Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6234f5efc5ea6f5a1aa300038b653bc90a90839fad776df954505ea542b953bf
+oid sha256:c9928f50443ed2c08961e4e8e38e16fcd28e5c0cbc43b330ef03aa9b2f49354b
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ef418c672ecf4e36954c9b82d8a10f705390599f6543e53b7532a0c1332d38
+oid sha256:27f16be20c5d77768f1f956748b2bd2a3003732d0a06ba86d54f59e4391830bb
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef679fab5fb3c676adcc7a412c8bf7d1e59930c83568ce20eee25fb1d0fb261
+oid sha256:95bf25a1864e543025fa7571f8882d89e42d46cc5f050b8d82f150a0921cfdbb
 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": 0.07366482504604052,
+  "epoch": 0.11049723756906077,
   "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": 178.228,
       "eval_steps_per_second": 89.889,
       "step": 20
+    },
+    {
+      "epoch": 0.07734806629834254,
+      "grad_norm": 3.160904884338379,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 43.7432,
+      "step": 21
+    },
+    {
+      "epoch": 0.08839779005524862,
+      "grad_norm": 3.4026870727539062,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 43.6194,
+      "step": 24
+    },
+    {
+      "epoch": 0.09208103130755065,
+      "eval_loss": 10.881987571716309,
+      "eval_runtime": 0.628,
+      "eval_samples_per_second": 183.133,
+      "eval_steps_per_second": 92.363,
+      "step": 25
+    },
+    {
+      "epoch": 0.09944751381215469,
+      "grad_norm": 3.349900960922241,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 43.5332,
+      "step": 27
+    },
+    {
+      "epoch": 0.11049723756906077,
+      "grad_norm": 3.4591774940490723,
+      "learning_rate": 0.0,
+      "loss": 43.4943,
+      "step": 30
+    },
+    {
+      "epoch": 0.11049723756906077,
+      "eval_loss": 10.875011444091797,
+      "eval_runtime": 0.6499,
+      "eval_samples_per_second": 176.948,
+      "eval_steps_per_second": 89.243,
+      "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": 436790624256.0,
+  "total_flos": 649986048000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null