Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726f1d560af359e7b2df6836f9f371eaba4b7263ff655ba94a33e480bee16453
+oid sha256:1be21ed468e01af6983756e26f22015d1f5801cab0f818bf28403454a69a95f4
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feabb5160bc6a27a5757ab30a314fdec88f354cd29b012eec7fcdf2d95e99b47
+oid sha256:f6acd3f058b34556d890cd08c6abd057bc57a8f3fcadadef66a722c8c6f6d532
 size 75739130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f2f2f9671a0d8993679216e22d8fd7eacb25068309e3f889f98e617666e158
+oid sha256:a0b6f10790bba0f96b0cc2cb9e9d4f04ac87e60f407c5013fc8f3f1738cf5c72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7153c3fc82f3a3ac998a443c5ffefa8487aa2c23d265568bb13e22e83eaa38
+oid sha256:ba96516c7a126eb3ad413f66fd7e0a83cd0c8d8402229e83222c4f7cb6f57202
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 400,
-  "best_metric": 2.6418941020965576,
-  "best_model_checkpoint": "business_qa_flan_t5_xl_rope_LoRA_model/checkpoint-400",
-  "epoch": 0.5533938607868569,
+  "best_global_step": 600,
+  "best_metric": 2.494161605834961,
+  "best_model_checkpoint": "business_qa_flan_t5_xl_rope_LoRA_model/checkpoint-600",
+  "epoch": 0.8300907911802854,
   "eval_steps": 200,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,42 @@
       "eval_samples_per_second": 2.416,
       "eval_steps_per_second": 0.606,
       "step": 400
+    },
+    {
+      "epoch": 0.622568093385214,
+      "grad_norm": 2.8039212226867676,
+      "learning_rate": 4.3875e-05,
+      "loss": 2.7732,
+      "step": 450
+    },
+    {
+      "epoch": 0.6917423259835711,
+      "grad_norm": 2.8921995162963867,
+      "learning_rate": 3.7625e-05,
+      "loss": 2.7173,
+      "step": 500
+    },
+    {
+      "epoch": 0.7609165585819282,
+      "grad_norm": 3.0461184978485107,
+      "learning_rate": 3.1375e-05,
+      "loss": 2.6135,
+      "step": 550
+    },
+    {
+      "epoch": 0.8300907911802854,
+      "grad_norm": 3.964676856994629,
+      "learning_rate": 2.5124999999999997e-05,
+      "loss": 2.6357,
+      "step": 600
+    },
+    {
+      "epoch": 0.8300907911802854,
+      "eval_loss": 2.494161605834961,
+      "eval_runtime": 532.8559,
+      "eval_samples_per_second": 2.412,
+      "eval_steps_per_second": 0.604,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -99,7 +135,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.49203642155008e+16,
+  "total_flos": 8.23805463232512e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null