Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130950f360a9e942ee6a8b4310fad71365e1be9d621b33fd2f16fb386f7ea17b
+oid sha256:aa26ff05bda1719f9abd6280e0febb8e1ede3e6b9885ac5c1a10008246ba71b8
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b940b0b011e2762b2101692c3cee5ec92e99db8e0d85938c64e4e0a86c4a08
+oid sha256:a3a3a5a90f430ff5a5097cfeb9f457ae2acedd8b62c25e2f0f06f1e1b93e6bd5
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8aca9166042fe2d6b7a9a9b4e76e763c0ff0628b7a16964c79fd2c39b80bd6
+oid sha256:e244b8eda6a0d4d8057ecdc7783a5d4d58a80de41ac82670c0ed1b7472d9e441
 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": 0.08438818565400844,
+  "epoch": 0.12658227848101267,
   "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": 2.0681,
       "step": 18
+    },
+    {
+      "epoch": 0.08860759493670886,
+      "grad_norm": 1.367913842201233,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9835,
+      "step": 21
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 1.8404457569122314,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.054,
+      "step": 24
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "eval_loss": 2.070768356323242,
+      "eval_runtime": 7.3523,
+      "eval_samples_per_second": 13.601,
+      "eval_steps_per_second": 6.801,
+      "step": 24
+    },
+    {
+      "epoch": 0.11392405063291139,
+      "grad_norm": 1.479858160018921,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.9064,
+      "step": 27
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "grad_norm": 1.1995352506637573,
+      "learning_rate": 0.0,
+      "loss": 1.9765,
+      "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": 2010596581048320.0,
+  "total_flos": 3015894871572480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null