Training in progress, step 1000

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "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": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5afc9a5a68982ad6490da739a4f7fdd686068ff02f06f519a0268aa034c1d04
+size 242041896

runs/Oct23_11-07-11_kudsit-dgxserver/events.out.tfevents.1729661838.kudsit-dgxserver.903183.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8df1b10ee058fbdb9e872bcc48f40790645c3a6562aa93e056f5c171544b39e
+size 6025

runs/Oct23_11-08-48_kudsit-dgxserver/events.out.tfevents.1729661949.kudsit-dgxserver.903183.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56c12d914fb98a9822e5687ab14c8c9d97def5fe4dc8ab63cb25bc55650e434
+size 6022

runs/Oct23_11-10-18_kudsit-dgxserver/events.out.tfevents.1729662019.kudsit-dgxserver.903183.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d29a1f13bd7cdd464ed80b0735d00045daee5de2be905bb4cd8c2dfa5dd90a2
+size 6022

runs/Oct23_11-14-13_kudsit-dgxserver/events.out.tfevents.1729662257.kudsit-dgxserver.903183.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f332ad9bf56ec59974d265404056ef015cf2d7ac30d52f158e4ac72b6fd04b8b
+size 6444

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f859aa8014581e62554e36d7166ea420908c595018c307334d9c933a8975d889
+size 5432