Training in progress, step 1000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d2bf4b1ee900ba2c7a93b0d3003dbb5b2f1930cd1a1d5dc722a1c2fff3dcc3e
+oid sha256:c4edf8e9dd34bd57ff5846e0212cffd8cd54278fc857157b04664b72b02c86a4
 size 598898116

run-0/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e6e2480ade2892cd518bd1a80d3676675a94d60a021608c5c130473861548e
+oid sha256:c4edf8e9dd34bd57ff5846e0212cffd8cd54278fc857157b04664b72b02c86a4
 size 598898116

run-0/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced4d4676df50961b7aefc683840c9fdf16db5f109f64beb472fa8faaf6f8b56
+oid sha256:ce4311d92b66555d67c64dfb50a5db312a63ee5b8100bb62dbe5f57efeb895f0
 size 1197886411

run-0/checkpoint-1000/trainer_state.json

@@ -11,34 +11,34 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8970967741935484,
-      "eval_loss": 2.0391886234283447,
-      "eval_runtime": 17.7829,
-      "eval_samples_per_second": 174.325,
-      "eval_steps_per_second": 5.455,
+      "eval_accuracy": 0.8764516129032258,
+      "eval_loss": 2.150498628616333,
+      "eval_runtime": 17.8438,
+      "eval_samples_per_second": 173.73,
+      "eval_steps_per_second": 5.436,
       "step": 477
     },
     {
       "epoch": 1.0482180293501049,
-      "grad_norm": 21.700918197631836,
+      "grad_norm": 27.51361083984375,
       "learning_rate": 1.302585604472397e-05,
-      "loss": 8.2637,
+      "loss": 5.9093,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.94,
-      "eval_loss": 1.2688708305358887,
-      "eval_runtime": 17.8037,
-      "eval_samples_per_second": 174.121,
-      "eval_steps_per_second": 5.448,
+      "eval_accuracy": 0.9274193548387096,
+      "eval_loss": 1.3017561435699463,
+      "eval_runtime": 18.0499,
+      "eval_samples_per_second": 171.746,
+      "eval_steps_per_second": 5.374,
       "step": 954
     },
     {
       "epoch": 2.0964360587002098,
-      "grad_norm": 8.109223365783691,
+      "grad_norm": 7.277801513671875,
       "learning_rate": 6.037735849056604e-06,
-      "loss": 1.3389,
+      "loss": 1.4917,
       "step": 1000
     }
   ],
@@ -59,12 +59,12 @@
       "attributes": {}
     }
   },
-  "total_flos": 448725995623620.0,
+  "total_flos": 631987256544708.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.04124860013748177,
+    "alpha": 0.8979553244778209,
     "num_train_epochs": 3,
-    "temperature": 2.878079794128767
+    "temperature": 4.375187631815162
   }
 }

run-0/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6300c874dd8d560d51ee9bf55d460b2a5df3fbfe9fa1e724e25742d02b9d2b07
+oid sha256:20b487dd7dd7a79406e30f85b1328021e4bfb070d1b507d4249e6c45909667ea
 size 5905