add baseline model ckpt

.gitattributes

@@ -33,3 +33,12 @@ 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
+checkpoint-5000/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/config.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/generation_config.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

checkpoint-5000/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a816a18dcfe99ecf1c5ab86e22b3354b846cb2fdddc15329b6d7b0ce509de9b
+size 1528

checkpoint-5000/generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6833851ce53496a43ef87a975c766f7a3049e2d598ecef609a526ca6308534
+size 142

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98bad1336f5b5bd7166561dd9169ef0ae0458d84a12fe4495dafdb4c698c8e3
+size 2371333

checkpoint-5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8d2b4fc474f2a3ee4e727ef3beeb48bda1580929f0533595549493a670dd58
+size 990408885

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1e41a24146cf5c2e027973b4674ca7056995fc270e892208cda116dacb7e4f
+size 14575

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06319e8fb637c8a375199a70338dd58362987a6132a8f8ca31b00c3b0b013d9b
+size 627

checkpoint-5000/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0896850485757f9eb02938e3a809abe3398bb4516d6af6b771aeffaf3094ae84
+size 3475

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a404763c15e6a97a510a639844e059871b1160163baa499ef23d347aae03a98
+size 4091

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "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,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852bf51b3b84310c6f60cef99cd64c1964d95b9ec68f08fd465090fbbb4fe39b
+size 2371333

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c3909f22445cc0a707b7b83434ab5f95c2ab5bbddf1d7b9f4b14a3dddc8ff3
+size 990408885

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba6c572f23aa9963da39e7213ee988824ff5da3fc545417fcd21bbf8c19dc45
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5e24b8bf255cbefe9d307944a9741807d095b40cc5429a7befe9515b366b0f
+size 627

trainer_state.json

@@ -0,0 +1,296 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5195263290501386,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.5e-05,
+      "loss": 0.8107,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.6702454090118408,
+      "eval_runtime": 4.5337,
+      "eval_samples_per_second": 66.17,
+      "eval_steps_per_second": 33.085,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9e-05,
+      "loss": 0.717,
+      "step": 1000
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.6662179827690125,
+      "eval_runtime": 5.109,
+      "eval_samples_per_second": 58.719,
+      "eval_steps_per_second": 29.36,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.5e-05,
+      "loss": 0.7212,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.6485440135002136,
+      "eval_runtime": 4.6475,
+      "eval_samples_per_second": 64.551,
+      "eval_steps_per_second": 32.276,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8e-05,
+      "loss": 0.7094,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6365593671798706,
+      "eval_runtime": 4.9661,
+      "eval_samples_per_second": 60.41,
+      "eval_steps_per_second": 30.205,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.7081,
+      "step": 2500
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.6411292552947998,
+      "eval_runtime": 5.0449,
+      "eval_samples_per_second": 59.466,
+      "eval_steps_per_second": 29.733,
+      "step": 2500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7e-05,
+      "loss": 0.6803,
+      "step": 3000
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.629453718662262,
+      "eval_runtime": 5.1787,
+      "eval_samples_per_second": 57.929,
+      "eval_steps_per_second": 28.965,
+      "step": 3000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 0.6886,
+      "step": 3500
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.6171028017997742,
+      "eval_runtime": 6.0926,
+      "eval_samples_per_second": 49.24,
+      "eval_steps_per_second": 24.62,
+      "step": 3500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 6e-05,
+      "loss": 0.673,
+      "step": 4000
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 0.6199834942817688,
+      "eval_runtime": 4.5562,
+      "eval_samples_per_second": 65.844,
+      "eval_steps_per_second": 32.922,
+      "step": 4000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6123,
+      "step": 4500
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 0.615871250629425,
+      "eval_runtime": 4.3914,
+      "eval_samples_per_second": 68.315,
+      "eval_steps_per_second": 34.158,
+      "step": 4500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5e-05,
+      "loss": 0.6036,
+      "step": 5000
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.6081268191337585,
+      "eval_runtime": 4.202,
+      "eval_samples_per_second": 71.395,
+      "eval_steps_per_second": 35.697,
+      "step": 5000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5854,
+      "step": 5500
+    },
+    {
+      "epoch": 1.39,
+      "eval_loss": 0.610887885093689,
+      "eval_runtime": 4.5399,
+      "eval_samples_per_second": 66.08,
+      "eval_steps_per_second": 33.04,
+      "step": 5500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 4e-05,
+      "loss": 0.5936,
+      "step": 6000
+    },
+    {
+      "epoch": 1.51,
+      "eval_loss": 0.6057543158531189,
+      "eval_runtime": 5.4963,
+      "eval_samples_per_second": 54.582,
+      "eval_steps_per_second": 27.291,
+      "step": 6000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5917,
+      "step": 6500
+    },
+    {
+      "epoch": 1.64,
+      "eval_loss": 0.6038711071014404,
+      "eval_runtime": 4.4545,
+      "eval_samples_per_second": 67.348,
+      "eval_steps_per_second": 33.674,
+      "step": 6500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3e-05,
+      "loss": 0.5848,
+      "step": 7000
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.6017142534255981,
+      "eval_runtime": 4.4106,
+      "eval_samples_per_second": 68.018,
+      "eval_steps_per_second": 34.009,
+      "step": 7000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5875,
+      "step": 7500
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.6017369627952576,
+      "eval_runtime": 4.4904,
+      "eval_samples_per_second": 66.809,
+      "eval_steps_per_second": 33.404,
+      "step": 7500
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2e-05,
+      "loss": 0.5975,
+      "step": 8000
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.5987575054168701,
+      "eval_runtime": 4.1962,
+      "eval_samples_per_second": 71.493,
+      "eval_steps_per_second": 35.747,
+      "step": 8000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.5e-05,
+      "loss": 0.5551,
+      "step": 8500
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.6018974781036377,
+      "eval_runtime": 4.1728,
+      "eval_samples_per_second": 71.894,
+      "eval_steps_per_second": 35.947,
+      "step": 8500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1e-05,
+      "loss": 0.5338,
+      "step": 9000
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.600771963596344,
+      "eval_runtime": 4.5111,
+      "eval_samples_per_second": 66.502,
+      "eval_steps_per_second": 33.251,
+      "step": 9000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 5e-06,
+      "loss": 0.5648,
+      "step": 9500
+    },
+    {
+      "epoch": 2.39,
+      "eval_loss": 0.599320650100708,
+      "eval_runtime": 4.3392,
+      "eval_samples_per_second": 69.138,
+      "eval_steps_per_second": 34.569,
+      "step": 9500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.0,
+      "loss": 0.5328,
+      "step": 10000
+    },
+    {
+      "epoch": 2.52,
+      "eval_loss": 0.6002569794654846,
+      "eval_runtime": 5.4729,
+      "eval_samples_per_second": 54.816,
+      "eval_steps_per_second": 27.408,
+      "step": 10000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 3,
+  "total_flos": 3.963545541632102e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a404763c15e6a97a510a639844e059871b1160163baa499ef23d347aae03a98
+size 4091