Training in progress, epoch 1

config.json

@@ -1,51 +1,7 @@
 {
   "_name_or_path": "t5-small",
-  "adapters": {
-    "adapters": {
-      "imdb_pfeiffer": "9076f36a74755ac4"
-    },
-    "config_map": {
-      "9076f36a74755ac4": {
-        "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": "relu",
-        "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": 16,
-        "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"
+    "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
@@ -56,11 +12,9 @@
   "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,
@@ -69,28 +23,6 @@
   "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": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e40f01a6989af3dbd8712678119ae884e164d8a136116cdec86327977573f8f
-size 243649520
+oid sha256:5deb8eaaf50dcd203f4c4b710030eb2ad7895a09ff0cf0ae55bb0617751e020c
+size 243231448

runs/Apr18_10-28-36_448e4276cffe/events.out.tfevents.1744972755.448e4276cffe.40881.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960a678826707a000c8e35e69827198e1fd3af6babf38a1c4900ae362133db3d
+size 405

runs/Apr18_11-09-55_448e4276cffe/events.out.tfevents.1744974597.448e4276cffe.40881.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e39dfad3b1e20733a403b69cca9492f8bc6df1b6e45be1b3610a697d4abeef
+size 6212

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7583de184e2beb0dc73eedd63571ec8daafb059f31aff0e63af2f61b42b1cc7f
+oid sha256:1ca501d2ba86ccc9a09ec9d382dddcf4c54f22483c66f9961156eb3af0262aa4
 size 5368