Version of the model as reported in MODELS'24 paper about ModelMate

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 32769,
+  "<EOL>": 32772,
+  "<URIPRE>": 32771,
+  "<s>": 32768,
+  "<unk>": 32770
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "codeparrot/codeparrot-small-multi",
+  "activation_function": "gelu_fast",
+  "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_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "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,
+  "tokenizer_class": "GPT2TokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 32773
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c64eb008f4b0be2c241b634aa2be0f19445ddd4de2c07065fc569efd7c906d
+size 888183493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5a6eabb853c7df70762d58fe50282acfbedcaa324ae93dacdb8d672b08012b
+size 456687165

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07517d2d5bab120e7d09d28bccf7e91381cbb580be0e4fd6ab2eccbd8b6b932e
+size 15597

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea1e4c6d2ae6abebc904cde77b35ce9565fcf03d92f690b2f0f9412bda4d46b
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf953b5e1cd4812ea41cddb3574300933d0d19dda6005ee2e77bbfc2333e19a
+size 627

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "codeparrot/codeparrot-small-multi",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": 1.0597896575927734,
+  "best_model_checkpoint": "runs/codeparrot/codeparrot-small-multi-xtext_mar-line-dedup-512/checkpoint-640",
+  "epoch": 7.996108949416342,
+  "global_step": 640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.5e-05,
+      "loss": 1.3972,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1680763959884644,
+      "eval_runtime": 9.276,
+      "eval_samples_per_second": 78.159,
+      "eval_steps_per_second": 19.621,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4e-05,
+      "loss": 1.1503,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1147633790969849,
+      "eval_runtime": 9.0648,
+      "eval_samples_per_second": 79.979,
+      "eval_steps_per_second": 20.078,
+      "step": 160
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.5e-05,
+      "loss": 1.0648,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0921669006347656,
+      "eval_runtime": 9.3128,
+      "eval_samples_per_second": 77.85,
+      "eval_steps_per_second": 19.543,
+      "step": 240
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 1.0046,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0750280618667603,
+      "eval_runtime": 9.2369,
+      "eval_samples_per_second": 78.49,
+      "eval_steps_per_second": 19.704,
+      "step": 320
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9591,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.07002854347229,
+      "eval_runtime": 9.2974,
+      "eval_samples_per_second": 77.979,
+      "eval_steps_per_second": 19.575,
+      "step": 400
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2e-05,
+      "loss": 0.9228,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.0629867315292358,
+      "eval_runtime": 9.2375,
+      "eval_samples_per_second": 78.484,
+      "eval_steps_per_second": 19.702,
+      "step": 480
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.5e-05,
+      "loss": 0.8922,
+      "step": 560
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.0609277486801147,
+      "eval_runtime": 9.2071,
+      "eval_samples_per_second": 78.744,
+      "eval_steps_per_second": 19.767,
+      "step": 560
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1e-05,
+      "loss": 0.8689,
+      "step": 640
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.0597896575927734,
+      "eval_runtime": 9.2819,
+      "eval_samples_per_second": 78.109,
+      "eval_steps_per_second": 19.608,
+      "step": 640
+    }
+  ],
+  "max_steps": 800,
+  "num_train_epochs": 10,
+  "total_flos": 1.0740147683328e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2a090d42689acf05ee4b1be0667b1647de7817053d7ed299fba710c06b9cc7
+size 3515