Training in progress, step 1500, checkpoint

checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716a82fb01b51ad7b5dab410fa2f97e40d6bbd4cb7dee758320fae07f2de6d08
+oid sha256:e6675f6d8390d2208ced782cc8a4161ed484190604e87016df84d9b71bf1716c
 size 437958648

checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16e5a100b9566c3a9324a69049f70c1950c19c1ac354ab4277d2b99a4b900c1
+oid sha256:42e5ad9be2ce49fbb8b7dc99f4bd67a01ade6a94c866e62336eaecebbb1c2323
 size 876032762

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1500/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 1500,
-  "best_metric": 0.9476439790575916,
+  "best_metric": 0.9545758183032732,
   "best_model_checkpoint": "C:\\Users\\Daniel\\Desktop\\GitHub\\NLPinitiative\\models\\dlsmallw\\NLPinitiative-Binary-Classification\\checkpoint-1500",
   "epoch": 1.632208922742111,
   "eval_steps": 500,
@@ -11,65 +11,65 @@
   "log_history": [
     {
       "epoch": 0.544069640914037,
-      "grad_norm": 0.14858652651309967,
+      "grad_norm": 17.53396987915039,
       "learning_rate": 1.637286906057309e-05,
-      "loss": 0.2817,
+      "loss": 0.2811,
       "step": 500
     },
     {
       "epoch": 0.544069640914037,
-      "eval_accuracy": 0.9330583756345178,
-      "eval_auprc": 0.2921851625500245,
-      "eval_auroc": 0.01756043735337567,
-      "eval_f1": 0.9321761491481839,
-      "eval_loss": 0.250454306602478,
-      "eval_precision": 0.90625,
-      "eval_recall": 0.9596293845135672,
-      "eval_runtime": 102.5806,
-      "eval_samples_per_second": 30.727,
-      "eval_steps_per_second": 3.841,
+      "eval_accuracy": 0.949238578680203,
+      "eval_auprc": 0.2945266340168414,
+      "eval_auroc": 0.015546624960699109,
+      "eval_f1": 0.946914399469144,
+      "eval_loss": 0.19298532605171204,
+      "eval_precision": 0.9564343163538874,
+      "eval_recall": 0.9375821287779238,
+      "eval_runtime": 102.1508,
+      "eval_samples_per_second": 30.856,
+      "eval_steps_per_second": 3.857,
       "step": 500
     },
     {
       "epoch": 1.088139281828074,
-      "grad_norm": 1.7654657363891602,
+      "grad_norm": 1.0602138042449951,
       "learning_rate": 1.2745738121146174e-05,
-      "loss": 0.1722,
+      "loss": 0.1844,
       "step": 1000
     },
     {
       "epoch": 1.088139281828074,
-      "eval_accuracy": 0.9479695431472082,
-      "eval_auprc": 0.29180260985958417,
-      "eval_auroc": 0.013246753142000309,
-      "eval_f1": 0.9453333333333334,
-      "eval_loss": 0.2592768967151642,
-      "eval_precision": 0.9523169912693082,
-      "eval_recall": 0.9384513567174056,
-      "eval_runtime": 102.9732,
-      "eval_samples_per_second": 30.61,
-      "eval_steps_per_second": 3.826,
+      "eval_accuracy": 0.9530456852791879,
+      "eval_auprc": 0.29439297154104793,
+      "eval_auroc": 0.013553767645090812,
+      "eval_f1": 0.9514435695538058,
+      "eval_loss": 0.19708991050720215,
+      "eval_precision": 0.9501965923984272,
+      "eval_recall": 0.9526938239159002,
+      "eval_runtime": 104.1259,
+      "eval_samples_per_second": 30.271,
+      "eval_steps_per_second": 3.784,
       "step": 1000
     },
     {
       "epoch": 1.632208922742111,
-      "grad_norm": 0.4014647901058197,
+      "grad_norm": 0.019807865843176842,
       "learning_rate": 9.11860718171926e-06,
-      "loss": 0.0946,
+      "loss": 0.0806,
       "step": 1500
     },
     {
       "epoch": 1.632208922742111,
-      "eval_accuracy": 0.949238578680203,
-      "eval_auprc": 0.29179891736469293,
-      "eval_auroc": 0.010873339568333138,
-      "eval_f1": 0.9476439790575916,
-      "eval_loss": 0.25160646438598633,
-      "eval_precision": 0.9372168284789644,
-      "eval_recall": 0.9583057577763071,
-      "eval_runtime": 103.2978,
-      "eval_samples_per_second": 30.514,
-      "eval_steps_per_second": 3.814,
+      "eval_accuracy": 0.9568527918781726,
+      "eval_auprc": 0.29427235149466713,
+      "eval_auroc": 0.011200752964697724,
+      "eval_f1": 0.9545758183032732,
+      "eval_loss": 0.23076476156711578,
+      "eval_precision": 0.9707880434782609,
+      "eval_recall": 0.9388961892247043,
+      "eval_runtime": 103.9447,
+      "eval_samples_per_second": 30.324,
+      "eval_steps_per_second": 3.79,
       "step": 1500
     }
   ],

checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29909eb692988507c7e2fe9dbaafabc7dfb2f1505ddb732d33ccf795d5cf3f37
+oid sha256:ba1c0cd83c87672929cbce8fc2ed371343bdb0fb899364dfc5bb23635f9b95ef
 size 5496