Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf4104191ae6939313ef1a6fdecaec553787a027b37fcc98d548b1790f4285d
+oid sha256:0892cb2e571b44d5942a997aa35ba80bcc592ce3bb5193d397e7316e056b6da0
 size 1112334200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea85e208a6daebb8bc69efdf1219ab403f97d9ba2a7aaf97f4393b3f6aba14a
+oid sha256:11a5d797ada3719b6ed3840e3ac9c82afabd94f3ba7665e77d016c8d3043ff1b
 size 4999698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f79b92daf8dc6726d9f2cc5c6eab1fd252a5802172ec5a5525da916ac369cb0
+oid sha256:454eadf6d869c3ef671c7d303b75726820b52ef79f805284b0badaa30198f863
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80b041a6a7fbae957f1842994caa209750d940772340214766874c83b0cd23c
+oid sha256:3cc0873bf8f3cb7a7665b601ff76bd0007b3fd5c53fba8a3b9f7c798f7147db4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4875621890547264,
-  "best_model_checkpoint": "/RuleBert-v0.0-k0/checkpoint-100",
-  "epoch": 0.22123893805309736,
+  "best_metric": 0.5050071530758227,
+  "best_model_checkpoint": "/RuleBert-v0.0-k0/checkpoint-400",
+  "epoch": 0.8849557522123894,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -53,6 +53,144 @@
       "eval_samples_per_second": 88.003,
       "eval_steps_per_second": 2.933,
       "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9987954562051724e-05,
+      "loss": 0.3947,
+      "step": 125
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.998265610184716e-05,
+      "loss": 0.3621,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.008333333333333333,
+      "eval_f1": 0.49451303155006865,
+      "eval_loss": 0.3777387738227844,
+      "eval_roc_auc": 0.6711924439197166,
+      "eval_runtime": 2.8618,
+      "eval_samples_per_second": 83.864,
+      "eval_steps_per_second": 2.795,
+      "step": 150
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.997639549247016e-05,
+      "loss": 0.3516,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 0.3541,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.025,
+      "eval_f1": 0.4965277777777778,
+      "eval_loss": 0.3699280917644501,
+      "eval_roc_auc": 0.6713821892393321,
+      "eval_runtime": 2.8771,
+      "eval_samples_per_second": 83.417,
+      "eval_steps_per_second": 2.781,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9960990332516875e-05,
+      "loss": 0.3512,
+      "step": 225
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 0.3322,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.0,
+      "eval_f1": 0.4925675675675676,
+      "eval_loss": 0.36883607506752014,
+      "eval_roc_auc": 0.6711713611064261,
+      "eval_runtime": 2.8206,
+      "eval_samples_per_second": 85.088,
+      "eval_steps_per_second": 2.836,
+      "step": 250
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9941745021174284e-05,
+      "loss": 0.3399,
+      "step": 275
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.9930684569549265e-05,
+      "loss": 0.3276,
+      "step": 300
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.008333333333333333,
+      "eval_f1": 0.49861495844875353,
+      "eval_loss": 0.36757946014404297,
+      "eval_roc_auc": 0.6724995783437342,
+      "eval_runtime": 2.7494,
+      "eval_samples_per_second": 87.293,
+      "eval_steps_per_second": 2.91,
+      "step": 300
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.991866697787626e-05,
+      "loss": 0.3467,
+      "step": 325
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.990569340443577e-05,
+      "loss": 0.3078,
+      "step": 350
+    },
+    {
+      "epoch": 0.77,
+      "eval_accuracy": 0.016666666666666666,
+      "eval_f1": 0.5012285012285013,
+      "eval_loss": 0.367951363325119,
+      "eval_roc_auc": 0.6728632568729971,
+      "eval_runtime": 2.7213,
+      "eval_samples_per_second": 88.192,
+      "eval_steps_per_second": 2.94,
+      "step": 350
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.989176509964781e-05,
+      "loss": 0.3211,
+      "step": 375
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.3293,
+      "step": 400
+    },
+    {
+      "epoch": 0.88,
+      "eval_accuracy": 0.0375,
+      "eval_f1": 0.5050071530758227,
+      "eval_loss": 0.36856791377067566,
+      "eval_roc_auc": 0.6734061393152301,
+      "eval_runtime": 2.704,
+      "eval_samples_per_second": 88.757,
+      "eval_steps_per_second": 2.959,
+      "step": 400
     }
   ],
   "logging_steps": 25,
@@ -60,7 +198,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 18,
   "save_steps": 100,
-  "total_flos": 210568219852800.0,
+  "total_flos": 842272879411200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null