Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b73e5d11b5834ced0f69587f2a75fde8af2ca0b231add975dac8e9592cd4141
+oid sha256:726f1d560af359e7b2df6836f9f371eaba4b7263ff655ba94a33e480bee16453
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebfc7d3e71e4c93147aeff460f92a93a994cb51b2f9626db0552da96d0adb47
+oid sha256:feabb5160bc6a27a5757ab30a314fdec88f354cd29b012eec7fcdf2d95e99b47
 size 75739130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e1db140c1ec6013de96c025259c6523bac475d1e1b27a3b2b004e446c85fc3
+oid sha256:01f2f2f9671a0d8993679216e22d8fd7eacb25068309e3f889f98e617666e158
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1219abde915c9cc7a07aaa50b3f6254d6d84b5343dcbf23c1ac7b3076d8ebb1a
+oid sha256:0b7153c3fc82f3a3ac998a443c5ffefa8487aa2c23d265568bb13e22e83eaa38
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 200,
-  "best_metric": 2.961073637008667,
-  "best_model_checkpoint": "business_qa_flan_t5_xl_rope_LoRA_model/checkpoint-200",
-  "epoch": 0.27669693039342846,
+  "best_global_step": 400,
+  "best_metric": 2.6418941020965576,
+  "best_model_checkpoint": "business_qa_flan_t5_xl_rope_LoRA_model/checkpoint-400",
+  "epoch": 0.5533938607868569,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,42 @@
       "eval_samples_per_second": 2.405,
       "eval_steps_per_second": 0.603,
       "step": 200
+    },
+    {
+      "epoch": 0.34587116299178555,
+      "grad_norm": 1.6946117877960205,
+      "learning_rate": 6.887500000000001e-05,
+      "loss": 3.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.4150453955901427,
+      "grad_norm": 1.938078761100769,
+      "learning_rate": 6.2625e-05,
+      "loss": 2.9921,
+      "step": 300
+    },
+    {
+      "epoch": 0.4842196281884998,
+      "grad_norm": 2.3420886993408203,
+      "learning_rate": 5.6375e-05,
+      "loss": 2.9324,
+      "step": 350
+    },
+    {
+      "epoch": 0.5533938607868569,
+      "grad_norm": 2.5413014888763428,
+      "learning_rate": 5.0125e-05,
+      "loss": 2.8571,
+      "step": 400
+    },
+    {
+      "epoch": 0.5533938607868569,
+      "eval_loss": 2.6418941020965576,
+      "eval_runtime": 531.7902,
+      "eval_samples_per_second": 2.416,
+      "eval_steps_per_second": 0.606,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -63,7 +99,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.74601821077504e+16,
+  "total_flos": 5.49203642155008e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null