Upload folder using huggingface_hub

checkpoint-60/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "vocab_size": 30522
+}

checkpoint-60/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60d012f2ffc4e98b6a73a23cba6b48e950612ead91cb136a2448cb238ad9b3b
+size 267832560

checkpoint-60/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4adaa201633b91242a4d05660189a3fce4c52c8bc83f5005733018fdae21ec2
+size 535724410

checkpoint-60/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a119a464492964f206274d8c2cfc18a0c7b06c76c10f05f3e33943615fdd62
+size 13990

checkpoint-60/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90979e82e94259c1d6f68c5ef23bb17c7019c0bbe3422cf6d46e9cdac106c874
+size 1064

checkpoint-60/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.85,
+      "eval_loss": 0.3328920304775238,
+      "eval_runtime": 19.3098,
+      "eval_samples_per_second": 2.071,
+      "eval_steps_per_second": 0.259,
+      "step": 20
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.1108067035675049,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5935,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.36818569898605347,
+      "eval_runtime": 19.4153,
+      "eval_samples_per_second": 2.06,
+      "eval_steps_per_second": 0.258,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.13847129046916962,
+      "learning_rate": 0.0,
+      "loss": 0.1087,
+      "step": 60
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 63584351354880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-60/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e464a2625faac84ce28854b56aa22de40827a7f85f1a107d48ed87dd3b21ad4e
+size 5176

checkpoint-87/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "vocab_size": 30522
+}

checkpoint-87/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a349c1e5d4576d99c61c5ead350f35b91a4fbb43cf87cfca993c4dfe810e20e
+size 267832560

checkpoint-87/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e2aa63acc3789e5a7f3727f9899c9bb65506fef07d9145ce744d3409f9e587
+size 535724410

checkpoint-87/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38389f072ec0d30f99df13707be5ca1cb3d208dba29a5dccc9e3baee97162213
+size 13990

checkpoint-87/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32b93c709a450374c8a5d9ec8dd207b166bccf542e023947107eae5bd3a09cb
+size 1064

checkpoint-87/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 87,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.2707670331001282,
+      "eval_runtime": 19.5658,
+      "eval_samples_per_second": 2.044,
+      "eval_steps_per_second": 0.256,
+      "step": 29
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 4.015429496765137,
+      "learning_rate": 3.275862068965517e-05,
+      "loss": 0.7211,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.34923750162124634,
+      "eval_runtime": 19.9116,
+      "eval_samples_per_second": 2.009,
+      "eval_steps_per_second": 0.251,
+      "step": 58
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.996155321598053,
+      "learning_rate": 1.5517241379310346e-05,
+      "loss": 0.1894,
+      "step": 60
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 87,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 90210298484736.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-87/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e464a2625faac84ce28854b56aa22de40827a7f85f1a107d48ed87dd3b21ad4e
+size 5176

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a349c1e5d4576d99c61c5ead350f35b91a4fbb43cf87cfca993c4dfe810e20e
+size 267832560

runs/Jul09_19-53-12_DESKTOP-O6LJL2H/events.out.tfevents.1720576420.DESKTOP-O6LJL2H.5552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72dd11f93110a659fb32463346dc5c2ab88113b855925773493a79e2986d4e3
+size 6718

runs/Jul09_19-53-12_DESKTOP-O6LJL2H/events.out.tfevents.1720581251.DESKTOP-O6LJL2H.5552.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bf80709b1aa11b47f65921e7c8e05fd3f4e529a44cd2670335dddb35eaa9ef
+size 6718

runs/Jul09_19-53-12_DESKTOP-O6LJL2H/events.out.tfevents.1720582067.DESKTOP-O6LJL2H.5552.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815fa1a110d9220935fb3d2a36f95f6559a90223f93ef3c1abbbe99fb0e087ed
+size 405