Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33620587b37c196969d3f412f74ef041dcfeee8258db5933dc3c4540e70b1e43
+oid sha256:f09ba02af072f6dab1b31924b201f644e12e95c27ead4dc9623741e011906d93
 size 268290900

run-2/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b49c4c0e9b9d02c51089e4c3ff6b97f6ce6bf63696a258f815cf8e2724d249b
+oid sha256:2265efdbd127f32817bf80110d8d6f541a55048b2e22b7e0e6227a688a9ef047
 size 268290900

run-2/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29be22eb573b537bdedf5ce6e084b35bbf1b9990d6e83979bb8aa210fa3c2fad
+oid sha256:c4557295dc599e62a6393fbd116ab5c4958396bbe86258e055f7094ff579a4f6
 size 536643898

run-2/checkpoint-1000/trainer_state.json

@@ -10,43 +10,43 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5948387096774194,
-      "eval_loss": 0.2074165940284729,
-      "eval_runtime": 5.1592,
-      "eval_samples_per_second": 600.867,
-      "eval_steps_per_second": 12.599,
+      "eval_accuracy": 0.5887096774193549,
+      "eval_loss": 0.19886387884616852,
+      "eval_runtime": 5.1582,
+      "eval_samples_per_second": 600.982,
+      "eval_steps_per_second": 12.601,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.538582980632782,
+      "grad_norm": 0.5294517874717712,
       "learning_rate": 1.650593990216632e-05,
-      "loss": 0.3336,
+      "loss": 0.3203,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8258064516129032,
-      "eval_loss": 0.09868818521499634,
-      "eval_runtime": 5.3751,
-      "eval_samples_per_second": 576.732,
-      "eval_steps_per_second": 12.093,
+      "eval_accuracy": 0.8193548387096774,
+      "eval_loss": 0.09618715196847916,
+      "eval_runtime": 5.4445,
+      "eval_samples_per_second": 569.379,
+      "eval_steps_per_second": 11.939,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8829032258064516,
-      "eval_loss": 0.06500214338302612,
-      "eval_runtime": 5.0949,
-      "eval_samples_per_second": 608.447,
-      "eval_steps_per_second": 12.758,
+      "eval_accuracy": 0.8783870967741936,
+      "eval_loss": 0.06421981006860733,
+      "eval_runtime": 5.3341,
+      "eval_samples_per_second": 581.17,
+      "eval_steps_per_second": 12.186,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.4604446291923523,
+      "grad_norm": 0.44660821557044983,
       "learning_rate": 1.3011879804332637e-05,
-      "loss": 0.1147,
+      "loss": 0.1116,
       "step": 1000
     }
   ],
@@ -71,8 +71,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.186668286700706,
+    "alpha": 0.38078945785669316,
     "num_train_epochs": 9,
-    "temperature": 8
+    "temperature": 11
   }
 }

run-2/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09a3826ab4ffc76c9981d2ccde475f4c95a27c3ed7ffae8225ce76a3cd34eeb
+oid sha256:a815016dfca6056394449b7eec53142e869a6e9ff738e6f9557bb4382010c025
 size 5240

run-2/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c7efa1eb43f0dbc4ee52d425f1c719b0ac50968b1ac6f289ce19795f21d6ef
+oid sha256:f09ba02af072f6dab1b31924b201f644e12e95c27ead4dc9623741e011906d93
 size 268290900

run-2/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1a0fe777f4f91fac7177404c72ccfef92ba997eca6a77ed69cb1115985106a
+oid sha256:875d936002e9ba81a59c4d5636d51888d66a375fc0c698deb36655a1e91c1333
 size 536643898

run-2/checkpoint-1500/trainer_state.json

@@ -10,59 +10,59 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5948387096774194,
-      "eval_loss": 0.2074165940284729,
-      "eval_runtime": 5.1592,
-      "eval_samples_per_second": 600.867,
-      "eval_steps_per_second": 12.599,
+      "eval_accuracy": 0.5887096774193549,
+      "eval_loss": 0.19886387884616852,
+      "eval_runtime": 5.1582,
+      "eval_samples_per_second": 600.982,
+      "eval_steps_per_second": 12.601,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.538582980632782,
+      "grad_norm": 0.5294517874717712,
       "learning_rate": 1.650593990216632e-05,
-      "loss": 0.3336,
+      "loss": 0.3203,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8258064516129032,
-      "eval_loss": 0.09868818521499634,
-      "eval_runtime": 5.3751,
-      "eval_samples_per_second": 576.732,
-      "eval_steps_per_second": 12.093,
+      "eval_accuracy": 0.8193548387096774,
+      "eval_loss": 0.09618715196847916,
+      "eval_runtime": 5.4445,
+      "eval_samples_per_second": 569.379,
+      "eval_steps_per_second": 11.939,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8829032258064516,
-      "eval_loss": 0.06500214338302612,
-      "eval_runtime": 5.0949,
-      "eval_samples_per_second": 608.447,
-      "eval_steps_per_second": 12.758,
+      "eval_accuracy": 0.8783870967741936,
+      "eval_loss": 0.06421981006860733,
+      "eval_runtime": 5.3341,
+      "eval_samples_per_second": 581.17,
+      "eval_steps_per_second": 12.186,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.4604446291923523,
+      "grad_norm": 0.44660821557044983,
       "learning_rate": 1.3011879804332637e-05,
-      "loss": 0.1147,
+      "loss": 0.1116,
       "step": 1000
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.8996774193548387,
-      "eval_loss": 0.049765754491090775,
-      "eval_runtime": 5.2676,
-      "eval_samples_per_second": 588.5,
-      "eval_steps_per_second": 12.34,
+      "eval_loss": 0.04962550476193428,
+      "eval_runtime": 5.1177,
+      "eval_samples_per_second": 605.746,
+      "eval_steps_per_second": 12.701,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.31128990650177,
+      "grad_norm": 0.3033629357814789,
       "learning_rate": 9.517819706498952e-06,
-      "loss": 0.0724,
+      "loss": 0.0713,
       "step": 1500
     }
   ],
@@ -87,8 +87,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.186668286700706,
+    "alpha": 0.38078945785669316,
     "num_train_epochs": 9,
-    "temperature": 8
+    "temperature": 11
   }
 }

run-2/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09a3826ab4ffc76c9981d2ccde475f4c95a27c3ed7ffae8225ce76a3cd34eeb
+oid sha256:a815016dfca6056394449b7eec53142e869a6e9ff738e6f9557bb4382010c025
 size 5240

runs/Oct11_17-03-17_c179252869f4/events.out.tfevents.1728667869.c179252869f4.732.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7da3002894e058a03f9c3e756d64286c2e3f4ea94e0957cf3230cd152f551e
-size 13298
+oid sha256:c1ef5556b5a378227de21603a8fff9c519c2252f5e86117c14ad4fb68edaf881
+size 15223