epoch": 0.0025161754133716753,
+      "grad_norm": 0.25965455174446106,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.812,
+      "step": 21
+    },
+    {
+      "epoch": 0.002875629043853343,
+      "grad_norm": 0.24722248315811157,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.8121,
+      "step": 24
+    },
+    {
+      "epoch": 0.0029954469206805653,
+      "eval_loss": 10.813106536865234,
+      "eval_runtime": 14.0562,
+      "eval_samples_per_second": 250.067,
+      "eval_steps_per_second": 125.069,
+      "step": 25
+    },
+    {
+      "epoch": 0.003235082674335011,
+      "grad_norm": 0.2858768105506897,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.8136,
+      "step": 27
+    },
+    {
+      "epoch": 0.0035945363048166786,
+      "grad_norm": 0.37482893466949463,
+      "learning_rate": 0.0,
+      "loss": 10.8134,
+      "step": 30
+    },
+    {
+      "epoch": 0.0035945363048166786,
+      "eval_loss": 10.812426567077637,
+      "eval_runtime": 14.0598,
+      "eval_samples_per_second": 250.004,
+      "eval_steps_per_second": 125.037,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3300371988480.0,
+  "total_flos": 4950557982720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null