Training in progress, epoch 5

logs/events.out.tfevents.1709713222.adc675a344d5.67573.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee0042c110ecebe6a7c28f7fb88734e26739d2362cb9f011636559f97bc76ef
-size 7362
+oid sha256:425f56e10a4d905faaae1e2dbb3f915c184d8e8ad2c400b79b52b03dd467ca07
+size 8045

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ee64d405d4c6d74a1cdef94a4088fb9057befe0008cff3e8dffb3ca7e7b831
+oid sha256:0ed95bb0c18f9d334c1a78a8121b8dc05b4b464ee73a6cc9485e7964b57d1a63
 size 17549312

run-0/checkpoint-960/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476ee8f1f83a2930e10c4fbd1ec962bea66c39ab816fe16405c1eab1f0bdca1b
+oid sha256:ba4a7003755b10592915508f55852913e649127e5440c66527724e592cc2c7b9
 size 17549312

run-0/checkpoint-960/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3772077f744c6e14da17813cc0b06415b68919b80b205f25aefe844530eaab5b
+oid sha256:af588371549f4acb73612d2ad9cd55882aa5fd9f7a0e04c941b81fe140e8d522
 size 35122746

run-0/checkpoint-960/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46991e9a48fd9f9c71effd0da425199be1ec600bef86bda24b5504c67c161567
+oid sha256:e74635b58993a273a88d047851a4965dd0f1dab13efd68e1f5c9a3b33d5098c1
 size 1064

run-0/checkpoint-960/tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 29,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

run-0/checkpoint-960/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6536203522504892,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-864",
+  "best_metric": 0.8228962818003914,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-768",
   "epoch": 10.0,
   "eval_steps": 500,
   "global_step": 960,
@@ -10,192 +10,192 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.8228768110275269,
-      "learning_rate": 1.922542063523116e-05,
-      "loss": 0.7149,
+      "grad_norm": 1.8004393577575684,
+      "learning_rate": 0.0007697157586205755,
+      "loss": 0.4935,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.007766990291262136,
-      "eval_loss": 0.7131175398826599,
-      "eval_precision": 0.5,
-      "eval_recall": 0.003913894324853229,
-      "eval_runtime": 26.5316,
-      "eval_samples_per_second": 38.52,
-      "eval_steps_per_second": 1.206,
+      "eval_accuracy": 0.7436399217221135,
+      "eval_f1": 0.7689594356261024,
+      "eval_loss": 0.448881596326828,
+      "eval_precision": 0.6998394863563403,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.6476,
+      "eval_samples_per_second": 35.675,
+      "eval_steps_per_second": 1.117,
       "step": 96
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.1306586265563965,
-      "learning_rate": 1.7089262786872146e-05,
-      "loss": 0.7062,
+      "grad_norm": 4.9879961013793945,
+      "learning_rate": 0.0006841917854405115,
+      "loss": 0.4571,
       "step": 192
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5136986301369864,
-      "eval_f1": 0.08133086876155268,
-      "eval_loss": 0.7069234848022461,
-      "eval_precision": 0.7333333333333333,
-      "eval_recall": 0.043052837573385516,
-      "eval_runtime": 26.8847,
-      "eval_samples_per_second": 38.014,
-      "eval_steps_per_second": 1.19,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.8057813911472448,
+      "eval_loss": 0.42557916045188904,
+      "eval_precision": 0.7483221476510067,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 28.772,
+      "eval_samples_per_second": 35.521,
+      "eval_steps_per_second": 1.112,
       "step": 192
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.5551536083221436,
-      "learning_rate": 1.4953104938513126e-05,
-      "loss": 0.6972,
+      "grad_norm": 3.279979705810547,
+      "learning_rate": 0.0005986678122604475,
+      "loss": 0.4337,
       "step": 288
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.512720156555773,
-      "eval_f1": 0.08791208791208792,
-      "eval_loss": 0.6998902559280396,
-      "eval_precision": 0.6857142857142857,
-      "eval_recall": 0.046966731898238745,
-      "eval_runtime": 26.6683,
-      "eval_samples_per_second": 38.323,
-      "eval_steps_per_second": 1.2,
+      "eval_accuracy": 0.7945205479452054,
+      "eval_f1": 0.8059149722735675,
+      "eval_loss": 0.4328659176826477,
+      "eval_precision": 0.7635726795096323,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.2776,
+      "eval_samples_per_second": 36.142,
+      "eval_steps_per_second": 1.132,
       "step": 288
     },
     {
       "epoch": 4.0,
-      "grad_norm": 2.080883741378784,
-      "learning_rate": 1.2816947090154107e-05,
-      "loss": 0.6854,
+      "grad_norm": 2.231189727783203,
+      "learning_rate": 0.0005131438390803836,
+      "loss": 0.4235,
       "step": 384
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5606653620352251,
-      "eval_f1": 0.3145038167938931,
-      "eval_loss": 0.6807624697685242,
-      "eval_precision": 0.7152777777777778,
-      "eval_recall": 0.20156555772994128,
-      "eval_runtime": 26.6572,
-      "eval_samples_per_second": 38.339,
-      "eval_steps_per_second": 1.2,
+      "eval_accuracy": 0.7690802348336595,
+      "eval_f1": 0.7704280155642023,
+      "eval_loss": 0.45082738995552063,
+      "eval_precision": 0.7659574468085106,
+      "eval_recall": 0.7749510763209393,
+      "eval_runtime": 29.4798,
+      "eval_samples_per_second": 34.668,
+      "eval_steps_per_second": 1.085,
       "step": 384
     },
     {
       "epoch": 5.0,
-      "grad_norm": 2.0045652389526367,
-      "learning_rate": 1.068078924179509e-05,
-      "loss": 0.6688,
+      "grad_norm": 0.6898621320724487,
+      "learning_rate": 0.00042761986590031967,
+      "loss": 0.4136,
       "step": 480
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6105675146771037,
-      "eval_f1": 0.49234693877551017,
-      "eval_loss": 0.6664517521858215,
-      "eval_precision": 0.706959706959707,
-      "eval_recall": 0.3776908023483366,
-      "eval_runtime": 26.8808,
-      "eval_samples_per_second": 38.02,
-      "eval_steps_per_second": 1.19,
+      "eval_accuracy": 0.8033268101761253,
+      "eval_f1": 0.814404432132964,
+      "eval_loss": 0.41852009296417236,
+      "eval_precision": 0.7709790209790209,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 29.6952,
+      "eval_samples_per_second": 34.416,
+      "eval_steps_per_second": 1.078,
       "step": 480
     },
     {
       "epoch": 6.0,
-      "grad_norm": 3.2470343112945557,
-      "learning_rate": 8.544631393436073e-06,
-      "loss": 0.6549,
+      "grad_norm": 1.360769510269165,
+      "learning_rate": 0.00034209589272025573,
+      "loss": 0.405,
       "step": 576
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6418786692759295,
-      "eval_f1": 0.5906040268456376,
-      "eval_loss": 0.6583118438720703,
-      "eval_precision": 0.6892950391644909,
-      "eval_recall": 0.5166340508806262,
-      "eval_runtime": 26.2817,
-      "eval_samples_per_second": 38.886,
-      "eval_steps_per_second": 1.218,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.8204667863554758,
+      "eval_loss": 0.4140284061431885,
+      "eval_precision": 0.75787728026534,
+      "eval_recall": 0.8943248532289628,
+      "eval_runtime": 28.8106,
+      "eval_samples_per_second": 35.473,
+      "eval_steps_per_second": 1.111,
       "step": 576
     },
     {
       "epoch": 7.0,
-      "grad_norm": 2.420502185821533,
-      "learning_rate": 6.4084735450770535e-06,
-      "loss": 0.6502,
+      "grad_norm": 1.9378271102905273,
+      "learning_rate": 0.0002565719195401918,
+      "loss": 0.3961,
       "step": 672
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6360078277886497,
-      "eval_f1": 0.5782312925170068,
-      "eval_loss": 0.6568923592567444,
-      "eval_precision": 0.6873315363881402,
-      "eval_recall": 0.49902152641878667,
-      "eval_runtime": 26.5443,
-      "eval_samples_per_second": 38.502,
-      "eval_steps_per_second": 1.206,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8301886792452831,
+      "eval_loss": 0.4103885591030121,
+      "eval_precision": 0.7674418604651163,
+      "eval_recall": 0.9041095890410958,
+      "eval_runtime": 29.2823,
+      "eval_samples_per_second": 34.902,
+      "eval_steps_per_second": 1.093,
       "step": 672
     },
     {
       "epoch": 8.0,
-      "grad_norm": 2.7794277667999268,
-      "learning_rate": 4.2723156967180365e-06,
-      "loss": 0.6453,
+      "grad_norm": 1.5738866329193115,
+      "learning_rate": 0.00017104794636012787,
+      "loss": 0.3931,
       "step": 768
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.649706457925636,
-      "eval_f1": 0.6108695652173913,
-      "eval_loss": 0.6531394720077515,
-      "eval_precision": 0.687041564792176,
-      "eval_recall": 0.5499021526418787,
-      "eval_runtime": 26.8208,
-      "eval_samples_per_second": 38.105,
-      "eval_steps_per_second": 1.193,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8340971585701191,
+      "eval_loss": 0.39944925904273987,
+      "eval_precision": 0.7844827586206896,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 29.1614,
+      "eval_samples_per_second": 35.046,
+      "eval_steps_per_second": 1.097,
       "step": 768
     },
     {
       "epoch": 9.0,
-      "grad_norm": 2.565406560897827,
-      "learning_rate": 2.1361578483590183e-06,
-      "loss": 0.6432,
+      "grad_norm": 0.702528178691864,
+      "learning_rate": 8.552397318006393e-05,
+      "loss": 0.3891,
       "step": 864
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6536203522504892,
-      "eval_f1": 0.616052060737527,
-      "eval_loss": 0.6520226001739502,
-      "eval_precision": 0.6909975669099757,
-      "eval_recall": 0.5557729941291585,
-      "eval_runtime": 26.3078,
-      "eval_samples_per_second": 38.848,
-      "eval_steps_per_second": 1.216,
+      "eval_accuracy": 0.8180039138943248,
+      "eval_f1": 0.8287292817679558,
+      "eval_loss": 0.39775392413139343,
+      "eval_precision": 0.782608695652174,
+      "eval_recall": 0.8806262230919765,
+      "eval_runtime": 29.1415,
+      "eval_samples_per_second": 35.07,
+      "eval_steps_per_second": 1.098,
       "step": 864
     },
     {
       "epoch": 10.0,
-      "grad_norm": 2.5873706340789795,
+      "grad_norm": 2.4524667263031006,
       "learning_rate": 0.0,
-      "loss": 0.645,
+      "loss": 0.3819,
       "step": 960
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.6536203522504892,
-      "eval_f1": 0.6168831168831169,
-      "eval_loss": 0.6515934467315674,
-      "eval_precision": 0.6900726392251816,
-      "eval_recall": 0.5577299412915852,
-      "eval_runtime": 26.5855,
-      "eval_samples_per_second": 38.442,
-      "eval_steps_per_second": 1.204,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8288119738072964,
+      "eval_loss": 0.3977544605731964,
+      "eval_precision": 0.7939068100358423,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 30.4608,
+      "eval_samples_per_second": 33.551,
+      "eval_steps_per_second": 1.051,
       "step": 960
     }
   ],
@@ -204,13 +204,13 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2204890555200.0,
+  "total_flos": 2356951972800.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8789746577248793,
-    "learning_rate": 2.136157848359018e-05,
+    "alpha": 0.735211359802956,
+    "learning_rate": 0.0008552397318006393,
     "num_train_epochs": 10,
-    "temperature": 14
+    "temperature": 25
   }
 }

run-0/checkpoint-960/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1d86d1ef9c5f73f9fb51b0ea325423f470c0f4f628eb656cb6d38e041dfed8
+oid sha256:23804eaaa0feed30486319d2982557f65dce708f7d788864c811c20b2e8c33b4
 size 4920

run-1/checkpoint-384/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ee64d405d4c6d74a1cdef94a4088fb9057befe0008cff3e8dffb3ca7e7b831
+oid sha256:58db24d6a1e94d489cf4b73b5c63cab45aa03d29d732a9d54d6f4f46aef7da02
 size 17549312

run-1/checkpoint-384/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7db08017862e0e251ef5c7fee81627b23e601266a28071888ee84dc4604daaf
+oid sha256:a4d03bf37ea38e30d96312f5718b7d70295e30f2d32d7091c3106fe205c75b2d
 size 35122746

run-1/checkpoint-384/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e6fc9a74bdc33046e740a32f8443a2cac1cdfee1791b57156767e02534f6781
+oid sha256:9d4b63168300ff1c1b6fb1c3579fe55a55c3b0dedd2cdac5f6ca12f671c781e4
 size 1064

run-1/checkpoint-384/tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 29,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

run-1/checkpoint-384/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-96",
+  "best_metric": 0.8140900195694716,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-288",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 384,
@@ -10,93 +10,93 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.5780554413795471,
-      "learning_rate": 4.753898010566846e-05,
-      "loss": 0.4511,
+      "grad_norm": 2.6617980003356934,
+      "learning_rate": 0.0006635023570917325,
+      "loss": 0.5037,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.2628569006919861,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 27.1178,
-      "eval_samples_per_second": 37.687,
-      "eval_steps_per_second": 1.18,
+      "eval_accuracy": 0.7661448140900196,
+      "eval_f1": 0.792714657415438,
+      "eval_loss": 0.4430159628391266,
+      "eval_precision": 0.7118380062305296,
+      "eval_recall": 0.8943248532289628,
+      "eval_runtime": 28.6854,
+      "eval_samples_per_second": 35.628,
+      "eval_steps_per_second": 1.116,
       "step": 96
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.48165255784988403,
-      "learning_rate": 4.1596607592459905e-05,
-      "loss": 0.2586,
+      "grad_norm": 1.12320077419281,
+      "learning_rate": 0.0004976267678187994,
+      "loss": 0.4391,
       "step": 192
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.24026808142662048,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 26.412,
-      "eval_samples_per_second": 38.694,
-      "eval_steps_per_second": 1.212,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_f1": 0.8227848101265822,
+      "eval_loss": 0.41584911942481995,
+      "eval_precision": 0.7647058823529411,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 28.5215,
+      "eval_samples_per_second": 35.833,
+      "eval_steps_per_second": 1.122,
       "step": 192
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.4460384845733643,
-      "learning_rate": 3.565423507925135e-05,
-      "loss": 0.2361,
+      "grad_norm": 2.946756362915039,
+      "learning_rate": 0.00033175117854586627,
+      "loss": 0.41,
       "step": 288
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.22164104878902435,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 26.2166,
-      "eval_samples_per_second": 38.983,
-      "eval_steps_per_second": 1.221,
+      "eval_accuracy": 0.8140900195694716,
+      "eval_f1": 0.8260073260073261,
+      "eval_loss": 0.43016910552978516,
+      "eval_precision": 0.7762478485370051,
+      "eval_recall": 0.8825831702544031,
+      "eval_runtime": 28.1244,
+      "eval_samples_per_second": 36.339,
+      "eval_steps_per_second": 1.138,
       "step": 288
     },
     {
       "epoch": 4.0,
-      "grad_norm": 1.0731241703033447,
-      "learning_rate": 2.971186256604279e-05,
-      "loss": 0.2235,
+      "grad_norm": 3.868119478225708,
+      "learning_rate": 0.00016587558927293314,
+      "loss": 0.4041,
       "step": 384
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.21637097001075745,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 29.8278,
-      "eval_samples_per_second": 34.263,
-      "eval_steps_per_second": 1.073,
+      "eval_accuracy": 0.8033268101761253,
+      "eval_f1": 0.802747791952895,
+      "eval_loss": 0.4142443835735321,
+      "eval_precision": 0.8051181102362205,
+      "eval_recall": 0.8003913894324853,
+      "eval_runtime": 29.1758,
+      "eval_samples_per_second": 35.029,
+      "eval_steps_per_second": 1.097,
       "step": 384
     }
   ],
   "logging_steps": 500,
-  "max_steps": 864,
+  "max_steps": 480,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 881956222080.0,
+  "total_flos": 942780789120.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.09512919148833521,
-    "learning_rate": 5.348135261887702e-05,
-    "num_train_epochs": 9,
-    "temperature": 18
+    "alpha": 0.7818460169984094,
+    "learning_rate": 0.0008293779463646656,
+    "num_train_epochs": 5,
+    "temperature": 3
   }
 }

run-1/checkpoint-384/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9294acd0d1ac9a0620db6e082aaf47884f1952d159c5d9fb3fb281c25ad02a64
+oid sha256:1ab2cfe4c2ab241510bc23e9ec5727876e620ab477a4e5ad72a937b25e09df23
 size 4920

run-2/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ef7ac15d70c06615ec62775bbd9d47a7a307f789675ebd91d014018802f0ac
+oid sha256:f72e368a0735e0614c97feb6fba15c5d298f68104e7128cf582de5807e255027
 size 17549312

run-2/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea9c584a6706cb5bee635fc6f64c59550cbdb80935f1c815de62851495dd156
+oid sha256:5b5aece18803da9b55ab957b14fbd401ac7b58d03d968f7138245dd9246cea4e
 size 35122746

run-2/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5feae9a058dc367ba00ad758a34b0a64ac558c1f8bd5163d9bb2ce9c13aac22
+oid sha256:773b7d3c411900ce077bec534b9aeadeaba63fc284f46150d41278a6fa17bea6
 size 1064

run-2/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7984344422700587,
+  "best_metric": 0.5,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 3.4323604106903076,
-      "learning_rate": 0.0004667999543114754,
-      "loss": 0.533,
+      "grad_norm": 3.4041388034820557,
+      "learning_rate": 8.656503841433308e-07,
+      "loss": 0.2746,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7984344422700587,
-      "eval_f1": 0.8049242424242424,
-      "eval_loss": 0.4442267119884491,
-      "eval_precision": 0.7798165137614679,
-      "eval_recall": 0.8317025440313112,
-      "eval_runtime": 28.6457,
-      "eval_samples_per_second": 35.677,
-      "eval_steps_per_second": 1.117,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.25451573729515076,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 28.1178,
+      "eval_samples_per_second": 36.347,
+      "eval_steps_per_second": 1.138,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 192,
+  "max_steps": 480,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.88253398201078,
-    "learning_rate": 0.0009335999086229508,
-    "num_train_epochs": 2,
-    "temperature": 19
+    "alpha": 0.04277939142155329,
+    "learning_rate": 1.0820629801791635e-06,
+    "num_train_epochs": 5,
+    "temperature": 6
   }
 }

run-2/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2659042d49fa36ce1404b1f7057dd4643dc22f653d1fc44d521700862149e4b7
+oid sha256:bd5c3fbfe040730ec9bc64036d615ae00f3fe41347ad2df02c2ead7e8faec2da
 size 4920

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 29,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9294acd0d1ac9a0620db6e082aaf47884f1952d159c5d9fb3fb281c25ad02a64
+oid sha256:019a0c30743454578a20e039f50246add333dec6abb36273bd6bc2339b797b34
 size 4920