Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

checkpoint-500/config.json

@@ -36,6 +36,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.26.1",
   "vocab_size": 30522
 }

checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79107900dee3a0a47f8f41075754fb1f905582f0a89edf90661e6b5635e4d443
-size 535751866
+oid sha256:b15638192ed1ab5f901937fcdeff09bdaff65bbf9df84d41383f10b37649104f
+size 535726074

checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2655f584bf43ef09092eb24e1c5daa8c6dd9b54fa33dd5c40f3eb5f58c35f541
+oid sha256:2636a72cc04b1941d8d9563a63e832834ffd3f31620a26415d097a7583e6f101
 size 14244

checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a918d281b0abb653538e3ad48219237d3e088ca744ffa6572595a0bb59b98300
+oid sha256:0f29365aa09523198baebebe95ffb09ad5f00205c944d1df89a9000244c3bc23
 size 1064

checkpoint-500/tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

checkpoint-500/tokenizer_config.json

@@ -1,53 +1,12 @@
 {
-  "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": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",

checkpoint-500/trainer_state.json

@@ -2,7 +2,6 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 2.0,
-  "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -10,36 +9,30 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 4.321141242980957,
       "learning_rate": 1e-05,
-      "loss": 0.8368,
+      "loss": 0.8062,
       "step": 250
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.918,
-      "eval_f1": 0.9174870444742153,
-      "eval_loss": 0.3010673224925995,
-      "eval_runtime": 2.3173,
-      "eval_samples_per_second": 863.058,
-      "eval_steps_per_second": 13.809,
+      "eval_accuracy": 0.9115,
+      "eval_f1": 0.9100250703245248,
+      "eval_loss": 0.30541306734085083,
+      "eval_runtime": 2.0854,
+      "eval_samples_per_second": 959.028,
+      "eval_steps_per_second": 15.344,
       "step": 250
     },
     {
       "epoch": 2.0,
-      "grad_norm": 6.54923152923584,
       "learning_rate": 0.0,
-      "loss": 0.2473,
+      "loss": 0.2399,
       "step": 500
     }
   ],
-  "logging_steps": 250,
   "max_steps": 500,
-  "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "save_steps": 500,
   "total_flos": 720342861696000.0,
-  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72795a5881e67826ec5de6ca8939d6b70de19a8cb251762f8ad5cd5c5288f6a
-size 4920
+oid sha256:8aab1ebd59775323e68a4c1858081f20377944583fade8f5ddcd8279ba9773dd
+size 3960

config.json

@@ -36,6 +36,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.26.1",
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90219563e1b25db874c968af86efcc8444a0dfc2e9225c2ae1d2e860a9cccfd
+size 267868266

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -1,53 +1,12 @@
 {
-  "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": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72795a5881e67826ec5de6ca8939d6b70de19a8cb251762f8ad5cd5c5288f6a
-size 4920
+oid sha256:8aab1ebd59775323e68a4c1858081f20377944583fade8f5ddcd8279ba9773dd
+size 3960