Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749271874a66a0bb44175c9c4e534fa913565b840fde7339f597ed30a42e479a
+oid sha256:bda5447e852aec1a88c6e1e170b80ba6fe9014a12dbe01e7be648c38a4de3614
 size 442668636

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d3381cb7fd88fdbe7c1cd9bfd41f3e3c8cc97d2b4a55d635f79a83987983bb
+oid sha256:11b2622b740fa4e8b9bde46ad5633bd5f457d760c14266e230077a93270f722d
 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:a4733e7616ec8d677f1ad74de3be0e8ae5883d8beda594b0ecd844ef01ca5ed9
+oid sha256:dbbf9fa8c1d04bf161b93e37605349a2dc1920d1f886b15f60d590d5c06678fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 5.4548899332682295,
   "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": 271.145,
       "eval_steps_per_second": 8.474,
       "step": 5496
+    },
+    {
+      "epoch": 6.004366812227074,
+      "grad_norm": 27.099462509155273,
+      "learning_rate": 2.4945414847161576e-05,
+      "loss": 5.0121,
+      "step": 5500
+    },
+    {
+      "epoch": 6.11353711790393,
+      "grad_norm": 26.199542999267578,
+      "learning_rate": 2.3580786026200875e-05,
+      "loss": 4.6621,
+      "step": 5600
+    },
+    {
+      "epoch": 6.222707423580786,
+      "grad_norm": 31.04909324645996,
+      "learning_rate": 2.2216157205240178e-05,
+      "loss": 4.6792,
+      "step": 5700
+    },
+    {
+      "epoch": 6.331877729257642,
+      "grad_norm": 26.449748992919922,
+      "learning_rate": 2.0851528384279477e-05,
+      "loss": 4.6471,
+      "step": 5800
+    },
+    {
+      "epoch": 6.441048034934497,
+      "grad_norm": 27.806798934936523,
+      "learning_rate": 1.948689956331878e-05,
+      "loss": 4.5161,
+      "step": 5900
+    },
+    {
+      "epoch": 6.550218340611353,
+      "grad_norm": 39.113399505615234,
+      "learning_rate": 1.812227074235808e-05,
+      "loss": 4.5787,
+      "step": 6000
+    },
+    {
+      "epoch": 6.6593886462882095,
+      "grad_norm": 30.493192672729492,
+      "learning_rate": 1.675764192139738e-05,
+      "loss": 4.6041,
+      "step": 6100
+    },
+    {
+      "epoch": 6.7685589519650655,
+      "grad_norm": 35.86678695678711,
+      "learning_rate": 1.5393013100436683e-05,
+      "loss": 4.6345,
+      "step": 6200
+    },
+    {
+      "epoch": 6.877729257641922,
+      "grad_norm": 44.66313934326172,
+      "learning_rate": 1.4028384279475984e-05,
+      "loss": 4.6063,
+      "step": 6300
+    },
+    {
+      "epoch": 6.986899563318778,
+      "grad_norm": 34.84800720214844,
+      "learning_rate": 1.2663755458515283e-05,
+      "loss": 4.6152,
+      "step": 6400
+    },
+    {
+      "epoch": 7.0,
+      "eval_avg_mae": 5.481756210327148,
+      "eval_loss": 5.481756210327148,
+      "eval_mae_lex": 4.816911220550537,
+      "eval_mae_sem": 3.748530626296997,
+      "eval_mae_syn": 7.87982702255249,
+      "eval_runtime": 27.0121,
+      "eval_samples_per_second": 271.248,
+      "eval_steps_per_second": 8.478,
+      "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