Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f852409632712ec242e524935d0f5fbbb7e6bc6de9599f5e4da3a2112671903
+oid sha256:3e6247673fbb13d32a81bff2d80b19b59edad902a4e88a7e900df9794a39b0da
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e9b6b5cb818666d5425cfba4602a6753c3da850bc7ec0c164a59734afe5933
+oid sha256:30e35d30aaa973be10cf314a0ba1b99916d0547fe6ca30fd780a200110e9cb2c
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2c364aa9ec073a1ed19f54580deb42614eacbe993e51f4be34783f86e19118
+oid sha256:d60207f033c3688522020da43c4c7c18a66d95617d4c8a64c7cbf2e7ecb93ac9
 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": 0.6146341463414634,
+  "epoch": 0.7024390243902439,
   "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": 35.46,
       "eval_steps_per_second": 4.509,
       "step": 63
+    },
+    {
+      "epoch": 0.6439024390243903,
+      "grad_norm": 0.24308180809020996,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 2.6941,
+      "step": 66
+    },
+    {
+      "epoch": 0.6731707317073171,
+      "grad_norm": 0.22699187695980072,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 3.0174,
+      "step": 69
+    },
+    {
+      "epoch": 0.7024390243902439,
+      "grad_norm": 0.20896831154823303,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 2.8152,
+      "step": 72
+    },
+    {
+      "epoch": 0.7024390243902439,
+      "eval_loss": 2.84454083442688,
+      "eval_runtime": 4.8793,
+      "eval_samples_per_second": 35.456,
+      "eval_steps_per_second": 4.509,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1455765885681664e+16,
+  "total_flos": 2.449800134708429e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null