Training in progress, epoch 1

config.json

@@ -0,0 +1,129 @@
+{
+  "_name_or_path": "t5-small",
+  "adapters": {
+    "adapters": {
+      "imdb_pfeiffer": "d252295ac7151db2"
+    },
+    "config_map": {
+      "d252295ac7151db2": {
+        "adapter_residual_before_ln": false,
+        "cross_adapter": false,
+        "dropout": 0.0,
+        "factorized_phm_W": true,
+        "factorized_phm_rule": false,
+        "hypercomplex_nonlinearity": "glorot-uniform",
+        "init_weights": "bert",
+        "inv_adapter": null,
+        "inv_adapter_reduction_factor": null,
+        "is_parallel": false,
+        "learn_phm": true,
+        "leave_out": [],
+        "ln_after": false,
+        "ln_before": false,
+        "mh_adapter": false,
+        "non_linearity": "gelu",
+        "original_ln_after": true,
+        "original_ln_before": true,
+        "output_adapter": true,
+        "phm_bias": true,
+        "phm_c_init": "normal",
+        "phm_dim": 4,
+        "phm_init_range": 0.0001,
+        "phm_layer": false,
+        "phm_rank": 1,
+        "reduction_factor": 8,
+        "residual_before_ln": true,
+        "scaling": 1.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "stochastic_depth": 0.0,
+        "use_gating": false
+      }
+    },
+    "fusion_config_map": {},
+    "fusion_name_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "T5AdapterModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "id2label": null,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "label2id": null,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "prediction_heads": {
+    "default": {
+      "activation_function": null,
+      "bias": false,
+      "head_type": "seq2seq_lm",
+      "label2id": null,
+      "layer_norm": false,
+      "layers": 1,
+      "shift_labels": false,
+      "vocab_size": 32128
+    },
+    "imdb_pfeiffer": {
+      "activation_function": null,
+      "bias": false,
+      "head_type": "seq2seq_lm",
+      "label2id": null,
+      "layer_norm": false,
+      "layers": 1,
+      "shift_labels": false,
+      "vocab_size": 32128
+    }
+  },
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b254e3ea4f9924ab30b7d1158acaa842d67f1670aa5fb2b48de23a1a1d5528
+size 245223920

runs/Apr18_17-09-37_8f7f7326e694/events.out.tfevents.1744996181.8f7f7326e694.264.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55e157ad337af96cded87e9458eada78f2ee3aa9fa283fa7042f267a47f99e9
+size 7837

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6368b5eaccec474c69badf980b4a6d3eb255d57392be65b0035ea6a22c229a
+size 5368