Training in progress, step 500

config.json

@@ -1,46 +1,59 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
   "architectures": [
-    "GPT2LMHeadModel"
+    "MBartForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
-    "0": "LABEL_0"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
-  "initializer_range": 0.02,
+  "init_std": 0.02,
+  "is_decoder": true,
+  "is_encoder_decoder": false,
   "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 250054
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735d11efc09a243527c90b01f0b1f8a665c2e0b6987a43dfd4fe092c2a5197d4
-size 327657928
+oid sha256:09c11930a281b98439733c553e6f482636e0bd0f6f7286612a36618f082c27fb
+size 1834718496

runs/Dec12_12-08-01_87fa4f095f30/events.out.tfevents.1702382882.87fa4f095f30.1650.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e72fc8178df78a5704114bb6cd774c215188e015214867db66b1ba4eb5cc474
-size 11580
+oid sha256:cf13cdcffd45053d6e57654f88a5228c72683f4dd5059d4b3e536a60b500ed0a
+size 11851

runs/Dec12_12-48-48_87fa4f095f30/events.out.tfevents.1702385334.87fa4f095f30.14555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09e0aeaf265d7012de233874a14cff9144b206542826e5d9d7a218371fb8440
+size 5153

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb3e3a2674c07ffd38c7ddaf9331f3c7bd0767283a24d39a7a8e14eb1d7b84a
+oid sha256:0ec444722bef4263f04d71bb6717e791f7af90334179008a6f4b1066ff73c394
 size 4600