Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f98446d239f2148fabf94fd2f448bf1352a9a3e2220fa854d364b803177a11e
+oid sha256:f44cf9a04782ca12a7633841fcc19400af4ad8e799dadfabc5c687d59c9f7e81
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303f347e2c76140bac6ddceefd4cf7089c2b6e7db40c0095c78d8c4e8b980a73
+oid sha256:ab033bf63f8fdd78844a192a87b460425533088a497019c24362a419310c70a5
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa173be0daf3b70291aa54f3fc172b70d25960de7e9a07e7f57c5f27ae513c9
+oid sha256:28cb1b5e093b2599d8fa1806646d1f09bc9ce7ac92f9796c6863470342508537
 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": 0.0007838526357044876,
+  "epoch": 0.0011757789535567313,
   "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": 4.1008,
       "step": 18
+    },
+    {
+      "epoch": 0.0008230452674897119,
+      "grad_norm": 0.9149162769317627,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.9544,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009406231628453851,
+      "grad_norm": 0.7564873099327087,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.7779,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009406231628453851,
+      "eval_loss": 3.865104913711548,
+      "eval_runtime": 820.9978,
+      "eval_samples_per_second": 13.087,
+      "eval_steps_per_second": 6.543,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010582010582010583,
+      "grad_norm": 0.8100905418395996,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.7656,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "grad_norm": 0.7570703029632568,
+      "learning_rate": 0.0,
+      "loss": 3.6563,
+      "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": 6990386933268480.0,
+  "total_flos": 1.048558039990272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null