deployment qa

app/pyfiles/gpt2_qa_model/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 50258
+}

app/pyfiles/gpt2_qa_model/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.1"
+}

app/pyfiles/gpt2_qa_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c58cfcd6f3183c6bd368cd2d249c0c5cb8b4cc3e2e63dbed19f827a63595bd
+size 497777280

app/pyfiles/gpt2_qa_model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e2d573dc0eaad6ed266613452b53c52fc0314974bbce6399425579de77be7c
+size 995648005

app/pyfiles/gpt2_qa_model/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70b22c76ffeb1a54dfea5e46ff4357813e4530099effda5ded403a5b6bad573
+size 14575

app/pyfiles/gpt2_qa_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1896dd01641cd5530a62fe19c8f250a473551bdb7196d9b92e1afcb65f1b0b
+size 627

app/pyfiles/gpt2_qa_model/trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 1000,
+  "global_step": 6624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.245169082125605e-06,
+      "loss": 5.1379,
+      "step": 500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.490338164251208e-06,
+      "loss": 2.6021,
+      "step": 1000
+    },
+    {
+      "epoch": 1.81,
+      "eval_R1": 0.4801,
+      "eval_R2": 0.2007,
+      "eval_RL": 0.3755,
+      "eval_RLsum": 0.375,
+      "eval_bleu": 24.4945,
+      "eval_loss": 3.176283836364746,
+      "eval_runtime": 4.6319,
+      "eval_samples_per_second": 31.305,
+      "eval_steps_per_second": 31.305,
+      "step": 1000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 7.735507246376812e-06,
+      "loss": 2.442,
+      "step": 1500
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 6.980676328502416e-06,
+      "loss": 2.3457,
+      "step": 2000
+    },
+    {
+      "epoch": 3.62,
+      "eval_R1": 0.4863,
+      "eval_R2": 0.2078,
+      "eval_RL": 0.3799,
+      "eval_RLsum": 0.3793,
+      "eval_bleu": 25.6685,
+      "eval_loss": 3.01701021194458,
+      "eval_runtime": 4.4695,
+      "eval_samples_per_second": 32.442,
+      "eval_steps_per_second": 32.442,
+      "step": 2000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 6.22584541062802e-06,
+      "loss": 2.2664,
+      "step": 2500
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 5.471014492753623e-06,
+      "loss": 2.2153,
+      "step": 3000
+    },
+    {
+      "epoch": 5.43,
+      "eval_R1": 0.4856,
+      "eval_R2": 0.2091,
+      "eval_RL": 0.3822,
+      "eval_RLsum": 0.3816,
+      "eval_bleu": 25.6215,
+      "eval_loss": 2.978219747543335,
+      "eval_runtime": 4.507,
+      "eval_samples_per_second": 32.172,
+      "eval_steps_per_second": 32.172,
+      "step": 3000
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 4.716183574879228e-06,
+      "loss": 2.1315,
+      "step": 3500
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 3.961352657004831e-06,
+      "loss": 2.1401,
+      "step": 4000
+    },
+    {
+      "epoch": 7.25,
+      "eval_R1": 0.4855,
+      "eval_R2": 0.206,
+      "eval_RL": 0.385,
+      "eval_RLsum": 0.3847,
+      "eval_bleu": 25.5534,
+      "eval_loss": 2.978952646255493,
+      "eval_runtime": 4.5866,
+      "eval_samples_per_second": 31.614,
+      "eval_steps_per_second": 31.614,
+      "step": 4000
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 3.206521739130435e-06,
+      "loss": 2.0507,
+      "step": 4500
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 2.451690821256039e-06,
+      "loss": 2.021,
+      "step": 5000
+    },
+    {
+      "epoch": 9.06,
+      "eval_R1": 0.4835,
+      "eval_R2": 0.2053,
+      "eval_RL": 0.384,
+      "eval_RLsum": 0.3834,
+      "eval_bleu": 25.5813,
+      "eval_loss": 2.980417013168335,
+      "eval_runtime": 4.6238,
+      "eval_samples_per_second": 31.36,
+      "eval_steps_per_second": 31.36,
+      "step": 5000
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 1.6968599033816427e-06,
+      "loss": 2.0242,
+      "step": 5500
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 9.420289855072465e-07,
+      "loss": 2.0082,
+      "step": 6000
+    },
+    {
+      "epoch": 10.87,
+      "eval_R1": 0.4861,
+      "eval_R2": 0.2068,
+      "eval_RL": 0.3845,
+      "eval_RLsum": 0.384,
+      "eval_bleu": 25.5723,
+      "eval_loss": 2.9800899028778076,
+      "eval_runtime": 4.497,
+      "eval_samples_per_second": 32.244,
+      "eval_steps_per_second": 32.244,
+      "step": 6000
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 1.8719806763285025e-07,
+      "loss": 1.974,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "total_flos": 825101038080000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

app/pyfiles/gpt2_qa_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277200f397cb704f1248c12d2812c5cb6ac52e08e7839e1c742dc2ba2e986b16
+size 4283