Training in progress, step 10

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "agemagician/mlong-t5-tglobal-base",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "transient-global",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "use_cache": false,
+  "vocab_size": 256384
+}

last-checkpoint/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "agemagician/mlong-t5-tglobal-base",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "transient-global",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "use_cache": false,
+  "vocab_size": 256384
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "decoder_start_token_id": 0,
+  "max_length": 1024,
+  "transformers_version": "4.30.0"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30400934a7693e3ddb9b0de4991f6ae635b77c814b2d4523f85c02b2e3fc9e3e
+size 4736616809

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86899c0d9b3c53042d0bf035073f9f464a95a31a24ebf7bc05caeb16e0c89f6a
+size 2368281769

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b118866415c54f4b86bf0042f44fb4250ac1f4296ad753ad081de1cade3ed8
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76a6c35ff0b6cd17227069b00654c363bcc2d4216ec234673be607facd57478
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

last-checkpoint/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df39d1fc39c686038078faca93a76cbae9e199a3b652997417ef370ad8c5677
+size 4555103

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1aeab8f9f01e0f5c8f9b8e06e3c1546696dff62a47a6729a0f91aaa24c98da4
+size 16795620

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 2.617305040359497,
+  "best_model_checkpoint": "output/checkpoint-10",
+  "epoch": 0.0016666666666666668,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 5.1377,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 5.1144,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.4e-05,
+      "loss": 5.2944,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 5.277,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 4.7688,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.8e-05,
+      "loss": 4.7068,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 4.905,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 4.6467,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.2e-05,
+      "loss": 4.4809,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8e-05,
+      "loss": 4.4408,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.617305040359497,
+      "eval_rouge1": 0.1402,
+      "eval_rouge2": 0.0375,
+      "eval_rougeL": 0.104,
+      "eval_rougeLsum": 0.1032,
+      "eval_runtime": 19.242,
+      "eval_samples_per_second": 2.598,
+      "eval_steps_per_second": 0.364,
+      "step": 10
+    }
+  ],
+  "max_steps": 6000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 8969223955120128.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6dbd721933f5a9cb95f3dd21903cd2647f65dd3a532864dec422744664755a
+size 5371

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86899c0d9b3c53042d0bf035073f9f464a95a31a24ebf7bc05caeb16e0c89f6a
+size 2368281769

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df39d1fc39c686038078faca93a76cbae9e199a3b652997417ef370ad8c5677
+size 4555103

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1aeab8f9f01e0f5c8f9b8e06e3c1546696dff62a47a6729a0f91aaa24c98da4
+size 16795620

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6dbd721933f5a9cb95f3dd21903cd2647f65dd3a532864dec422744664755a
+size 5371