Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05fb1093959dc6d1c3e60858fbc69e5ace92aa810b221d5d1efca6d4fb8c03a
+oid sha256:a11e77d71a6398bf84076eb67132be2a9b0c0eda7b7ccdc4ced87477e74fd26a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d046a135df80667728bcbc2a9b06c63aaec3edd0b75ac12f26d50df24ef88d84
+oid sha256:8106d5a92cdb9f2ccd687cddd5ad73ed6dab150c4c95eb2b47a28c25749b97ed
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b67bd18c19d450b6e9540356d3dd1899dcc04f35f70c1cdcb528c1e2e8ee989
+oid sha256:3aa10da0a18ea67917350fb6e6f8db87ade3225f86b79930eb7ac553eb290db0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0041360111354145955,
+  "epoch": 0.006204016703121893,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 32.218,
       "eval_steps_per_second": 16.115,
       "step": 26
+    },
+    {
+      "epoch": 0.004772320540862995,
+      "grad_norm": 3.8575828075408936,
+      "learning_rate": 5e-05,
+      "loss": 2.6921,
+      "step": 30
+    },
+    {
+      "epoch": 0.006204016703121893,
+      "eval_loss": 2.445974349975586,
+      "eval_runtime": 82.1313,
+      "eval_samples_per_second": 32.229,
+      "eval_steps_per_second": 16.121,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4808867045179392.0,
+  "total_flos": 7213300567769088.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null