Upload 14 files

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|assistant|>": 49154,
+  "<|end|>": 49155,
+  "<|system|>": 49152,
+  "<|user|>": 49153
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 0.2658990031540996,
+    "train_runtime": 7827.5947,
+    "train_samples": 8463,
+    "train_samples_per_second": 3.244,
+    "train_steps_per_second": 0.025
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoderbase",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49156
+}

dialogue_template.json

@@ -0,0 +1,17 @@
+{
+  "system": "",
+  "messages": [
+    {
+      "content": "You are given the following SQL database tables: \ninterviews(id, notes, date, project_id, created_at, updated_at, deleted_at)\nprojects(id, name, description, created_at, updated_at, deleted_at)\nOutput a json string with the following schema {table, column, referencedTable, referencedColumn} that contains the foreign key relationship between the two tables.",
+      "role": "user"
+    },
+    {
+      "content": "{\"table\": \"interviews\", \"column\": \"project_id\", \"referencedTable\": \"projects\", \"referencedColumn\": \"id\"}",
+      "role": "assistant"
+    }
+  ],
+  "system_token": "<|system|>",
+  "user_token": "<|user|>",
+  "assistant_token": "<|assistant|>",
+  "end_token": "<|end|>"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 0.2658990031540996,
+    "train_runtime": 7827.5947,
+    "train_samples": 8463,
+    "train_samples_per_second": 3.244,
+    "train_steps_per_second": 0.025
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9943289224952743,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 1.0585,
+      "step": 1
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 0.6923,
+      "step": 8
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2e-05,
+      "loss": 0.5149,
+      "step": 16
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2e-05,
+      "loss": 0.3899,
+      "step": 24
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2e-05,
+      "loss": 0.3511,
+      "step": 32
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2e-05,
+      "loss": 0.3321,
+      "step": 40
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2e-05,
+      "loss": 0.3254,
+      "step": 48
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2e-05,
+      "loss": 0.3104,
+      "step": 56
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2e-05,
+      "loss": 0.3007,
+      "step": 64
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2e-05,
+      "loss": 0.2617,
+      "step": 72
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2e-05,
+      "loss": 0.2454,
+      "step": 80
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2e-05,
+      "loss": 0.2362,
+      "step": 88
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2e-05,
+      "loss": 0.2334,
+      "step": 96
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2e-05,
+      "loss": 0.2275,
+      "step": 104
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2e-05,
+      "loss": 0.23,
+      "step": 112
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2e-05,
+      "loss": 0.217,
+      "step": 120
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2e-05,
+      "loss": 0.2205,
+      "step": 128
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2e-05,
+      "loss": 0.2031,
+      "step": 136
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 2e-05,
+      "loss": 0.1629,
+      "step": 144
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2e-05,
+      "loss": 0.167,
+      "step": 152
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2e-05,
+      "loss": 0.1627,
+      "step": 160
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 2e-05,
+      "loss": 0.1594,
+      "step": 168
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2e-05,
+      "loss": 0.1553,
+      "step": 176
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2e-05,
+      "loss": 0.1623,
+      "step": 184
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2e-05,
+      "loss": 0.1576,
+      "step": 192
+    },
+    {
+      "epoch": 2.99,
+      "step": 198,
+      "total_flos": 424189693526016.0,
+      "train_loss": 0.2658990031540996,
+      "train_runtime": 7827.5947,
+      "train_samples_per_second": 3.244,
+      "train_steps_per_second": 0.025
+    }
+  ],
+  "max_steps": 198,
+  "num_train_epochs": 3,
+  "total_flos": 424189693526016.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef13f51408f86df0fd7309c4689c5113c2ab930bf5a50e61edf0f7e1b7d2c13
+size 4859