Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743d04477815523908b30f625327999b9e967a8921dcfecc9d08bc07ac415f2e
+oid sha256:1d6afd8c88d58dcee55bca5a95d85c13b66d814d8611856e87a33076cf7240aa
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02048682211bb6f2aa2a7405ce6ef6fdbf793163f9b10e2c66dd20ce792a0a86
+oid sha256:685e03bd7e0f63c3822370bf0872adec603b84e1526d8fb0092eb97e3ae03e9e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d6c6954105413e254c1dc776a27dd427206924cc5f1ee48db29b4f18851c42
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 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": 0.032119914346895075,
+  "epoch": 0.06423982869379015,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 11.72,
       "eval_steps_per_second": 5.89,
       "step": 15
+    },
+    {
+      "epoch": 0.03854389721627409,
+      "grad_norm": 5.0306220054626465,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.7838,
+      "step": 18
+    },
+    {
+      "epoch": 0.042826552462526764,
+      "eval_loss": 0.9224191308021545,
+      "eval_runtime": 16.8299,
+      "eval_samples_per_second": 11.705,
+      "eval_steps_per_second": 5.882,
+      "step": 20
+    },
+    {
+      "epoch": 0.044967880085653104,
+      "grad_norm": 4.892726421356201,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.6091,
+      "step": 21
+    },
+    {
+      "epoch": 0.05139186295503212,
+      "grad_norm": 5.650697231292725,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.7052,
+      "step": 24
+    },
+    {
+      "epoch": 0.05353319057815846,
+      "eval_loss": 0.9060010313987732,
+      "eval_runtime": 16.8329,
+      "eval_samples_per_second": 11.703,
+      "eval_steps_per_second": 5.881,
+      "step": 25
+    },
+    {
+      "epoch": 0.057815845824411134,
+      "grad_norm": 5.063366413116455,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.8202,
+      "step": 27
+    },
+    {
+      "epoch": 0.06423982869379015,
+      "grad_norm": 5.16721773147583,
+      "learning_rate": 0.0,
+      "loss": 3.3161,
+      "step": 30
+    },
+    {
+      "epoch": 0.06423982869379015,
+      "eval_loss": 0.9025107622146606,
+      "eval_runtime": 16.8392,
+      "eval_samples_per_second": 11.699,
+      "eval_steps_per_second": 5.879,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5273474260008960.0,
+  "total_flos": 1.054694852001792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null