--- license: apache-2.0 datasets: - CoIR-Retrieval/CodeSearchNet-python-queries-corpus language: - en - ar - zh - ru - fr metrics: - loss - accuracy base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 pipeline_tag: text-generation library_name: transformers tags: - chat - conversational - programming - algorithms - ethical-hacking - open-source - tinyllama new_version: v1.0 training_data: 156GB of diverse text data (including programming and algorithmic content) model-index: - name: TINYLAMA results: - task: type: text-generation dataset: type: custom name: Local Dataset (156GB) metrics: - type: loss value: TBD (To Be Determined after retraining) - type: accuracy value: TBD (To Be Determined after retraining) eval_results: - task: Text Generation dataset: Local Dataset (156GB) metrics: - name: Loss value: TBD (To Be Determined after retraining) - name: Accuracy value: TBD (To Be Determined after retraining)

config.json

@@ -0,0 +1,45 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "float16",
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.51.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fc67449109c83aafcc06c26bd90d5ede698510ae13d0c9787f3133b9fa0dad
+size 163832712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2188eb8623f7e71b920ab341ef3ba9e600b2037942429d360f9f8c2290e47df5
+size 327712058

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad440af714c205e76efff6aa1e7af2d3eb478003db06214ecc6569fe02a4a1f
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7c32259d51730d9f585a8cfbc002399970b539c9a026c11ce95a37aa25dd07
+size 1064

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": NaN,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0,
+      "step": 3
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 489931407360.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb072f49907d09fe0fe06ac83d238961aacd9cc5b832c75eb128aa72cdbd66
+size 5304