Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef98c214f894b9eaafffccee543bc517341c21f8e1ef4f0f604fce66bfbf568a
+oid sha256:05e08a45a8e1e8463c665d73017436f00270720c497acfb7a0535baa450f73dd
 size 1713050034

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db127c9d8872f32202403ef502f7be45fde5f39392ddf83d1608848d7c11f25
+oid sha256:c55c9dc56f6e2653e64cf4db13ceadf1c6809893935ce0a254a6e7de08da890b
 size 816721594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835fa15d5ee259a20363d49fe5750b05246ede3fc9ea34b413c89a27a2b55d03
+oid sha256:c14fce3758035959f898e70de7d19b424b0d86c00829dca095608b26db539dc5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6febcbce2d8b205570d2efa69c454cd179cc521bea99161ff253d852812d61cc
+oid sha256:eaf6d6998ff06033b88dda03e29bde638bd304679f095d182d159c9ab8d60af9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.881577453692444e-05,
-  "best_model_checkpoint": "ProtChem_ESM2_MolGen_Decoder/checkpoint-23833",
-  "epoch": 5.999874126754358,
+  "best_metric": 5.877429066458717e-05,
+  "best_model_checkpoint": "ProtChem_ESM2_MolGen_Decoder/checkpoint-27805",
+  "epoch": 6.999811190131537,
   "eval_steps": 500,
-  "global_step": 23833,
+  "global_step": 27805,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -384,6 +384,70 @@
       "eval_samples_per_second": 15.239,
       "eval_steps_per_second": 0.952,
       "step": 23833
+    },
+    {
+      "epoch": 6.041915790798666,
+      "grad_norm": 0.008056640625,
+      "learning_rate": 7.4144912901460355e-06,
+      "loss": 0.0001,
+      "step": 24000
+    },
+    {
+      "epoch": 6.167789036440305,
+      "grad_norm": 0.0050048828125,
+      "learning_rate": 7.014572980005667e-06,
+      "loss": 0.0001,
+      "step": 24500
+    },
+    {
+      "epoch": 6.293662282081944,
+      "grad_norm": 0.0023956298828125,
+      "learning_rate": 6.619831215914974e-06,
+      "loss": 0.0001,
+      "step": 25000
+    },
+    {
+      "epoch": 6.419535527723582,
+      "grad_norm": 0.00182342529296875,
+      "learning_rate": 6.230950455710592e-06,
+      "loss": 0.0001,
+      "step": 25500
+    },
+    {
+      "epoch": 6.545408773365221,
+      "grad_norm": 0.00457763671875,
+      "learning_rate": 5.848604994610434e-06,
+      "loss": 0.0002,
+      "step": 26000
+    },
+    {
+      "epoch": 6.67128201900686,
+      "grad_norm": 0.002960205078125,
+      "learning_rate": 5.4734577960274515e-06,
+      "loss": 0.0001,
+      "step": 26500
+    },
+    {
+      "epoch": 6.797155264648499,
+      "grad_norm": 0.0128173828125,
+      "learning_rate": 5.106159342032e-06,
+      "loss": 0.0001,
+      "step": 27000
+    },
+    {
+      "epoch": 6.923028510290138,
+      "grad_norm": 0.0020294189453125,
+      "learning_rate": 4.747346505456123e-06,
+      "loss": 0.0001,
+      "step": 27500
+    },
+    {
+      "epoch": 6.999811190131537,
+      "eval_loss": 5.877429066458717e-05,
+      "eval_runtime": 16781.6197,
+      "eval_samples_per_second": 15.248,
+      "eval_steps_per_second": 0.953,
+      "step": 27805
     }
   ],
   "logging_steps": 500,
@@ -412,7 +476,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6004004856963985e+19,
+  "total_flos": 1.8671338999791317e+19,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null