Push tokenizer and the last model checkpoints

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "classifier_dropout": 0.3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdccb9a1326282ce172abc05046d8868d5a53154be6b0905220f3aa58f59e7f1
+size 737722356

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d635017647497837523dbad9bcb82e9b738f9c5e7a0ffa17b00200367a854171
+size 1475564538

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793360edb51cd3988eb774af5dc5baade22c92a0feab952b0442e9f0363feb8a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1d4b62c8569136ac533bea6bd4720b618f75d960825875ab003fa764178d75
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.7336740904072855,
+  "best_model_checkpoint": "/shevtsov/sent_results/checkpoint-55176",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 55176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.982656478881836,
+      "learning_rate": 5e-06,
+      "loss": 0.278,
+      "step": 6897
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6962722394803728,
+      "eval_f1": 0.6954934097978532,
+      "eval_loss": 0.27303698658943176,
+      "eval_precision": 0.7032410224368593,
+      "eval_recall": 0.6962722394803728,
+      "eval_runtime": 235.2201,
+      "eval_samples_per_second": 90.324,
+      "eval_steps_per_second": 11.292,
+      "step": 6897
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.829893112182617,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.1974,
+      "step": 13794
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7188176597947848,
+      "eval_f1": 0.7159777515871979,
+      "eval_loss": 0.2562166452407837,
+      "eval_precision": 0.7156618605155758,
+      "eval_recall": 0.7188176597947848,
+      "eval_runtime": 235.187,
+      "eval_samples_per_second": 90.337,
+      "eval_steps_per_second": 11.293,
+      "step": 13794
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.553038597106934,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 0.172,
+      "step": 20691
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7296902946436976,
+      "eval_f1": 0.7289604788993475,
+      "eval_loss": 0.27564719319343567,
+      "eval_precision": 0.7285244419417612,
+      "eval_recall": 0.7296902946436976,
+      "eval_runtime": 235.2108,
+      "eval_samples_per_second": 90.327,
+      "eval_steps_per_second": 11.292,
+      "step": 20691
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.199881076812744,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.154,
+      "step": 27588
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7309611220935706,
+      "eval_f1": 0.7313527175830589,
+      "eval_loss": 0.3117690682411194,
+      "eval_precision": 0.7331236097784076,
+      "eval_recall": 0.7309611220935706,
+      "eval_runtime": 235.1385,
+      "eval_samples_per_second": 90.355,
+      "eval_steps_per_second": 11.295,
+      "step": 27588
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.5583109855651855,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.1405,
+      "step": 34485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7292196178104113,
+      "eval_f1": 0.7306905410800046,
+      "eval_loss": 0.3434309661388397,
+      "eval_precision": 0.7340143377006256,
+      "eval_recall": 0.7292196178104113,
+      "eval_runtime": 235.1135,
+      "eval_samples_per_second": 90.365,
+      "eval_steps_per_second": 11.297,
+      "step": 34485
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.269964218139648,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.1292,
+      "step": 41382
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.728372399510496,
+      "eval_f1": 0.7270264813978528,
+      "eval_loss": 0.37885233759880066,
+      "eval_precision": 0.7276053091596871,
+      "eval_recall": 0.728372399510496,
+      "eval_runtime": 235.0304,
+      "eval_samples_per_second": 90.397,
+      "eval_steps_per_second": 11.301,
+      "step": 41382
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.499964714050293,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.1205,
+      "step": 48279
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7335969123599736,
+      "eval_f1": 0.7320317760805066,
+      "eval_loss": 0.4042453467845917,
+      "eval_precision": 0.7316491391334223,
+      "eval_recall": 0.7335969123599736,
+      "eval_runtime": 235.1289,
+      "eval_samples_per_second": 90.359,
+      "eval_steps_per_second": 11.296,
+      "step": 48279
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.1066179275512695,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 0.1145,
+      "step": 55176
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7338793184599454,
+      "eval_f1": 0.7336740904072855,
+      "eval_loss": 0.4205409288406372,
+      "eval_precision": 0.7335551105156711,
+      "eval_recall": 0.7338793184599454,
+      "eval_runtime": 235.1161,
+      "eval_samples_per_second": 90.364,
+      "eval_steps_per_second": 11.297,
+      "step": 55176
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 68970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.968525969553408e+17,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25bd04595533c4a434f13ac4e4cfbd167bcb4a00df5bd299061065f66a73363
+size 5304