add model checkpoint FUNCTION-base-flatten

.gitattributes

@@ -33,3 +33,8 @@ 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-*/*bim filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

checkpoint-10000/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "FiDT5"
+  ],
+  "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
+}

checkpoint-10000/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"
+}

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337bb55603ebee89cb75dec21a9c866c67a9172a10eaa13590c6e617c99537c4
+size 2371333

checkpoint-10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b745769676f63fdcd414ff882cdcee4e322aba6ef69bea206e1d7fb4e5f7e6c
+size 990408885

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc462a4cd692df29deb3db06d4e4ea5357a3f9583326b1e4246b17e9779a0bd
+size 14575

checkpoint-10000/scheduler.pt

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

checkpoint-10000/trainer_state.json

@@ -0,0 +1,296 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2616704516780217,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.25e-05,
+      "loss": 5.1725,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.6939732432365417,
+      "eval_runtime": 5.8238,
+      "eval_samples_per_second": 17.171,
+      "eval_steps_per_second": 8.585,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.782608695652174e-05,
+      "loss": 0.5104,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.641968846321106,
+      "eval_runtime": 6.0125,
+      "eval_samples_per_second": 16.632,
+      "eval_steps_per_second": 8.316,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.239130434782609e-05,
+      "loss": 0.485,
+      "step": 1500
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.6206984519958496,
+      "eval_runtime": 5.6411,
+      "eval_samples_per_second": 17.727,
+      "eval_steps_per_second": 8.864,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.695652173913044e-05,
+      "loss": 0.4644,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.6094934344291687,
+      "eval_runtime": 4.7677,
+      "eval_samples_per_second": 20.974,
+      "eval_steps_per_second": 10.487,
+      "step": 2000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.152173913043478e-05,
+      "loss": 0.4563,
+      "step": 2500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.6136000156402588,
+      "eval_runtime": 5.1919,
+      "eval_samples_per_second": 19.261,
+      "eval_steps_per_second": 9.63,
+      "step": 2500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.608695652173914e-05,
+      "loss": 0.4426,
+      "step": 3000
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.6097093224525452,
+      "eval_runtime": 5.562,
+      "eval_samples_per_second": 17.979,
+      "eval_steps_per_second": 8.99,
+      "step": 3000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.065217391304349e-05,
+      "loss": 0.4401,
+      "step": 3500
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.5967560410499573,
+      "eval_runtime": 5.8426,
+      "eval_samples_per_second": 17.116,
+      "eval_steps_per_second": 8.558,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.521739130434783e-05,
+      "loss": 0.4258,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6082923412322998,
+      "eval_runtime": 5.3584,
+      "eval_samples_per_second": 18.662,
+      "eval_steps_per_second": 9.331,
+      "step": 4000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.9782608695652175e-05,
+      "loss": 0.424,
+      "step": 4500
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.5975988507270813,
+      "eval_runtime": 4.7572,
+      "eval_samples_per_second": 21.021,
+      "eval_steps_per_second": 10.51,
+      "step": 4500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.4347826086956524e-05,
+      "loss": 0.4375,
+      "step": 5000
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.5958980321884155,
+      "eval_runtime": 5.8907,
+      "eval_samples_per_second": 16.976,
+      "eval_steps_per_second": 8.488,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.4341,
+      "step": 5500
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.5830276012420654,
+      "eval_runtime": 5.3687,
+      "eval_samples_per_second": 18.626,
+      "eval_steps_per_second": 9.313,
+      "step": 5500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.4337,
+      "step": 6000
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.5838184356689453,
+      "eval_runtime": 5.9136,
+      "eval_samples_per_second": 16.91,
+      "eval_steps_per_second": 8.455,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.4363,
+      "step": 6500
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.5774537920951843,
+      "eval_runtime": 5.28,
+      "eval_samples_per_second": 18.939,
+      "eval_steps_per_second": 9.47,
+      "step": 6500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.4122,
+      "step": 7000
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.5706260800361633,
+      "eval_runtime": 5.6473,
+      "eval_samples_per_second": 17.707,
+      "eval_steps_per_second": 8.854,
+      "step": 7000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4074,
+      "step": 7500
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 0.5714925527572632,
+      "eval_runtime": 3.7863,
+      "eval_samples_per_second": 26.411,
+      "eval_steps_per_second": 13.206,
+      "step": 7500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.4137,
+      "step": 8000
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 0.5754862427711487,
+      "eval_runtime": 6.0221,
+      "eval_samples_per_second": 16.605,
+      "eval_steps_per_second": 8.303,
+      "step": 8000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.362,
+      "step": 8500
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.5741321444511414,
+      "eval_runtime": 5.8113,
+      "eval_samples_per_second": 17.208,
+      "eval_steps_per_second": 8.604,
+      "step": 8500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3791,
+      "step": 9000
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.570868968963623,
+      "eval_runtime": 5.5735,
+      "eval_samples_per_second": 17.942,
+      "eval_steps_per_second": 8.971,
+      "step": 9000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3628,
+      "step": 9500
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.5734958052635193,
+      "eval_runtime": 5.3626,
+      "eval_samples_per_second": 18.648,
+      "eval_steps_per_second": 9.324,
+      "step": 9500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0,
+      "loss": 0.3694,
+      "step": 10000
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.573215663433075,
+      "eval_runtime": 4.6899,
+      "eval_samples_per_second": 21.322,
+      "eval_steps_per_second": 10.661,
+      "step": 10000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 2,
+  "total_flos": 3.8513087293824e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92133b734236cd14623f5f32d7dac13646e59db8ee0cae12878e084143f07cb4
+size 4219

checkpoint-5000/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "FiDT5"
+  ],
+  "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
+}

checkpoint-5000/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"
+}

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf86974bcdabe8d4b82019dd893671ec7dc44eebe5d722a1ca82b4ca3e2208a
+size 2371333

checkpoint-5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03e000db887a4c2ae1e3911ba55550f93b8468c29500cd6a9bca46d21b96adc
+size 990408885

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9b4ed4f719b5c091aaee0f8a3b0a2f1977980e6eb7bbd803bf6300cea01e57
+size 14575

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5db814da74fa52897e2706d0a6e369da3f074aa77a52775256fa20b47664cee
+size 627

checkpoint-5000/trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6308352258390109,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.25e-05,
+      "loss": 5.1725,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.6939732432365417,
+      "eval_runtime": 5.8238,
+      "eval_samples_per_second": 17.171,
+      "eval_steps_per_second": 8.585,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.782608695652174e-05,
+      "loss": 0.5104,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.641968846321106,
+      "eval_runtime": 6.0125,
+      "eval_samples_per_second": 16.632,
+      "eval_steps_per_second": 8.316,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.239130434782609e-05,
+      "loss": 0.485,
+      "step": 1500
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.6206984519958496,
+      "eval_runtime": 5.6411,
+      "eval_samples_per_second": 17.727,
+      "eval_steps_per_second": 8.864,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.695652173913044e-05,
+      "loss": 0.4644,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.6094934344291687,
+      "eval_runtime": 4.7677,
+      "eval_samples_per_second": 20.974,
+      "eval_steps_per_second": 10.487,
+      "step": 2000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.152173913043478e-05,
+      "loss": 0.4563,
+      "step": 2500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.6136000156402588,
+      "eval_runtime": 5.1919,
+      "eval_samples_per_second": 19.261,
+      "eval_steps_per_second": 9.63,
+      "step": 2500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.608695652173914e-05,
+      "loss": 0.4426,
+      "step": 3000
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.6097093224525452,
+      "eval_runtime": 5.562,
+      "eval_samples_per_second": 17.979,
+      "eval_steps_per_second": 8.99,
+      "step": 3000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.065217391304349e-05,
+      "loss": 0.4401,
+      "step": 3500
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.5967560410499573,
+      "eval_runtime": 5.8426,
+      "eval_samples_per_second": 17.116,
+      "eval_steps_per_second": 8.558,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.521739130434783e-05,
+      "loss": 0.4258,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6082923412322998,
+      "eval_runtime": 5.3584,
+      "eval_samples_per_second": 18.662,
+      "eval_steps_per_second": 9.331,
+      "step": 4000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.9782608695652175e-05,
+      "loss": 0.424,
+      "step": 4500
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.5975988507270813,
+      "eval_runtime": 4.7572,
+      "eval_samples_per_second": 21.021,
+      "eval_steps_per_second": 10.51,
+      "step": 4500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.4347826086956524e-05,
+      "loss": 0.4375,
+      "step": 5000
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.5958980321884155,
+      "eval_runtime": 5.8907,
+      "eval_samples_per_second": 16.976,
+      "eval_steps_per_second": 8.488,
+      "step": 5000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 2,
+  "total_flos": 1.921873153314816e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92133b734236cd14623f5f32d7dac13646e59db8ee0cae12878e084143f07cb4
+size 4219