Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7298d7dff90c79a18b8d051854838990df2aa7e29c44711504b5abc338a2474c
+oid sha256:c20d8188b86a1a957e3695ff6f0c2ad833070cb07cc51b2264b9dfb62982cde7
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec2d8e54f5e05c470160b6b534cb6d096b0680d893b539c1d3526ad2b42a4a1
+oid sha256:b148d763242297d420ddf6ad2192477ec67505e703912291bb57139e1049c80b
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50f61a9d24412ccb5614996adc0c93b90c6c68062631ebea450b2af34b256f3
+oid sha256:9e9e2753b11a378f439eb55a76dec3311b386900784ab3db90c49c8cceeb20fa
 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": 0.009575104727707959,
+  "epoch": 0.01436265709156194,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 11.763,
       "step": 18
+    },
+    {
+      "epoch": 0.010053859964093357,
+      "grad_norm": 0.03411255031824112,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.7624,
+      "step": 21
+    },
+    {
+      "epoch": 0.011490125673249552,
+      "grad_norm": 0.03235261142253876,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.7629,
+      "step": 24
+    },
+    {
+      "epoch": 0.011490125673249552,
+      "eval_loss": 11.762428283691406,
+      "eval_runtime": 22.1727,
+      "eval_samples_per_second": 39.688,
+      "eval_steps_per_second": 19.844,
+      "step": 24
+    },
+    {
+      "epoch": 0.012926391382405745,
+      "grad_norm": 0.037291403859853745,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.7616,
+      "step": 27
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "grad_norm": 0.041370291262865067,
+      "learning_rate": 0.0,
+      "loss": 11.7615,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2800875601920.0,
+  "total_flos": 4150388391936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null