Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9cdc6d6e806f829e185b7e1c91b7daca15d78a8cb474f568e08d774bdc47884
+oid sha256:46ce372cad065e55d174da1e445a8f0ea10b2376323b42a677da77260c7071a6
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:414882d77207fe8f45d43c14f1c95ea691fd5ed34c4290a0b1453ad34016b55b
+oid sha256:10d42d77f8c6a953d5603efdc1935e08c3c040db9ecf4228edd5e673a1368974
 size 66578772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85446ac734307ad4c1e230db7d5d6a8d6dac6e2bec648ba2b41d25022bee9cdf
+oid sha256:f05e2a7fe5f9efc4996d13bce479f8f30cf4261d161f444cb216569e0ff49c89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29132947976878615,
+  "epoch": 0.3329479768786127,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 15.606,
       "eval_steps_per_second": 1.967,
       "step": 63
+    },
+    {
+      "epoch": 0.30520231213872834,
+      "grad_norm": 13.206997871398926,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 8.8766,
+      "step": 66
+    },
+    {
+      "epoch": 0.3190751445086705,
+      "grad_norm": 10.500737190246582,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 7.9143,
+      "step": 69
+    },
+    {
+      "epoch": 0.3329479768786127,
+      "grad_norm": 11.877433776855469,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 8.8372,
+      "step": 72
+    },
+    {
+      "epoch": 0.3329479768786127,
+      "eval_loss": 2.1602916717529297,
+      "eval_runtime": 23.3824,
+      "eval_samples_per_second": 15.61,
+      "eval_steps_per_second": 1.967,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.24790182044631e+16,
+  "total_flos": 9.426173509081498e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null