Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f360b7ad4ad730f4fa9bce7f2ea631339233584bd74af6ad41791d4820f21ebe
+oid sha256:cc4c14887bb898e6d51d45159a3d5afa90eb8abbf7272fffea1eb7946c015094
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24df988401d0e0304f7e1f2ae193afe449ecc27c6eb3f375636d948253ea8f74
+oid sha256:ee3cdd4a54c4c48e32e09390aff9d77afc48773b4802a112008575762c7dea51
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e9e7b978e914c84d386479aa37cc1d7c932c264297fa6273686f760143c92a
+oid sha256:477b8bdb96ef0a719a9f207ca69a3d5d20ccc9cc1f6ae115b891fb65634fc1ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015902230729588455,
+  "epoch": 0.0185526025178532,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 14.359,
       "eval_steps_per_second": 1.795,
       "step": 54
+    },
+    {
+      "epoch": 0.01678568799234337,
+      "grad_norm": 7.015294075012207,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 3.6007,
+      "step": 57
+    },
+    {
+      "epoch": 0.017669145255098283,
+      "grad_norm": 8.451822280883789,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 3.2948,
+      "step": 60
+    },
+    {
+      "epoch": 0.0185526025178532,
+      "grad_norm": 7.4288129806518555,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 3.4584,
+      "step": 63
+    },
+    {
+      "epoch": 0.0185526025178532,
+      "eval_loss": 0.872480034828186,
+      "eval_runtime": 398.1418,
+      "eval_samples_per_second": 14.367,
+      "eval_steps_per_second": 1.796,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.597138352327885e+16,
+  "total_flos": 8.863328077715866e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null