Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da878284afc2ad077756c318f60ca3a858be95bcfe80c75f6d349843f12ed55
+oid sha256:216e0cd82857e4874f1929d13cc61b7979f425836ee167a1ef0c76583a252fd2
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f498ed63910f7b173ab999cfd6ea66f992fbe595b23ee5511698c60e464eb654
+oid sha256:a53f37cb86ccedaed09ce2b5a7fa135a5144004c1c7e6316f94f1e702fba7047
 size 68874

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": 0.04744958481613286,
+  "epoch": 0.0711743772241993,
   "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": 161.354,
       "eval_steps_per_second": 80.677,
       "step": 20
+    },
+    {
+      "epoch": 0.0498220640569395,
+      "grad_norm": 0.07418444007635117,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.9278,
+      "step": 21
+    },
+    {
+      "epoch": 0.05693950177935943,
+      "grad_norm": 0.03907062113285065,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.9359,
+      "step": 24
+    },
+    {
+      "epoch": 0.05931198102016608,
+      "eval_loss": 11.931854248046875,
+      "eval_runtime": 1.1216,
+      "eval_samples_per_second": 158.697,
+      "eval_steps_per_second": 79.348,
+      "step": 25
+    },
+    {
+      "epoch": 0.06405693950177936,
+      "grad_norm": 0.04348384216427803,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9273,
+      "step": 27
+    },
+    {
+      "epoch": 0.0711743772241993,
+      "grad_norm": 0.0798867717385292,
+      "learning_rate": 0.0,
+      "loss": 11.9306,
+      "step": 30
+    },
+    {
+      "epoch": 0.0711743772241993,
+      "eval_loss": 11.931843757629395,
+      "eval_runtime": 1.1094,
+      "eval_samples_per_second": 160.452,
+      "eval_steps_per_second": 80.226,
+      "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": 7494696960.0,
+  "total_flos": 11242045440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null