Training in progress, epoch 1

config.json

@@ -8,7 +8,7 @@
   "classifier_dropout": null,
   "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.4,
+  "hidden_dropout_prob": 0.25,
   "hidden_size": 1024,
   "id2label": {
     "0": "O",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4680459157412298d93395ef5f003554d765a9bff4da0861248a75ae8e04c709
+oid sha256:f09d8d496ae081bf04ca22ff4ae34ccfe0eaefbcdf2bbe50c822c39e19052ba0
 size 2235760364

tmp-checkpoint-14088/config.json

@@ -0,0 +1,202 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.4,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-ah",
+    "2": "I-ah",
+    "3": "B-at",
+    "4": "I-at",
+    "5": "B-az",
+    "6": "I-az",
+    "7": "B-g_",
+    "8": "I-g_",
+    "9": "B-gc",
+    "10": "I-gc",
+    "11": "B-gh",
+    "12": "I-gh",
+    "13": "B-gl",
+    "14": "I-gl",
+    "15": "B-gp",
+    "16": "I-gp",
+    "17": "B-gq",
+    "18": "I-gq",
+    "19": "B-gr",
+    "20": "I-gr",
+    "21": "B-gs",
+    "22": "I-gs",
+    "23": "B-gt",
+    "24": "I-gt",
+    "25": "B-gu",
+    "26": "I-gu",
+    "27": "B-i_",
+    "28": "I-i_",
+    "29": "B-ia",
+    "30": "I-ia",
+    "31": "B-ic",
+    "32": "I-ic",
+    "33": "B-if",
+    "34": "I-if",
+    "35": "B-io",
+    "36": "I-io",
+    "37": "B-mn",
+    "38": "I-mn",
+    "39": "B-mt",
+    "40": "I-mt",
+    "41": "B-mr",
+    "42": "I-mr",
+    "43": "B-o_",
+    "44": "I-o_",
+    "45": "B-oa",
+    "46": "I-oa",
+    "47": "B-oc",
+    "48": "I-oc",
+    "49": "B-oe",
+    "50": "I-oe",
+    "51": "B-om",
+    "52": "I-om",
+    "53": "B-op",
+    "54": "I-op",
+    "55": "B-or",
+    "56": "I-or",
+    "57": "B-p_",
+    "58": "I-p_",
+    "59": "B-pb",
+    "60": "I-pb",
+    "61": "B-pc",
+    "62": "I-pc",
+    "63": "B-pd",
+    "64": "I-pd",
+    "65": "B-pf",
+    "66": "I-pf",
+    "67": "B-pm",
+    "68": "I-pm",
+    "69": "B-pp",
+    "70": "I-pp",
+    "71": "B-ps",
+    "72": "I-ps",
+    "73": "B-td",
+    "74": "I-td",
+    "75": "B-tf",
+    "76": "I-tf",
+    "77": "B-th",
+    "78": "I-th",
+    "79": "B-ti",
+    "80": "I-ti",
+    "81": "B-tm",
+    "82": "I-tm",
+    "83": "B-ty",
+    "84": "I-ty"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-ah": 1,
+    "B-at": 3,
+    "B-az": 5,
+    "B-g_": 7,
+    "B-gc": 9,
+    "B-gh": 11,
+    "B-gl": 13,
+    "B-gp": 15,
+    "B-gq": 17,
+    "B-gr": 19,
+    "B-gs": 21,
+    "B-gt": 23,
+    "B-gu": 25,
+    "B-i_": 27,
+    "B-ia": 29,
+    "B-ic": 31,
+    "B-if": 33,
+    "B-io": 35,
+    "B-mn": 37,
+    "B-mr": 41,
+    "B-mt": 39,
+    "B-o_": 43,
+    "B-oa": 45,
+    "B-oc": 47,
+    "B-oe": 49,
+    "B-om": 51,
+    "B-op": 53,
+    "B-or": 55,
+    "B-p_": 57,
+    "B-pb": 59,
+    "B-pc": 61,
+    "B-pd": 63,
+    "B-pf": 65,
+    "B-pm": 67,
+    "B-pp": 69,
+    "B-ps": 71,
+    "B-td": 73,
+    "B-tf": 75,
+    "B-th": 77,
+    "B-ti": 79,
+    "B-tm": 81,
+    "B-ty": 83,
+    "I-ah": 2,
+    "I-at": 4,
+    "I-az": 6,
+    "I-g_": 8,
+    "I-gc": 10,
+    "I-gh": 12,
+    "I-gl": 14,
+    "I-gp": 16,
+    "I-gq": 18,
+    "I-gr": 20,
+    "I-gs": 22,
+    "I-gt": 24,
+    "I-gu": 26,
+    "I-i_": 28,
+    "I-ia": 30,
+    "I-ic": 32,
+    "I-if": 34,
+    "I-io": 36,
+    "I-mn": 38,
+    "I-mr": 42,
+    "I-mt": 40,
+    "I-o_": 44,
+    "I-oa": 46,
+    "I-oc": 48,
+    "I-oe": 50,
+    "I-om": 52,
+    "I-op": 54,
+    "I-or": 56,
+    "I-p_": 58,
+    "I-pb": 60,
+    "I-pc": 62,
+    "I-pd": 64,
+    "I-pf": 66,
+    "I-pm": 68,
+    "I-pp": 70,
+    "I-ps": 72,
+    "I-td": 74,
+    "I-tf": 76,
+    "I-th": 78,
+    "I-ti": 80,
+    "I-tm": 82,
+    "I-ty": 84,
+    "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-14088/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9ef5ec0ced919b674066492dfd945071c1e37431302dca4d66de17c698a27c
+size 2235760364

tmp-checkpoint-14088/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91deef4f829b7a5d87b87e6805f61868a9cadc4ae4dc7489aced83ac9da2742a
+size 4471754431

tmp-checkpoint-14088/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9db8b2d74df15a2e8d1b0931dd5e6f4e66a644079c6db86e137a2efdacb84c
+size 14244

tmp-checkpoint-14088/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91728cdb58910e6dd029ad2a96685ab110fdaa247c8482958b98a5cf8dc5ef0
+size 1064

tmp-checkpoint-14088/sentencepiece.bpe.model

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

tmp-checkpoint-14088/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-14088/tokenizer.json

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

tmp-checkpoint-14088/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_prefix_space": true,
+  "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-14088/trainer_state.json

@@ -0,0 +1,261 @@
+{
+  "best_metric": 0.8202488202488203,
+  "best_model_checkpoint": "models/CNEC1_1_xlm-roberta-large/checkpoint-14088",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 14088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9716070414537196e-05,
+      "loss": 1.3576,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.943214082907439e-05,
+      "loss": 1.0705,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.9148211243611586e-05,
+      "loss": 0.8038,
+      "step": 1500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.886428165814878e-05,
+      "loss": 0.6997,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9015184043093016,
+      "eval_f1": 0.634045200082936,
+      "eval_loss": 0.47193410992622375,
+      "eval_precision": 0.5977326035965598,
+      "eval_recall": 0.6750551876379691,
+      "eval_runtime": 5.8847,
+      "eval_samples_per_second": 99.751,
+      "eval_steps_per_second": 49.96,
+      "step": 2348
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.8580352072685975e-05,
+      "loss": 0.6216,
+      "step": 2500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.829642248722317e-05,
+      "loss": 0.5899,
+      "step": 3000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.8012492901760365e-05,
+      "loss": 0.5431,
+      "step": 3500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.772856331629756e-05,
+      "loss": 0.5252,
+      "step": 4000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.7444633730834754e-05,
+      "loss": 0.4756,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9339162340450446,
+      "eval_f1": 0.7610769556921773,
+      "eval_loss": 0.3348279595375061,
+      "eval_precision": 0.7320554649265906,
+      "eval_recall": 0.7924944812362031,
+      "eval_runtime": 5.9019,
+      "eval_samples_per_second": 99.459,
+      "eval_steps_per_second": 49.814,
+      "step": 4696
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.716070414537195e-05,
+      "loss": 0.4742,
+      "step": 5000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.6876774559909144e-05,
+      "loss": 0.4196,
+      "step": 5500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.659284497444634e-05,
+      "loss": 0.4043,
+      "step": 6000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.6308915388983533e-05,
+      "loss": 0.46,
+      "step": 6500
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.6024985803520728e-05,
+      "loss": 0.3944,
+      "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9385612240914946,
+      "eval_f1": 0.7840034217279727,
+      "eval_loss": 0.30876749753952026,
+      "eval_precision": 0.7602654500207383,
+      "eval_recall": 0.8092715231788079,
+      "eval_runtime": 5.8788,
+      "eval_samples_per_second": 99.85,
+      "eval_steps_per_second": 50.01,
+      "step": 7044
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.5741056218057923e-05,
+      "loss": 0.3589,
+      "step": 7500
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 1.5457126632595118e-05,
+      "loss": 0.3685,
+      "step": 8000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.5173197047132312e-05,
+      "loss": 0.3812,
+      "step": 8500
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.4889267461669507e-05,
+      "loss": 0.3682,
+      "step": 9000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9458995276942894,
+      "eval_f1": 0.8104856037816931,
+      "eval_loss": 0.2806117832660675,
+      "eval_precision": 0.7894516534114693,
+      "eval_recall": 0.8326710816777042,
+      "eval_runtime": 5.9429,
+      "eval_samples_per_second": 98.773,
+      "eval_steps_per_second": 49.47,
+      "step": 9392
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 1.4605337876206702e-05,
+      "loss": 0.3384,
+      "step": 9500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 1.4321408290743897e-05,
+      "loss": 0.3283,
+      "step": 10000
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 1.4037478705281091e-05,
+      "loss": 0.293,
+      "step": 10500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.3753549119818286e-05,
+      "loss": 0.3297,
+      "step": 11000
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 1.346961953435548e-05,
+      "loss": 0.331,
+      "step": 11500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9441039853233928,
+      "eval_f1": 0.8113004097476818,
+      "eval_loss": 0.2846803665161133,
+      "eval_precision": 0.7930016863406408,
+      "eval_recall": 0.8304635761589404,
+      "eval_runtime": 6.1995,
+      "eval_samples_per_second": 94.685,
+      "eval_steps_per_second": 47.423,
+      "step": 11740
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 1.3185689948892676e-05,
+      "loss": 0.3012,
+      "step": 12000
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 1.2901760363429869e-05,
+      "loss": 0.3,
+      "step": 12500
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 1.2617830777967067e-05,
+      "loss": 0.2906,
+      "step": 13000
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 1.2333901192504261e-05,
+      "loss": 0.2722,
+      "step": 13500
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 1.2049971607041454e-05,
+      "loss": 0.2882,
+      "step": 14000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9443772200320075,
+      "eval_f1": 0.8202488202488203,
+      "eval_loss": 0.2983391284942627,
+      "eval_precision": 0.7976637463496037,
+      "eval_recall": 0.844150110375276,
+      "eval_runtime": 5.8822,
+      "eval_samples_per_second": 99.793,
+      "eval_steps_per_second": 49.981,
+      "step": 14088
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 35220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 3074016120337854.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-14088/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8b926a569cc8dfe6413032865c13f21937df780baf481be0cd8e8e635836c7
+size 4728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b926a569cc8dfe6413032865c13f21937df780baf481be0cd8e8e635836c7
+oid sha256:26d3e140e215160a384e862c60895f5d329429f13fc06e65c51efbadb0afb6e1
 size 4728