Training in progress, step 500

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google-t5/t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "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,
+  "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": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951ec0c9a0d8998941de97c28c943af8d48ed0f2d4f23983148810075fe966a8
+size 242041896

runs/Nov05_23-33-21_0aa5ebbb1b6d/events.out.tfevents.1730849603.0aa5ebbb1b6d.30.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf74e15ed9c5095048a73c11bddc19017ae92968ce5aeb2c5f99f7096f33955
+size 5948

runs/Nov05_23-37-11_0aa5ebbb1b6d/events.out.tfevents.1730849833.0aa5ebbb1b6d.30.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede3928075b855cf878921810cabe1363be1ce2f97eb93760664c0f846ff7d37
+size 5948

runs/Nov05_23-40-02_0aa5ebbb1b6d/events.out.tfevents.1730850003.0aa5ebbb1b6d.30.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3a8f3a92418619df83a997514d065a5e4f33c001290b8c2ab8cee98b61fe9c
+size 7013

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432bf5e8acd61e672b59eaa7bf5ffb1fcee48c6a9d8c9279ca8e5521c56fb25a
+size 5368