Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7381c11af32f450ef90a1f41be45370df688105c59000f73049a6f3d855bf5bf
+oid sha256:e61b427c7e90098665041fc0a0a842c2a81a5d94700dec207f9f18e8fa3e68fe
 size 442668636

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa5f76c2cf56d06474142e07bd2538df2e0f93a495907116066ebde69a2488c
+oid sha256:af3007c1d17883475830f0951448eb8859176b25fee74d22b9b7c1cb61d5b54a
 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": 5.645811716715495,
   "best_model_checkpoint": "./results/checkpoint-2748",
-  "epoch": 3.0,
+  "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": 269.899,
       "eval_steps_per_second": 8.435,
       "step": 2748
+    },
+    {
+      "epoch": 3.056768558951965,
+      "grad_norm": 31.40544319152832,
+      "learning_rate": 1.8537117903930135e-05,
+      "loss": 5.4937,
+      "step": 2800
+    },
+    {
+      "epoch": 3.165938864628821,
+      "grad_norm": 28.67197608947754,
+      "learning_rate": 1.8127729257641922e-05,
+      "loss": 5.5573,
+      "step": 2900
+    },
+    {
+      "epoch": 3.2751091703056767,
+      "grad_norm": 26.671180725097656,
+      "learning_rate": 1.7718340611353713e-05,
+      "loss": 5.6147,
+      "step": 3000
+    },
+    {
+      "epoch": 3.3842794759825328,
+      "grad_norm": 32.73609924316406,
+      "learning_rate": 1.7308951965065504e-05,
+      "loss": 5.2704,
+      "step": 3100
+    },
+    {
+      "epoch": 3.493449781659389,
+      "grad_norm": 26.268295288085938,
+      "learning_rate": 1.689956331877729e-05,
+      "loss": 5.4946,
+      "step": 3200
+    },
+    {
+      "epoch": 3.6026200873362444,
+      "grad_norm": 24.3873233795166,
+      "learning_rate": 1.649017467248908e-05,
+      "loss": 5.5757,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7117903930131004,
+      "grad_norm": 26.872316360473633,
+      "learning_rate": 1.6080786026200872e-05,
+      "loss": 5.3305,
+      "step": 3400
+    },
+    {
+      "epoch": 3.8209606986899565,
+      "grad_norm": 31.78321647644043,
+      "learning_rate": 1.5671397379912666e-05,
+      "loss": 5.4091,
+      "step": 3500
+    },
+    {
+      "epoch": 3.930131004366812,
+      "grad_norm": 37.95060729980469,
+      "learning_rate": 1.5262008733624454e-05,
+      "loss": 5.464,
+      "step": 3600
+    },
+    {
+      "epoch": 4.0,
+      "eval_avg_mae": 5.841625213623047,
+      "eval_loss": 5.841624736785889,
+      "eval_mae_lex": 5.572142124176025,
+      "eval_mae_sem": 3.7872631549835205,
+      "eval_mae_syn": 8.1654691696167,
+      "eval_runtime": 27.1382,
+      "eval_samples_per_second": 269.988,
+      "eval_steps_per_second": 8.438,
+      "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