Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca719f1f88c169c20fd2954d2447e8cad4579301a34f33c7b415d1cc5ead674
+oid sha256:161e892e2db27d1ead9f9d155f56ff17be5911b49260df19fe3a8b7254e8d210
 size 2235481556

runs/Mar05_13-04-17_g04/events.out.tfevents.1709640258.g04.2705734.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11896918310b01755d959b7b02771604f588250fad4f5f698a8c8a26c9ddd08
-size 8754
+oid sha256:53279b552e90ddce1a4a691a6262b2c0ff461675bae0124624027c9ca1a54018
+size 9383

runs/Mar05_13-37-03_g04/events.out.tfevents.1709642225.g04.2708531.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6775bb31608227228d62e550e7ee72575a991a50e76dff1c280c814da79b4e
+size 5609

tmp-checkpoint-3500/config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.15,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-A",
+    "2": "I-A",
+    "3": "B-G",
+    "4": "I-G",
+    "5": "B-I",
+    "6": "I-I",
+    "7": "B-M",
+    "8": "I-M",
+    "9": "B-N",
+    "10": "I-N",
+    "11": "B-O",
+    "12": "I-O",
+    "13": "B-P",
+    "14": "I-P",
+    "15": "B-T",
+    "16": "I-T"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-A": 1,
+    "B-G": 3,
+    "B-I": 5,
+    "B-M": 7,
+    "B-N": 9,
+    "B-O": 11,
+    "B-P": 13,
+    "B-T": 15,
+    "I-A": 2,
+    "I-G": 4,
+    "I-I": 6,
+    "I-M": 8,
+    "I-N": 10,
+    "I-O": 12,
+    "I-P": 14,
+    "I-T": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

tmp-checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9161f548ad61cb5f9d3710f4818d2da8a5d4ba7df0a90b315fe58069914bbda1
+size 2235481556

tmp-checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc4b71a6b5e4a9a041884baf35bfe56c53c931a73f39274d9433e3e87b48c38
+size 4471196863

tmp-checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f5658fac6eeafc6d20f933ab264b1fd3ec15e67373eb025e218928698c59b1
+size 14244

tmp-checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacf60dbd73a2432e4bfc0ce9771c15e35e7524b2db503a497e03a02cb9e5c34
+size 1064

tmp-checkpoint-3500/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tmp-checkpoint-3500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tmp-checkpoint-3500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

tmp-checkpoint-3500/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>"
+}

tmp-checkpoint-3500/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.8486549707602338,
+  "best_model_checkpoint": "models/CNEC2_0_Supertypes_xlm-roberta-large/checkpoint-3500",
+  "epoch": 7.777777777777778,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.2917,
+      "step": 500
+    },
+    {
+      "epoch": 1.11,
+      "eval_accuracy": 0.9599304650152107,
+      "eval_f1": 0.7754179846362405,
+      "eval_loss": 0.15004079043865204,
+      "eval_precision": 0.7289719626168224,
+      "eval_recall": 0.8281853281853282,
+      "eval_runtime": 4.6975,
+      "eval_samples_per_second": 191.59,
+      "eval_steps_per_second": 12.134,
+      "step": 500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.1372,
+      "step": 1000
+    },
+    {
+      "epoch": 2.22,
+      "eval_accuracy": 0.964855859771114,
+      "eval_f1": 0.8055303717135086,
+      "eval_loss": 0.13003575801849365,
+      "eval_precision": 0.7594017094017094,
+      "eval_recall": 0.8576254826254827,
+      "eval_runtime": 4.6975,
+      "eval_samples_per_second": 191.593,
+      "eval_steps_per_second": 12.134,
+      "step": 1000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0997,
+      "step": 1500
+    },
+    {
+      "epoch": 3.33,
+      "eval_accuracy": 0.969085904679125,
+      "eval_f1": 0.8323009864647856,
+      "eval_loss": 0.12816864252090454,
+      "eval_precision": 0.7931788369042414,
+      "eval_recall": 0.8754826254826255,
+      "eval_runtime": 4.7169,
+      "eval_samples_per_second": 190.802,
+      "eval_steps_per_second": 12.084,
+      "step": 1500
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.0761,
+      "step": 2000
+    },
+    {
+      "epoch": 4.44,
+      "eval_accuracy": 0.9693756337824134,
+      "eval_f1": 0.8434682080924855,
+      "eval_loss": 0.13885976374149323,
+      "eval_precision": 0.8095872170439414,
+      "eval_recall": 0.8803088803088803,
+      "eval_runtime": 4.7114,
+      "eval_samples_per_second": 191.027,
+      "eval_steps_per_second": 12.098,
+      "step": 2000
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0629,
+      "step": 2500
+    },
+    {
+      "epoch": 5.56,
+      "eval_accuracy": 0.9691438504997827,
+      "eval_f1": 0.844465203176086,
+      "eval_loss": 0.1371108740568161,
+      "eval_precision": 0.8180995475113122,
+      "eval_recall": 0.8725868725868726,
+      "eval_runtime": 4.6978,
+      "eval_samples_per_second": 191.581,
+      "eval_steps_per_second": 12.133,
+      "step": 2500
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0459,
+      "step": 3000
+    },
+    {
+      "epoch": 6.67,
+      "eval_accuracy": 0.9691148775894539,
+      "eval_f1": 0.842691415313225,
+      "eval_loss": 0.15476708114147186,
+      "eval_precision": 0.8114387846291331,
+      "eval_recall": 0.8764478764478765,
+      "eval_runtime": 4.7025,
+      "eval_samples_per_second": 191.386,
+      "eval_steps_per_second": 12.121,
+      "step": 3000
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0384,
+      "step": 3500
+    },
+    {
+      "epoch": 7.78,
+      "eval_accuracy": 0.9687672026655078,
+      "eval_f1": 0.8486549707602338,
+      "eval_loss": 0.16143788397312164,
+      "eval_precision": 0.8234226055379028,
+      "eval_recall": 0.8754826254826255,
+      "eval_runtime": 4.7237,
+      "eval_samples_per_second": 190.529,
+      "eval_steps_per_second": 12.067,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0236315472473384e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb1063a3cba5656b5d199bb19124128f2bc0d80293264bdd587e50dc52cd216
+size 4728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb1063a3cba5656b5d199bb19124128f2bc0d80293264bdd587e50dc52cd216
+oid sha256:ff2597b0c209a1978f083f12133803ede44586aeb35038ea397ad91f4e2df165
 size 4728