Training in progress, epoch 3

config.json

@@ -3,72 +3,61 @@
     "EncoderDecoderModel"
   ],
   "decoder": {
-    "_name_or_path": "gayane/BARTSmiles",
-    "activation_dropout": 0.1,
-    "activation_function": "gelu",
-    "add_bias_logits": false,
+    "_name_or_path": "seyonec/PubChem10M_SMILES_BPE_450k",
     "add_cross_attention": true,
-    "add_final_layer_norm": false,
     "architectures": [
-      "BartModel"
+      "RobertaForMaskedLM"
     ],
-    "attention_dropout": 0.1,
+    "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
-    "classif_dropout": 0.1,
-    "classifier_dropout": 0.0,
+    "classifier_dropout": null,
     "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,
+    "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.1,
-    "early_stopping": true,
-    "encoder_attention_heads": 16,
-    "encoder_ffn_dim": 4096,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 12,
+    "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
-    "forced_bos_token_id": 0,
-    "forced_eos_token_id": 2,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
     "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
-      "1": "LABEL_1",
-      "2": "LABEL_2"
+      "1": "LABEL_1"
     },
-    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
     "is_decoder": true,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
-      "LABEL_1": 1,
-      "LABEL_2": 2
+      "LABEL_1": 1
     },
+    "layer_norm_eps": 1e-12,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 128,
+    "max_position_embeddings": 512,
     "min_length": 0,
-    "model_type": "bart",
-    "no_repeat_ngram_size": 3,
-    "normalize_before": false,
+    "model_type": "roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
-    "num_beams": 4,
-    "num_hidden_layers": 12,
+    "num_beams": 1,
+    "num_hidden_layers": 6,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
     "pad_token_id": 1,
+    "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -76,29 +65,9 @@
     "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": {
-      "summarization": {
-        "length_penalty": 1.0,
-        "max_length": 128,
-        "min_length": 12,
-        "num_beams": 4
-      },
-      "summarization_cnn": {
-        "length_penalty": 2.0,
-        "max_length": 142,
-        "min_length": 56,
-        "num_beams": 4
-      },
-      "summarization_xsum": {
-        "length_penalty": 1.0,
-        "max_length": 62,
-        "min_length": 11,
-        "num_beams": 6
-      }
-    },
+    "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
@@ -106,12 +75,13 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
+    "type_vocab_size": 1,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 1025
+    "vocab_size": 7924
   },
   "decoder_start_token_id": 0,
   "encoder": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0dee8c34767816d09c35854f739cd1e64fb9ce17d01760468b06eea462fca8
-size 1408891684
+oid sha256:aea7bd6f63d3d0a52416bc19ac9e0496a5a59e43601b8fd8b1b5848c1396150c
+size 852404428

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331dd79c0d92cfbb953b1f370c43d2db7c1aac858a40c76b884735dd4089e9dd
+oid sha256:e62830d213bb1984f87b4fc22c7bfd36933ee06a1a9a7abcb594aae048d79e3b
 size 5304