Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e654e4d50bd4c08e40f1c40359055b24af92e519f539420a2ae3729b5bff38
+oid sha256:73bbaf13257e8852680c22d11642ea0013f2247fef35d8272beebba796d36512
 size 442668636

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a152b235056b4fcbaeb415b6d13c581c062ea5ef61192c30dcf14433ed941558
+oid sha256:cf26cb804bb88b36cd19298767e57275ff1af51ef66a60b94073c0dcb74bb3c9
 size 885457146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b3b8471ca0351c811d90c5b574a45dac1c24b25ffcf13ec6b85586685c4c47
+oid sha256:049c6f40a328629846cab1b27e3807d44ea469304a69ff0f3d676cc813cde6b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8143cf4c2b0cbae224cb6ee44d414097e32f9582a6067851f3fe7a3ab225aca6
+oid sha256:7668389514d10a3d53f140c85ff46df71dcd9dc34fbc1ed6530f2d1a175df2a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.088820139567058,
-  "best_model_checkpoint": "./results/checkpoint-2748",
-  "epoch": 3.0,
+  "best_metric": 5.853533426920573,
+  "best_model_checkpoint": "./results/checkpoint-3664",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 2748,
+  "global_step": 3664,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,81 @@
       "eval_samples_per_second": 271.974,
       "eval_steps_per_second": 8.5,
       "step": 2748
+    },
+    {
+      "epoch": 3.056768558951965,
+      "grad_norm": 25.13582420349121,
+      "learning_rate": 1.8537117903930135e-05,
+      "loss": 5.5729,
+      "step": 2800
+    },
+    {
+      "epoch": 3.165938864628821,
+      "grad_norm": 26.646804809570312,
+      "learning_rate": 1.8127729257641922e-05,
+      "loss": 5.6211,
+      "step": 2900
+    },
+    {
+      "epoch": 3.2751091703056767,
+      "grad_norm": 28.627378463745117,
+      "learning_rate": 1.7718340611353713e-05,
+      "loss": 5.5775,
+      "step": 3000
+    },
+    {
+      "epoch": 3.3842794759825328,
+      "grad_norm": 28.54901123046875,
+      "learning_rate": 1.7308951965065504e-05,
+      "loss": 5.3086,
+      "step": 3100
+    },
+    {
+      "epoch": 3.493449781659389,
+      "grad_norm": 27.549345016479492,
+      "learning_rate": 1.689956331877729e-05,
+      "loss": 5.5229,
+      "step": 3200
+    },
+    {
+      "epoch": 3.6026200873362444,
+      "grad_norm": 29.306232452392578,
+      "learning_rate": 1.649017467248908e-05,
+      "loss": 5.6348,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7117903930131004,
+      "grad_norm": 29.256425857543945,
+      "learning_rate": 1.6080786026200872e-05,
+      "loss": 5.3936,
+      "step": 3400
+    },
+    {
+      "epoch": 3.8209606986899565,
+      "grad_norm": 31.816057205200195,
+      "learning_rate": 1.5671397379912666e-05,
+      "loss": 5.431,
+      "step": 3500
+    },
+    {
+      "epoch": 3.930131004366812,
+      "grad_norm": 25.876789093017578,
+      "learning_rate": 1.5262008733624454e-05,
+      "loss": 5.4981,
+      "step": 3600
+    },
+    {
+      "epoch": 4.0,
+      "eval_avg_mae": 5.853533426920573,
+      "eval_loss": 5.8535332679748535,
+      "eval_mae_lex": 5.371854305267334,
+      "eval_mae_sem": 3.812947988510132,
+      "eval_mae_syn": 8.375797271728516,
+      "eval_runtime": 26.9386,
+      "eval_samples_per_second": 271.989,
+      "eval_steps_per_second": 8.501,
+      "step": 3664
     }
   ],
   "logging_steps": 100,
@@ -251,7 +326,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5783298700015872.0,
+  "total_flos": 7711064933354496.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null