Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87059de773a647f0f146c9c6d0b08d5535f799d9fa1c34e6aec16f5407fc67c
+oid sha256:bf0c8d4acae67ad3b83cbd4e674eafe4b5a6c8d746be9c99d1ef727781796bb5
 size 442668636

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7994e3322be09b5f88a7dbc2a5814c66fcb49eac3f6f61e2db6e5b2dd3f344e8
+oid sha256:41230f95650a3fed4682e423dc55159f44a49adabeba81e64b3b775c35abfd0c
 size 885457146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473ecb09e5f106de8046a76cc9b1107489610a4ca8d22c8acd37629ea6ee333c
+oid sha256:8ff6cc6d0cbab2c0d1b846e878224dd13dea331cdbd300a43f50d003878abb4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2068a5d955976d9311723e9deb7bf5d0b82ab774ba392808af341e32685de248
+oid sha256:da1c1820d44ac0531e8dbb97bd434cc82c577f59ee0c117b537ddaef94516da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 5.272278467814128,
   "best_model_checkpoint": "./results/checkpoint-5496",
-  "epoch": 6.0,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 5496,
+  "global_step": 6412,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,6 +457,88 @@
       "eval_samples_per_second": 270.548,
       "eval_steps_per_second": 8.456,
       "step": 5496
+    },
+    {
+      "epoch": 6.004366812227074,
+      "grad_norm": 29.006881713867188,
+      "learning_rate": 7.483624454148472e-06,
+      "loss": 4.8767,
+      "step": 5500
+    },
+    {
+      "epoch": 6.11353711790393,
+      "grad_norm": 29.40102195739746,
+      "learning_rate": 7.074235807860262e-06,
+      "loss": 4.6832,
+      "step": 5600
+    },
+    {
+      "epoch": 6.222707423580786,
+      "grad_norm": 32.63214111328125,
+      "learning_rate": 6.664847161572053e-06,
+      "loss": 4.6676,
+      "step": 5700
+    },
+    {
+      "epoch": 6.331877729257642,
+      "grad_norm": 32.83290481567383,
+      "learning_rate": 6.2554585152838425e-06,
+      "loss": 4.6235,
+      "step": 5800
+    },
+    {
+      "epoch": 6.441048034934497,
+      "grad_norm": 36.680030822753906,
+      "learning_rate": 5.846069868995633e-06,
+      "loss": 4.4681,
+      "step": 5900
+    },
+    {
+      "epoch": 6.550218340611353,
+      "grad_norm": 37.740535736083984,
+      "learning_rate": 5.436681222707424e-06,
+      "loss": 4.518,
+      "step": 6000
+    },
+    {
+      "epoch": 6.6593886462882095,
+      "grad_norm": 33.8775749206543,
+      "learning_rate": 5.027292576419214e-06,
+      "loss": 4.6268,
+      "step": 6100
+    },
+    {
+      "epoch": 6.7685589519650655,
+      "grad_norm": 50.033729553222656,
+      "learning_rate": 4.617903930131005e-06,
+      "loss": 4.6026,
+      "step": 6200
+    },
+    {
+      "epoch": 6.877729257641922,
+      "grad_norm": 34.454341888427734,
+      "learning_rate": 4.208515283842795e-06,
+      "loss": 4.618,
+      "step": 6300
+    },
+    {
+      "epoch": 6.986899563318778,
+      "grad_norm": 41.41761779785156,
+      "learning_rate": 3.799126637554585e-06,
+      "loss": 4.6299,
+      "step": 6400
+    },
+    {
+      "epoch": 7.0,
+      "eval_avg_mae": 5.449769337972005,
+      "eval_loss": 5.449769496917725,
+      "eval_mae_lex": 4.877564430236816,
+      "eval_mae_sem": 3.8569977283477783,
+      "eval_mae_syn": 7.614744663238525,
+      "eval_runtime": 27.0562,
+      "eval_samples_per_second": 270.806,
+      "eval_steps_per_second": 8.464,
+      "step": 6412
     }
   ],
   "logging_steps": 100,
@@ -476,7 +558,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1566597400031744e+16,
+  "total_flos": 1.3494363633370368e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null