Training in progress, epoch 0, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,184 @@
+{
+  "_name_or_path": "ProtChem_ESM2_MolGen_CrossAttention",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "zjunlp/MolGen-large",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "BartForConditionalGeneration"
+    ],
+    "attention_dropout": 0.2,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.2,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "bart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 185
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "facebook/esm2_t33_650M_UR50D",
+    "add_cross_attention": false,
+    "architectures": [
+      "EsmForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "emb_layer_norm_before": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "esmfold_config": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "is_folding_model": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "mask_token_id": 32,
+    "max_length": 20,
+    "max_position_embeddings": 1026,
+    "min_length": 0,
+    "model_type": "esm",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 20,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 33,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "rotary",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "token_dropout": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_list": null,
+    "vocab_size": 33
+  },
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 1,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2"
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.45.2"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178530fd64f5986b87c68d4d25287bb190e9dc948cfcc39ffd1fb87d818d0756
+size 1713050034

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c0457a86b221612d25748e0aa0dda1614f71fb98d3fe0ccd5424e96cd0f7ee
+size 816721594

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557d974c659fd0bb715c14aad20461250be107b6c6982f3edba5bffe93c03d67
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f243675b1550a6e1c2b2f39823155e548c4797f1bca6374367a6b4525499792
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 9.923595644067973e-05,
+  "best_model_checkpoint": "ProtChem_ESM2_MolGen_Decoder/checkpoint-3972",
+  "epoch": 0.9999370633771791,
+  "eval_steps": 500,
+  "global_step": 3972,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12587324564163888,
+      "grad_norm": 0.044921875,
+      "learning_rate": 5e-06,
+      "loss": 0.0025,
+      "step": 500
+    },
+    {
+      "epoch": 0.25174649128327775,
+      "grad_norm": 0.01129150390625,
+      "learning_rate": 1e-05,
+      "loss": 0.0013,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3776197369249166,
+      "grad_norm": 0.01416015625,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0007,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5034929825665555,
+      "grad_norm": 0.0133056640625,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6293662282081943,
+      "grad_norm": 0.00872802734375,
+      "learning_rate": 1.9991330308838565e-05,
+      "loss": 0.0003,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7552394738498333,
+      "grad_norm": 0.020263671875,
+      "learning_rate": 1.996533626806322e-05,
+      "loss": 0.0003,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8811127194914721,
+      "grad_norm": 0.0024261474609375,
+      "learning_rate": 1.992206294973508e-05,
+      "loss": 0.0002,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9999370633771791,
+      "eval_loss": 9.923595644067973e-05,
+      "eval_runtime": 16805.4557,
+      "eval_samples_per_second": 15.226,
+      "eval_steps_per_second": 0.952,
+      "step": 3972
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 39720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6673341428273306e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd29142db25d1d3c994290a0ecd8ee5779d7ef21c12920f918ed3eebcda77bd
+size 5368