Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790e59fe9066d0dd6221cfe2764f4275cd9c904136ac1745ccc0f3eb48a5ed1b
+oid sha256:ef98c214f894b9eaafffccee543bc517341c21f8e1ef4f0f604fce66bfbf568a
 size 1713050034

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df630dcd81b9b194bc0ac1be2a6a9fef794e8226952b0be6694b2f40bb7e1a82
+oid sha256:6db127c9d8872f32202403ef502f7be45fde5f39392ddf83d1608848d7c11f25
 size 816721594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8693c95f0f09ea2f300c00a9d97d4ecc249e7fd41ef6cc52cb95a982ef985bca
+oid sha256:835fa15d5ee259a20363d49fe5750b05246ede3fc9ea34b413c89a27a2b55d03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:414d81b0296706ee8544c28eaf6013748a0dfc834c3d7fbd1015bc57e89aeb34
+oid sha256:6febcbce2d8b205570d2efa69c454cd179cc521bea99161ff253d852812d61cc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.9128127759322524e-05,
-  "best_model_checkpoint": "ProtChem_ESM2_MolGen_Decoder/checkpoint-19861",
-  "epoch": 4.999937063377179,
+  "best_metric": 5.881577453692444e-05,
+  "best_model_checkpoint": "ProtChem_ESM2_MolGen_Decoder/checkpoint-23833",
+  "epoch": 5.999874126754358,
   "eval_steps": 500,
-  "global_step": 19861,
+  "global_step": 23833,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -320,6 +320,70 @@
       "eval_samples_per_second": 15.24,
       "eval_steps_per_second": 0.952,
       "step": 19861
+    },
+    {
+      "epoch": 5.034929825665555,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 1.071565749483434e-05,
+      "loss": 0.0002,
+      "step": 20000
+    },
+    {
+      "epoch": 5.1608030713071935,
+      "grad_norm": 0.00118255615234375,
+      "learning_rate": 1.0299788946114352e-05,
+      "loss": 0.0001,
+      "step": 20500
+    },
+    {
+      "epoch": 5.286676316948832,
+      "grad_norm": 0.002471923828125,
+      "learning_rate": 9.883400581879077e-06,
+      "loss": 0.0001,
+      "step": 21000
+    },
+    {
+      "epoch": 5.412549562590471,
+      "grad_norm": 0.0062255859375,
+      "learning_rate": 9.467214393832746e-06,
+      "loss": 0.0002,
+      "step": 21500
+    },
+    {
+      "epoch": 5.53842280823211,
+      "grad_norm": 0.00531005859375,
+      "learning_rate": 9.051952023118563e-06,
+      "loss": 0.0001,
+      "step": 22000
+    },
+    {
+      "epoch": 5.664296053873749,
+      "grad_norm": 0.006683349609375,
+      "learning_rate": 8.638333509037537e-06,
+      "loss": 0.0001,
+      "step": 22500
+    },
+    {
+      "epoch": 5.790169299515388,
+      "grad_norm": 0.003631591796875,
+      "learning_rate": 8.227076040544813e-06,
+      "loss": 0.0002,
+      "step": 23000
+    },
+    {
+      "epoch": 5.916042545157027,
+      "grad_norm": 0.0093994140625,
+      "learning_rate": 7.818892712688328e-06,
+      "loss": 0.0001,
+      "step": 23500
+    },
+    {
+      "epoch": 5.999874126754358,
+      "eval_loss": 5.881577453692444e-05,
+      "eval_runtime": 16791.1194,
+      "eval_samples_per_second": 15.239,
+      "eval_steps_per_second": 0.952,
+      "step": 23833
     }
   ],
   "logging_steps": 500,
@@ -348,7 +412,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3336670714136654e+19,
+  "total_flos": 1.6004004856963985e+19,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null