Training in progress, step 45

config.json

@@ -0,0 +1,60 @@
+{
+  "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": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb56f2599b9e4f053cb2422599d72de1371466251ed87b1b0f93f2ed4ca50c0
+size 242041896

runs/Aug11_18-16-04_de43f70b9fa9/events.out.tfevents.1754936165.de43f70b9fa9.136.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf678118a4843da569a62878ececb447890ae85717b6915d6131028a4a54aae
+size 5815

runs/Aug11_18-16-58_de43f70b9fa9/events.out.tfevents.1754936219.de43f70b9fa9.136.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977c0d6964679f1fd4429899b287c152bd04d83f5a9317caafa8be68579da71e
+size 5815

runs/Aug11_18-17-59_de43f70b9fa9/events.out.tfevents.1754936279.de43f70b9fa9.136.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b17fe2c20b43178108297273747bb48b619c6bdc46e99ef65779ccc4d3ff83d
+size 5815

runs/Aug11_18-18-41_de43f70b9fa9/events.out.tfevents.1754936322.de43f70b9fa9.136.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6fdf1a1da9553d50c882c91bdba62dc378c25a161d3532318a2f6565468eac
+size 5815

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c02b8f544f69b14466523f84364dd4691dd5ccd6ee18de1567015e2a7a4a59c
+size 5304