Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bedc646b0c32b1ad68548c5bacfc0ac7530fd21e564481050cda862faf0d974
+oid sha256:533bcedc70c1ba977edf8f964162e29dac2f2ded0e80d5ac138e3337711e299e
 size 442668636

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea5909b394f56ca428fdba6c8839a075b2ff8da5f2fe574e5efdd06083bea54
+oid sha256:c39e29d6e0217e4ee207e0d4bef98c40b17e4a76692586b3f4efc7b21d165f95
 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 sha256:094473adb9147cbc574c74fa5cf34500f7166f96e92615702ffcaba4852f1943
+oid sha256:39dce596f597946769554edb972b9f1c6abe7c7f4150e7ed88047695e2bb4c5f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 5.39035161336263,
   "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": 269.005,
       "eval_steps_per_second": 8.408,
       "step": 5496
+    },
+    {
+      "epoch": 6.004366812227074,
+      "grad_norm": 30.764888763427734,
+      "learning_rate": 1.2472707423580788e-05,
+      "loss": 4.7749,
+      "step": 5500
+    },
+    {
+      "epoch": 6.11353711790393,
+      "grad_norm": 32.09075164794922,
+      "learning_rate": 1.1790393013100438e-05,
+      "loss": 4.6015,
+      "step": 5600
+    },
+    {
+      "epoch": 6.222707423580786,
+      "grad_norm": 30.449230194091797,
+      "learning_rate": 1.1108078602620089e-05,
+      "loss": 4.5258,
+      "step": 5700
+    },
+    {
+      "epoch": 6.331877729257642,
+      "grad_norm": 26.658090591430664,
+      "learning_rate": 1.0425764192139738e-05,
+      "loss": 4.5119,
+      "step": 5800
+    },
+    {
+      "epoch": 6.441048034934497,
+      "grad_norm": 35.33096694946289,
+      "learning_rate": 9.74344978165939e-06,
+      "loss": 4.3653,
+      "step": 5900
+    },
+    {
+      "epoch": 6.550218340611353,
+      "grad_norm": 31.823776245117188,
+      "learning_rate": 9.06113537117904e-06,
+      "loss": 4.4477,
+      "step": 6000
+    },
+    {
+      "epoch": 6.6593886462882095,
+      "grad_norm": 29.176389694213867,
+      "learning_rate": 8.37882096069869e-06,
+      "loss": 4.5485,
+      "step": 6100
+    },
+    {
+      "epoch": 6.7685589519650655,
+      "grad_norm": 39.900264739990234,
+      "learning_rate": 7.696506550218342e-06,
+      "loss": 4.5233,
+      "step": 6200
+    },
+    {
+      "epoch": 6.877729257641922,
+      "grad_norm": 28.541597366333008,
+      "learning_rate": 7.014192139737992e-06,
+      "loss": 4.5032,
+      "step": 6300
+    },
+    {
+      "epoch": 6.986899563318778,
+      "grad_norm": 37.577293395996094,
+      "learning_rate": 6.3318777292576415e-06,
+      "loss": 4.507,
+      "step": 6400
+    },
+    {
+      "epoch": 7.0,
+      "eval_avg_mae": 5.4305070241292315,
+      "eval_loss": 5.430506706237793,
+      "eval_mae_lex": 4.818454742431641,
+      "eval_mae_sem": 3.808347702026367,
+      "eval_mae_syn": 7.664718151092529,
+      "eval_runtime": 27.2304,
+      "eval_samples_per_second": 269.074,
+      "eval_steps_per_second": 8.41,
+      "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