chore: update default temperature

all_results.json

@@ -1,12 +0,0 @@
-{
-    "epoch": 1.9936479128856623,
-    "eval_loss": 0.4997712969779968,
-    "eval_runtime": 472.9101,
-    "eval_samples_per_second": 5.887,
-    "eval_steps_per_second": 0.736,
-    "total_flos": 192523449925632.0,
-    "train_loss": 0.47888606233023556,
-    "train_runtime": 10712.2216,
-    "train_samples_per_second": 9.875,
-    "train_steps_per_second": 0.034
-}

eval_results.json

@@ -1,7 +0,0 @@
-{
-    "epoch": 1.9936479128856623,
-    "eval_loss": 0.4997712969779968,
-    "eval_runtime": 472.9101,
-    "eval_samples_per_second": 5.887,
-    "eval_steps_per_second": 0.736
-}

generation_config.json

@@ -11,7 +11,7 @@
   ],
   "gamma": 1.0,
   "kl_temperature": 1.0,
-  "temperature": 0.7,
+  "temperature": 0.4,
   "top_p": 0.95,
   "transformers_version": "4.46.1"
-}
+}

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 1.9936479128856623,
-    "total_flos": 192523449925632.0,
-    "train_loss": 0.47888606233023556,
-    "train_runtime": 10712.2216,
-    "train_samples_per_second": 9.875,
-    "train_steps_per_second": 0.034
-}

trainer_log.jsonl

@@ -1,37 +0,0 @@
-{"current_steps": 10, "total_steps": 366, "loss": 0.6313, "lr": 1.9963183634476757e-05, "epoch": 0.0544464609800363, "percentage": 2.73, "elapsed_time": "0:04:56", "remaining_time": "2:55:58"}
-{"current_steps": 20, "total_steps": 366, "loss": 0.5461, "lr": 1.985300562686109e-05, "epoch": 0.1088929219600726, "percentage": 5.46, "elapsed_time": "0:09:48", "remaining_time": "2:49:45"}
-{"current_steps": 30, "total_steps": 366, "loss": 0.5357, "lr": 1.9670277247913205e-05, "epoch": 0.16333938294010888, "percentage": 8.2, "elapsed_time": "0:14:40", "remaining_time": "2:44:18"}
-{"current_steps": 40, "total_steps": 366, "loss": 0.5269, "lr": 1.941634397659126e-05, "epoch": 0.2177858439201452, "percentage": 10.93, "elapsed_time": "0:19:32", "remaining_time": "2:39:13"}
-{"current_steps": 50, "total_steps": 366, "loss": 0.5195, "lr": 1.909307559292236e-05, "epoch": 0.27223230490018147, "percentage": 13.66, "elapsed_time": "0:24:24", "remaining_time": "2:34:13"}
-{"current_steps": 60, "total_steps": 366, "loss": 0.5296, "lr": 1.8702852410301556e-05, "epoch": 0.32667876588021777, "percentage": 16.39, "elapsed_time": "0:29:16", "remaining_time": "2:29:15"}
-{"current_steps": 70, "total_steps": 366, "loss": 0.5077, "lr": 1.8248547748594246e-05, "epoch": 0.3811252268602541, "percentage": 19.13, "elapsed_time": "0:34:08", "remaining_time": "2:24:21"}
-{"current_steps": 80, "total_steps": 366, "loss": 0.518, "lr": 1.77335067770973e-05, "epoch": 0.4355716878402904, "percentage": 21.86, "elapsed_time": "0:39:00", "remaining_time": "2:19:27"}
-{"current_steps": 90, "total_steps": 366, "loss": 0.5148, "lr": 1.7161521883143936e-05, "epoch": 0.4900181488203267, "percentage": 24.59, "elapsed_time": "0:43:52", "remaining_time": "2:14:32"}
-{"current_steps": 100, "total_steps": 366, "loss": 0.512, "lr": 1.653680474772006e-05, "epoch": 0.5444646098003629, "percentage": 27.32, "elapsed_time": "0:48:44", "remaining_time": "2:09:39"}
-{"current_steps": 110, "total_steps": 366, "loss": 0.5029, "lr": 1.586395533370696e-05, "epoch": 0.5989110707803993, "percentage": 30.05, "elapsed_time": "0:53:36", "remaining_time": "2:04:44"}
-{"current_steps": 120, "total_steps": 366, "loss": 0.5089, "lr": 1.5147928015098309e-05, "epoch": 0.6533575317604355, "percentage": 32.79, "elapsed_time": "0:58:27", "remaining_time": "1:59:50"}
-{"current_steps": 130, "total_steps": 366, "loss": 0.5084, "lr": 1.4393995096591415e-05, "epoch": 0.7078039927404719, "percentage": 35.52, "elapsed_time": "1:03:19", "remaining_time": "1:54:57"}
-{"current_steps": 140, "total_steps": 366, "loss": 0.4943, "lr": 1.3607707992167836e-05, "epoch": 0.7622504537205081, "percentage": 38.25, "elapsed_time": "1:08:11", "remaining_time": "1:50:05"}
-{"current_steps": 150, "total_steps": 366, "loss": 0.5068, "lr": 1.2794856348516095e-05, "epoch": 0.8166969147005445, "percentage": 40.98, "elapsed_time": "1:13:03", "remaining_time": "1:45:12"}
-{"current_steps": 160, "total_steps": 366, "loss": 0.5003, "lr": 1.196142541428197e-05, "epoch": 0.8711433756805808, "percentage": 43.72, "elapsed_time": "1:17:54", "remaining_time": "1:40:18"}
-{"current_steps": 170, "total_steps": 366, "loss": 0.5053, "lr": 1.1113551969048088e-05, "epoch": 0.925589836660617, "percentage": 46.45, "elapsed_time": "1:22:47", "remaining_time": "1:35:26"}
-{"current_steps": 180, "total_steps": 366, "loss": 0.5017, "lr": 1.0257479136549889e-05, "epoch": 0.9800362976406534, "percentage": 49.18, "elapsed_time": "1:27:39", "remaining_time": "1:30:34"}
-{"current_steps": 190, "total_steps": 366, "loss": 0.4806, "lr": 9.399510414850518e-06, "epoch": 1.0353901996370236, "percentage": 51.91, "elapsed_time": "1:32:31", "remaining_time": "1:25:42"}
-{"current_steps": 200, "total_steps": 366, "loss": 0.4415, "lr": 8.545963261963102e-06, "epoch": 1.08983666061706, "percentage": 54.64, "elapsed_time": "1:37:23", "remaining_time": "1:20:49"}
-{"current_steps": 210, "total_steps": 366, "loss": 0.4406, "lr": 7.703122578682047e-06, "epoch": 1.144283121597096, "percentage": 57.38, "elapsed_time": "1:42:14", "remaining_time": "1:15:57"}
-{"current_steps": 220, "total_steps": 366, "loss": 0.4345, "lr": 6.877194431142055e-06, "epoch": 1.1987295825771325, "percentage": 60.11, "elapsed_time": "1:47:06", "remaining_time": "1:11:05"}
-{"current_steps": 230, "total_steps": 366, "loss": 0.4443, "lr": 6.074260353858283e-06, "epoch": 1.2531760435571688, "percentage": 62.84, "elapsed_time": "1:51:58", "remaining_time": "1:06:12"}
-{"current_steps": 240, "total_steps": 366, "loss": 0.4329, "lr": 5.300232569726805e-06, "epoch": 1.3076225045372052, "percentage": 65.57, "elapsed_time": "1:56:50", "remaining_time": "1:01:20"}
-{"current_steps": 250, "total_steps": 366, "loss": 0.4376, "lr": 4.560810456712754e-06, "epoch": 1.3620689655172413, "percentage": 68.31, "elapsed_time": "2:01:42", "remaining_time": "0:56:28"}
-{"current_steps": 260, "total_steps": 366, "loss": 0.4375, "lr": 3.86143858177388e-06, "epoch": 1.4165154264972777, "percentage": 71.04, "elapsed_time": "2:06:34", "remaining_time": "0:51:36"}
-{"current_steps": 270, "total_steps": 366, "loss": 0.439, "lr": 3.207266611027069e-06, "epoch": 1.470961887477314, "percentage": 73.77, "elapsed_time": "2:11:25", "remaining_time": "0:46:43"}
-{"current_steps": 280, "total_steps": 366, "loss": 0.4437, "lr": 2.6031113913503337e-06, "epoch": 1.5254083484573502, "percentage": 76.5, "elapsed_time": "2:16:17", "remaining_time": "0:41:51"}
-{"current_steps": 290, "total_steps": 366, "loss": 0.4413, "lr": 2.0534214826237486e-06, "epoch": 1.5798548094373865, "percentage": 79.23, "elapsed_time": "2:21:09", "remaining_time": "0:36:59"}
-{"current_steps": 300, "total_steps": 366, "loss": 0.4321, "lr": 1.5622444017681438e-06, "epoch": 1.634301270417423, "percentage": 81.97, "elapsed_time": "2:26:02", "remaining_time": "0:32:07"}
-{"current_steps": 310, "total_steps": 366, "loss": 0.4335, "lr": 1.1331968197725985e-06, "epoch": 1.6887477313974593, "percentage": 84.7, "elapsed_time": "2:30:54", "remaining_time": "0:27:15"}
-{"current_steps": 320, "total_steps": 366, "loss": 0.437, "lr": 7.694379311582401e-07, "epoch": 1.7431941923774956, "percentage": 87.43, "elapsed_time": "2:35:46", "remaining_time": "0:22:23"}
-{"current_steps": 330, "total_steps": 366, "loss": 0.4404, "lr": 4.73646191966175e-07, "epoch": 1.7976406533575318, "percentage": 90.16, "elapsed_time": "2:40:37", "remaining_time": "0:17:31"}
-{"current_steps": 340, "total_steps": 366, "loss": 0.4364, "lr": 2.479995975541749e-07, "epoch": 1.852087114337568, "percentage": 92.9, "elapsed_time": "2:45:29", "remaining_time": "0:12:39"}
-{"current_steps": 350, "total_steps": 366, "loss": 0.422, "lr": 9.415964542203059e-08, "epoch": 1.9065335753176043, "percentage": 95.63, "elapsed_time": "2:50:21", "remaining_time": "0:07:47"}
-{"current_steps": 360, "total_steps": 366, "loss": 0.4297, "lr": 1.325910115169471e-08, "epoch": 1.9609800362976406, "percentage": 98.36, "elapsed_time": "2:55:13", "remaining_time": "0:02:55"}
-{"current_steps": 366, "total_steps": 366, "epoch": 1.9936479128856623, "percentage": 100.0, "elapsed_time": "2:58:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -1,294 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.9936479128856623,
-  "eval_steps": 400,
-  "global_step": 366,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0544464609800363,
-      "grad_norm": 0.5656834527948309,
-      "learning_rate": 1.9963183634476757e-05,
-      "loss": 0.6313,
-      "step": 10
-    },
-    {
-      "epoch": 0.1088929219600726,
-      "grad_norm": 0.38873067732428473,
-      "learning_rate": 1.985300562686109e-05,
-      "loss": 0.5461,
-      "step": 20
-    },
-    {
-      "epoch": 0.16333938294010888,
-      "grad_norm": 0.3356665320772086,
-      "learning_rate": 1.9670277247913205e-05,
-      "loss": 0.5357,
-      "step": 30
-    },
-    {
-      "epoch": 0.2177858439201452,
-      "grad_norm": 0.3461983668544632,
-      "learning_rate": 1.941634397659126e-05,
-      "loss": 0.5269,
-      "step": 40
-    },
-    {
-      "epoch": 0.27223230490018147,
-      "grad_norm": 0.32613528937825276,
-      "learning_rate": 1.909307559292236e-05,
-      "loss": 0.5195,
-      "step": 50
-    },
-    {
-      "epoch": 0.32667876588021777,
-      "grad_norm": 0.36288090303738013,
-      "learning_rate": 1.8702852410301556e-05,
-      "loss": 0.5296,
-      "step": 60
-    },
-    {
-      "epoch": 0.3811252268602541,
-      "grad_norm": 0.34412368424241435,
-      "learning_rate": 1.8248547748594246e-05,
-      "loss": 0.5077,
-      "step": 70
-    },
-    {
-      "epoch": 0.4355716878402904,
-      "grad_norm": 0.3623487490391009,
-      "learning_rate": 1.77335067770973e-05,
-      "loss": 0.518,
-      "step": 80
-    },
-    {
-      "epoch": 0.4900181488203267,
-      "grad_norm": 0.352530554726309,
-      "learning_rate": 1.7161521883143936e-05,
-      "loss": 0.5148,
-      "step": 90
-    },
-    {
-      "epoch": 0.5444646098003629,
-      "grad_norm": 0.33271158256626093,
-      "learning_rate": 1.653680474772006e-05,
-      "loss": 0.512,
-      "step": 100
-    },
-    {
-      "epoch": 0.5989110707803993,
-      "grad_norm": 0.3411018751679214,
-      "learning_rate": 1.586395533370696e-05,
-      "loss": 0.5029,
-      "step": 110
-    },
-    {
-      "epoch": 0.6533575317604355,
-      "grad_norm": 0.3194587165760062,
-      "learning_rate": 1.5147928015098309e-05,
-      "loss": 0.5089,
-      "step": 120
-    },
-    {
-      "epoch": 0.7078039927404719,
-      "grad_norm": 0.3254055350803121,
-      "learning_rate": 1.4393995096591415e-05,
-      "loss": 0.5084,
-      "step": 130
-    },
-    {
-      "epoch": 0.7622504537205081,
-      "grad_norm": 0.3258921051684478,
-      "learning_rate": 1.3607707992167836e-05,
-      "loss": 0.4943,
-      "step": 140
-    },
-    {
-      "epoch": 0.8166969147005445,
-      "grad_norm": 0.3270931532081039,
-      "learning_rate": 1.2794856348516095e-05,
-      "loss": 0.5068,
-      "step": 150
-    },
-    {
-      "epoch": 0.8711433756805808,
-      "grad_norm": 0.3230906659414158,
-      "learning_rate": 1.196142541428197e-05,
-      "loss": 0.5003,
-      "step": 160
-    },
-    {
-      "epoch": 0.925589836660617,
-      "grad_norm": 0.2935800627644772,
-      "learning_rate": 1.1113551969048088e-05,
-      "loss": 0.5053,
-      "step": 170
-    },
-    {
-      "epoch": 0.9800362976406534,
-      "grad_norm": 0.3326717159128385,
-      "learning_rate": 1.0257479136549889e-05,
-      "loss": 0.5017,
-      "step": 180
-    },
-    {
-      "epoch": 1.0353901996370236,
-      "grad_norm": 0.32878956222583294,
-      "learning_rate": 9.399510414850518e-06,
-      "loss": 0.4806,
-      "step": 190
-    },
-    {
-      "epoch": 1.08983666061706,
-      "grad_norm": 0.34757108365501066,
-      "learning_rate": 8.545963261963102e-06,
-      "loss": 0.4415,
-      "step": 200
-    },
-    {
-      "epoch": 1.144283121597096,
-      "grad_norm": 0.3284219242043158,
-      "learning_rate": 7.703122578682047e-06,
-      "loss": 0.4406,
-      "step": 210
-    },
-    {
-      "epoch": 1.1987295825771325,
-      "grad_norm": 0.32386273566803453,
-      "learning_rate": 6.877194431142055e-06,
-      "loss": 0.4345,
-      "step": 220
-    },
-    {
-      "epoch": 1.2531760435571688,
-      "grad_norm": 0.3142506822733221,
-      "learning_rate": 6.074260353858283e-06,
-      "loss": 0.4443,
-      "step": 230
-    },
-    {
-      "epoch": 1.3076225045372052,
-      "grad_norm": 0.3003800601330196,
-      "learning_rate": 5.300232569726805e-06,
-      "loss": 0.4329,
-      "step": 240
-    },
-    {
-      "epoch": 1.3620689655172413,
-      "grad_norm": 0.3069697265508909,
-      "learning_rate": 4.560810456712754e-06,
-      "loss": 0.4376,
-      "step": 250
-    },
-    {
-      "epoch": 1.4165154264972777,
-      "grad_norm": 0.293876545095534,
-      "learning_rate": 3.86143858177388e-06,
-      "loss": 0.4375,
-      "step": 260
-    },
-    {
-      "epoch": 1.470961887477314,
-      "grad_norm": 0.30476524182675285,
-      "learning_rate": 3.207266611027069e-06,
-      "loss": 0.439,
-      "step": 270
-    },
-    {
-      "epoch": 1.5254083484573502,
-      "grad_norm": 0.30324429690826615,
-      "learning_rate": 2.6031113913503337e-06,
-      "loss": 0.4437,
-      "step": 280
-    },
-    {
-      "epoch": 1.5798548094373865,
-      "grad_norm": 0.29418290787317664,
-      "learning_rate": 2.0534214826237486e-06,
-      "loss": 0.4413,
-      "step": 290
-    },
-    {
-      "epoch": 1.634301270417423,
-      "grad_norm": 0.2916751951846426,
-      "learning_rate": 1.5622444017681438e-06,
-      "loss": 0.4321,
-      "step": 300
-    },
-    {
-      "epoch": 1.6887477313974593,
-      "grad_norm": 0.2931814539684998,
-      "learning_rate": 1.1331968197725985e-06,
-      "loss": 0.4335,
-      "step": 310
-    },
-    {
-      "epoch": 1.7431941923774956,
-      "grad_norm": 0.2911760868779227,
-      "learning_rate": 7.694379311582401e-07,
-      "loss": 0.437,
-      "step": 320
-    },
-    {
-      "epoch": 1.7976406533575318,
-      "grad_norm": 0.3025253032847626,
-      "learning_rate": 4.73646191966175e-07,
-      "loss": 0.4404,
-      "step": 330
-    },
-    {
-      "epoch": 1.852087114337568,
-      "grad_norm": 0.2836449089434229,
-      "learning_rate": 2.479995975541749e-07,
-      "loss": 0.4364,
-      "step": 340
-    },
-    {
-      "epoch": 1.9065335753176043,
-      "grad_norm": 0.2777013740756467,
-      "learning_rate": 9.415964542203059e-08,
-      "loss": 0.422,
-      "step": 350
-    },
-    {
-      "epoch": 1.9609800362976406,
-      "grad_norm": 0.29069644830400626,
-      "learning_rate": 1.325910115169471e-08,
-      "loss": 0.4297,
-      "step": 360
-    },
-    {
-      "epoch": 1.9936479128856623,
-      "step": 366,
-      "total_flos": 192523449925632.0,
-      "train_loss": 0.47888606233023556,
-      "train_runtime": 10712.2216,
-      "train_samples_per_second": 9.875,
-      "train_steps_per_second": 0.034
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 366,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 400,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 192523449925632.0,
-  "train_batch_size": 6,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5bff2f2a55e5e287584c6c848ef23be2862cfb47d6614fbf6580562c88c552ca
-size 7224