Training in progress, step 1000, checkpoint

checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b636fa03a865e058e1317485bada1b817430fa6fd2646090f7abef263f1af
+oid sha256:e1e167bdd7d8f3d3df783dc6da538cb061c2b1a4aede4109829840cc9b6bfa94
 size 437958648

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9199a88c435e0f15b4d79df590d5a2b106cdbbc029466ad65e1b4070521dc0c2
+oid sha256:c170a993eefc702b0c1daf7693a4d23fb2dfca973ca1ee25d074b1aee57828f4
 size 876032762

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/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-1000/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 1000,
-  "best_metric": 0.9453333333333334,
+  "best_metric": 0.9514435695538058,
   "best_model_checkpoint": "C:\\Users\\Daniel\\Desktop\\GitHub\\NLPinitiative\\models\\dlsmallw\\NLPinitiative-Binary-Classification\\checkpoint-1000",
   "epoch": 1.088139281828074,
   "eval_steps": 500,
@@ -11,44 +11,44 @@
   "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
     }
   ],

checkpoint-1000/training_args.bin

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