Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "distilbert-base-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -33,6 +32,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.51.1",
   "vocab_size": 28996
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e68fd628f2354a6a657de268a85d88023f92d72b0575f8b18769ddf9cc28a15
+oid sha256:9da2b50d764ec4892615756f28b7f3791e58fcb1f4a7aaca85f3a762d620ba82
 size 263150840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c50dc24e634ed44e89d3f9744310f42352dc1a84846d6360a2351aceafe8904
+oid sha256:7c26ccda4cdd04b409b751e4c65644ed4b49bf18f5b451a594b6a214986bc2d3
 size 526363834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b90df5d61f2cf16876715eb8ad68783d2e9241e7463932793f4e217a880ced5
+oid sha256:7ade29898300bdfe6aa118e313dc4535c61d3ab3cb9471a30db0149ce92d1637
 size 14244

last-checkpoint/tokenizer_config.json

@@ -41,9 +41,10 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": false,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

last-checkpoint/trainer_state.json

@@ -1,5 +1,6 @@
 {
-  "best_metric": 0.7061901924276679,
+  "best_global_step": 815,
+  "best_metric": 0.6462251355534618,
   "best_model_checkpoint": "bert-emotion/checkpoint-815",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,27 +11,42 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.8416,
+      "grad_norm": 1.0934220552444458,
+      "learning_rate": 3.335378323108385e-05,
+      "loss": 0.8487,
       "step": 815
     },
     {
       "epoch": 1.0,
-      "eval_fscore": 0.7061901924276679,
-      "eval_loss": 0.7683064937591553,
-      "eval_precision": 0.7000145689951174,
-      "eval_recall": 0.7141334228293426,
-      "eval_runtime": 0.8695,
-      "eval_samples_per_second": 430.12,
-      "eval_steps_per_second": 108.105,
+      "eval_fscore": 0.6462251355534618,
+      "eval_loss": 0.901279866695404,
+      "eval_precision": 0.6936353805007801,
+      "eval_recall": 0.6374950356605054,
+      "eval_runtime": 0.6754,
+      "eval_samples_per_second": 553.712,
+      "eval_steps_per_second": 139.168,
       "step": 815
     }
   ],
   "logging_steps": 500,
   "max_steps": 2445,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 31692920583072.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 31727849756232.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2294a0df7e2df7fd066300ebcd07ab493a37e08d865146532978b0b09b32751a
-size 4536
+oid sha256:f557261a28af4f326474ddcf104c41422d034dc108f102149ac2cbda2093deac
+size 5304