Training in progress, step 10240, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04079bfefeee402afc5a90d5c17f6f80721f862aaa72a88da6fe8812bbc9936a
+oid sha256:29f4d92da286543c9bdb8ad539649d6985177e4b3c3961cba55582df3b0df187
 size 3246333568

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14807f80ce3bbc41ea4a5a0a8585f9f94fdf7d942abd7afa637ea124d5cb75fe
+oid sha256:27d09ec44e8186d29aaaccf802b9b06f8694f3099ca7a5d0e4d4230346284452
 size 6220672307

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb732be4c200b0b68d66033f545d69b981d9d12cd9b1fae529a2b5f11bc8689a
+oid sha256:7b60dc5f90831a3cb044b4ac92382bb3956ae1e5aaac38365110e8ca62c577d1
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d01bd9a4022a13f67fdd7d636c82f1f80d3271c4bc9442507442a46e90b7e21a
+oid sha256:7894a9112e4a5e884676aae0344ab1825a867cb653f81b5c319da7c319adf295
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 8431.3798828125,
-  "best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-7680",
-  "epoch": 0.5674335269724873,
+  "best_metric": 8206.45703125,
+  "best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-10240",
+  "epoch": 0.7565780359633163,
   "eval_steps": 512,
-  "global_step": 7680,
+  "global_step": 10240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,106 @@
       "eval_samples_per_second": 65.427,
       "eval_steps_per_second": 65.427,
       "step": 7680
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.136249445840107e-05,
+      "loss": 9255.4785,
+      "step": 7936
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.947096202157529e-05,
+      "loss": 9076.7949,
+      "step": 8192
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 8366.28515625,
+      "eval_runtime": 54.9213,
+      "eval_samples_per_second": 61.87,
+      "eval_steps_per_second": 61.87,
+      "step": 8192
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.757942958474952e-05,
+      "loss": 9096.5859,
+      "step": 8448
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.5687897147923746e-05,
+      "loss": 9114.2637,
+      "step": 8704
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 8331.78125,
+      "eval_runtime": 52.2996,
+      "eval_samples_per_second": 64.972,
+      "eval_steps_per_second": 64.972,
+      "step": 8704
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.379636471109798e-05,
+      "loss": 9127.2627,
+      "step": 8960
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.19048322742722e-05,
+      "loss": 9108.6582,
+      "step": 9216
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 8280.7763671875,
+      "eval_runtime": 52.2791,
+      "eval_samples_per_second": 64.997,
+      "eval_steps_per_second": 64.997,
+      "step": 9216
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.0013299837446435e-05,
+      "loss": 9030.9062,
+      "step": 9472
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.8121767400620657e-05,
+      "loss": 9014.1484,
+      "step": 9728
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 8238.181640625,
+      "eval_runtime": 52.4655,
+      "eval_samples_per_second": 64.766,
+      "eval_steps_per_second": 64.766,
+      "step": 9728
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.6230234963794885e-05,
+      "loss": 8962.5713,
+      "step": 9984
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.4338702526969114e-05,
+      "loss": 8950.7715,
+      "step": 10240
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 8206.45703125,
+      "eval_runtime": 52.6843,
+      "eval_samples_per_second": 64.497,
+      "eval_steps_per_second": 64.497,
+      "step": 10240
     }
   ],
   "logging_steps": 256,