Training in progress, step 2400, checkpoint

checkpoint-2400/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
+  "architectures": [
+    "LiltForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "channel_shrink_ratio": 4,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Contact Info Section",
+    "1": "Education Section",
+    "2": "Experience Section",
+    "3": "Tech Skills Section",
+    "4": "Internship Section",
+    "5": "Soft Skills Section"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "model_type": "lilt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-2400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a4447c2dcab4ef4d3f9d31cc0b44b2046628d1a826694655fa839632bf5f13
+size 1134316848

checkpoint-2400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca96f93cae50a29bf3d0089534d1a01d4b5e30e07e6df2a466385c64b7962571
+size 2265894110

checkpoint-2400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda4b6ff1f67b7640f36ec3e40eb9a087843df1b2bb103372ead3033127da213
+size 14244

checkpoint-2400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4626a3647a44dc9ce549d969eb6c4d356c9a2662835d5650db19e1d483b913
+size 1064

checkpoint-2400/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

checkpoint-2400/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-2400/trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": 0.9064039408866996,
+  "best_model_checkpoint": "AAmeni/LILT-checkpoints/checkpoint-1600",
+  "epoch": 29.26829268292683,
+  "eval_steps": 200,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.4390243902439024,
+      "eval_accuracy": 0.9208400646203554,
+      "eval_f1": 0.8652657601977751,
+      "eval_loss": 0.29326215386390686,
+      "eval_precision": 0.875,
+      "eval_recall": 0.8557457212713936,
+      "eval_runtime": 10.0837,
+      "eval_samples_per_second": 4.165,
+      "eval_steps_per_second": 1.091,
+      "step": 200
+    },
+    {
+      "epoch": 4.878048780487805,
+      "eval_accuracy": 0.925686591276252,
+      "eval_f1": 0.8767123287671232,
+      "eval_loss": 0.3650479018688202,
+      "eval_precision": 0.8934010152284264,
+      "eval_recall": 0.8606356968215159,
+      "eval_runtime": 10.3053,
+      "eval_samples_per_second": 4.076,
+      "eval_steps_per_second": 1.067,
+      "step": 400
+    },
+    {
+      "epoch": 6.097560975609756,
+      "grad_norm": 15.58462905883789,
+      "learning_rate": 3.989837398373984e-05,
+      "loss": 0.3014,
+      "step": 500
+    },
+    {
+      "epoch": 7.317073170731708,
+      "eval_accuracy": 0.938610662358643,
+      "eval_f1": 0.8976572133168927,
+      "eval_loss": 0.382191926240921,
+      "eval_precision": 0.9054726368159204,
+      "eval_recall": 0.8899755501222494,
+      "eval_runtime": 9.3762,
+      "eval_samples_per_second": 4.479,
+      "eval_steps_per_second": 1.173,
+      "step": 600
+    },
+    {
+      "epoch": 9.75609756097561,
+      "eval_accuracy": 0.938610662358643,
+      "eval_f1": 0.8902589395807645,
+      "eval_loss": 0.4051755368709564,
+      "eval_precision": 0.8980099502487562,
+      "eval_recall": 0.882640586797066,
+      "eval_runtime": 8.2706,
+      "eval_samples_per_second": 5.078,
+      "eval_steps_per_second": 1.33,
+      "step": 800
+    },
+    {
+      "epoch": 12.195121951219512,
+      "grad_norm": 0.035131603479385376,
+      "learning_rate": 2.973577235772358e-05,
+      "loss": 0.0365,
+      "step": 1000
+    },
+    {
+      "epoch": 12.195121951219512,
+      "eval_accuracy": 0.938610662358643,
+      "eval_f1": 0.8932515337423313,
+      "eval_loss": 0.4668120741844177,
+      "eval_precision": 0.896551724137931,
+      "eval_recall": 0.8899755501222494,
+      "eval_runtime": 10.5119,
+      "eval_samples_per_second": 3.995,
+      "eval_steps_per_second": 1.046,
+      "step": 1000
+    },
+    {
+      "epoch": 14.634146341463415,
+      "eval_accuracy": 0.9434571890145396,
+      "eval_f1": 0.9009900990099009,
+      "eval_loss": 0.46639078855514526,
+      "eval_precision": 0.9122807017543859,
+      "eval_recall": 0.8899755501222494,
+      "eval_runtime": 9.1524,
+      "eval_samples_per_second": 4.589,
+      "eval_steps_per_second": 1.202,
+      "step": 1200
+    },
+    {
+      "epoch": 17.073170731707318,
+      "eval_accuracy": 0.9369951534733441,
+      "eval_f1": 0.8888888888888887,
+      "eval_loss": 0.4993242025375366,
+      "eval_precision": 0.8977556109725686,
+      "eval_recall": 0.8801955990220048,
+      "eval_runtime": 8.3567,
+      "eval_samples_per_second": 5.026,
+      "eval_steps_per_second": 1.316,
+      "step": 1400
+    },
+    {
+      "epoch": 18.29268292682927,
+      "grad_norm": 0.003389735473319888,
+      "learning_rate": 1.957317073170732e-05,
+      "loss": 0.0091,
+      "step": 1500
+    },
+    {
+      "epoch": 19.51219512195122,
+      "eval_accuracy": 0.9466882067851373,
+      "eval_f1": 0.9064039408866996,
+      "eval_loss": 0.47225338220596313,
+      "eval_precision": 0.913151364764268,
+      "eval_recall": 0.8997555012224939,
+      "eval_runtime": 9.4714,
+      "eval_samples_per_second": 4.434,
+      "eval_steps_per_second": 1.161,
+      "step": 1600
+    },
+    {
+      "epoch": 21.951219512195124,
+      "eval_accuracy": 0.9466882067851373,
+      "eval_f1": 0.905521472392638,
+      "eval_loss": 0.4826250672340393,
+      "eval_precision": 0.9088669950738916,
+      "eval_recall": 0.902200488997555,
+      "eval_runtime": 9.1048,
+      "eval_samples_per_second": 4.613,
+      "eval_steps_per_second": 1.208,
+      "step": 1800
+    },
+    {
+      "epoch": 24.390243902439025,
+      "grad_norm": 0.0026210923679172993,
+      "learning_rate": 9.410569105691056e-06,
+      "loss": 0.0004,
+      "step": 2000
+    },
+    {
+      "epoch": 24.390243902439025,
+      "eval_accuracy": 0.9466882067851373,
+      "eval_f1": 0.9041769041769042,
+      "eval_loss": 0.4790293276309967,
+      "eval_precision": 0.908641975308642,
+      "eval_recall": 0.8997555012224939,
+      "eval_runtime": 8.7609,
+      "eval_samples_per_second": 4.794,
+      "eval_steps_per_second": 1.256,
+      "step": 2000
+    },
+    {
+      "epoch": 26.829268292682926,
+      "eval_accuracy": 0.9466882067851373,
+      "eval_f1": 0.9041769041769042,
+      "eval_loss": 0.48069363832473755,
+      "eval_precision": 0.908641975308642,
+      "eval_recall": 0.8997555012224939,
+      "eval_runtime": 8.8195,
+      "eval_samples_per_second": 4.762,
+      "eval_steps_per_second": 1.247,
+      "step": 2200
+    },
+    {
+      "epoch": 29.26829268292683,
+      "eval_accuracy": 0.9466882067851373,
+      "eval_f1": 0.9041769041769042,
+      "eval_loss": 0.481835275888443,
+      "eval_precision": 0.908641975308642,
+      "eval_recall": 0.8997555012224939,
+      "eval_runtime": 9.4712,
+      "eval_samples_per_second": 4.434,
+      "eval_steps_per_second": 1.161,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1335170049638400.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34be5d922d8c64fe27e059e6d5b714f7fe0ab0877fec2e98c81a06b6f099c90
+size 5176