Training in progress, step 7680, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869b484e58461f1536cc21d599303cb514c3d752e29ef44231f6d6c363605817
+oid sha256:4ca37dad208975487ae890dd2447d9fd111a4d500fddec1a394f9efeef88557e
 size 4725595416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a089b06ff32225e1d8e28e6b6c1cab9f01e70af7cbc2eac64ef56b2989354d
+oid sha256:f0b8169b03af949ee4c5ddf91eed20622e053b6dde7d912b4c3311f20f6495a7
 size 9179193343

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1239486b7f83e4a2231cde24a50b503b22ee79d6ee232760274da141c18674
+oid sha256:cb732be4c200b0b68d66033f545d69b981d9d12cd9b1fae529a2b5f11bc8689a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce8999a5d1b14a256d594f72ba3d10015736fefa5fd7057a03491428983da78
+oid sha256:7802dd5061761c471fafcb314e7fa5bea1fb541e8e1ce0821e89ee84f8e88b84
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4288.33056640625,
-  "best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-5120",
-  "epoch": 0.37828901798165815,
+  "best_metric": 3752.7509765625,
+  "best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-7680",
+  "epoch": 0.5674335269724873,
   "eval_steps": 512,
-  "global_step": 5120,
+  "global_step": 7680,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,106 @@
       "eval_samples_per_second": 66.616,
       "eval_steps_per_second": 66.616,
       "step": 5120
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.205556376533177e-05,
+      "loss": 5085.8599,
+      "step": 5376
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.167725727796661e-05,
+      "loss": 5071.4478,
+      "step": 5632
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 4449.0048828125,
+      "eval_runtime": 55.4547,
+      "eval_samples_per_second": 61.275,
+      "eval_steps_per_second": 61.275,
+      "step": 5632
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.129895079060146e-05,
+      "loss": 5510.5103,
+      "step": 5888
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.09206443032363e-05,
+      "loss": 5384.3877,
+      "step": 6144
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 7380.9560546875,
+      "eval_runtime": 49.4679,
+      "eval_samples_per_second": 68.691,
+      "eval_steps_per_second": 68.691,
+      "step": 6144
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.054233781587114e-05,
+      "loss": 5411.5742,
+      "step": 6400
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.016403132850599e-05,
+      "loss": 5327.8291,
+      "step": 6656
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 6015.3486328125,
+      "eval_runtime": 49.5302,
+      "eval_samples_per_second": 68.605,
+      "eval_steps_per_second": 68.605,
+      "step": 6656
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.978572484114084e-05,
+      "loss": 5498.8262,
+      "step": 6912
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.940741835377569e-05,
+      "loss": 5376.377,
+      "step": 7168
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 4817.3671875,
+      "eval_runtime": 49.2566,
+      "eval_samples_per_second": 68.986,
+      "eval_steps_per_second": 68.986,
+      "step": 7168
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.902911186641053e-05,
+      "loss": 5066.939,
+      "step": 7424
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.865080537904538e-05,
+      "loss": 4955.6113,
+      "step": 7680
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 3752.7509765625,
+      "eval_runtime": 51.0919,
+      "eval_samples_per_second": 66.508,
+      "eval_steps_per_second": 66.508,
+      "step": 7680
     }
   ],
   "logging_steps": 256,