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:fc8de36b9b0fcd3d2f83e75ac9194d59297fce97c03e18d98a9e52cd379dc33e
+size 888183493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b473f848a2fbdf5b2679eea9852b35957a246f0feb84186f9bf0f7b04f5034a6
+size 456687165

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bbc51f310b948dc0795f50be6140cdd17b8b5f45d66dad7c8d92f90f5eed816
+size 15597

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ec07a12731ae6f9765d05fe7c8495505f1d0f90b4cc6255a0853fec3970808
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ebdb05c79a4eb141f2d1c33ec8d5353ac5a8a41d72da20623877e35572bc70
+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 +1,86 @@
+{
+  "best_metric": 0.8726145625114441,
+  "best_model_checkpoint": "runs/codeparrot/codeparrot-small-multi-ecore_line-512/checkpoint-800",
+  "epoch": 4.998829496683574,
+  "global_step": 800,
+  "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": 1.0255,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9181002378463745,
+      "eval_runtime": 18.9044,
+      "eval_samples_per_second": 78.923,
+      "eval_steps_per_second": 19.731,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4e-05,
+      "loss": 0.8865,
+      "step": 320
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8927440643310547,
+      "eval_runtime": 18.8288,
+      "eval_samples_per_second": 79.24,
+      "eval_steps_per_second": 19.81,
+      "step": 320
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.5e-05,
+      "loss": 0.8313,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8809273838996887,
+      "eval_runtime": 18.7583,
+      "eval_samples_per_second": 79.538,
+      "eval_steps_per_second": 19.885,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.7884,
+      "step": 640
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8755712509155273,
+      "eval_runtime": 19.3412,
+      "eval_samples_per_second": 77.141,
+      "eval_steps_per_second": 19.285,
+      "step": 640
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7539,
+      "step": 800
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.8726145625114441,
+      "eval_runtime": 18.9056,
+      "eval_samples_per_second": 78.918,
+      "eval_steps_per_second": 19.73,
+      "step": 800
+    }
+  ],
+  "max_steps": 1600,
+  "num_train_epochs": 10,
+  "total_flos": 1.339121664e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b97c2b82d758fd696ead9148467e62f2996197912ae145ee3f160b119fd8e9
+size 3451