Upload folder using huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "pGenomeOcean/GenomeOcean-100M",
+  "architectures": [
+    "MistralForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "pGenomeOcean/GenomeOcean-100M--configuration_mistral.MistralConfig",
+    "AutoModel": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralModel",
+    "AutoModelForCausalLM": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForCausalLM",
+    "AutoModelForMaskedLM": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForMaskedLM",
+    "AutoModelForSequenceClassification": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_causal": true,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "pad_token_id": 3,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 4096
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4f73e4913ffca2984a45bddfbf3ca91cc295d72b68c0e732d80648366342df
+size 465662960

optimizer_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbbd8b9626feb859b7c53b9fd1aeeadd487b6303e94fd6316eb5fc5d1635f9d
+size 931398901

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "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": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.5273802876472473,
+  "best_model_checkpoint": "output_pipe/prom_300_tata/origin/checkpoint-200",
+  "epoch": 4.0,
+  "eval_steps": 200,
+  "global_step": 308,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 16.239261627197266,
+      "learning_rate": 2.4767441860465116e-05,
+      "loss": 0.6103,
+      "step": 100
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 17.608713150024414,
+      "learning_rate": 1.313953488372093e-05,
+      "loss": 0.3571,
+      "step": 200
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "eval_accuracy": 0.7748776508972267,
+      "eval_f1": 0.7730506728478527,
+      "eval_loss": 0.5273802876472473,
+      "eval_matthews_correlation": 0.5791078000958941,
+      "eval_precision": 0.7973376111673984,
+      "eval_recall": 0.7819739511049428,
+      "eval_runtime": 0.1894,
+      "eval_samples_per_second": 3236.113,
+      "eval_steps_per_second": 52.791,
+      "step": 200
+    },
+    {
+      "epoch": 3.896103896103896,
+      "grad_norm": 13.628073692321777,
+      "learning_rate": 1.5116279069767443e-06,
+      "loss": 0.1742,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "step": 308,
+      "total_flos": 946505703112704.0,
+      "train_loss": 0.37393945765185665,
+      "train_runtime": 21.4272,
+      "train_samples_per_second": 915.473,
+      "train_steps_per_second": 14.374
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 308,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 946505703112704.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927a7bf0cf20defe98619d51419261abf4c2ba74b85631d0fa7a781765676e42
+size 5368