Upload folder using huggingface_hub

README.md

@@ -0,0 +1,18 @@
+# instruction_prompt_1_model
+
+## Model Description
+This model is a fine-tuned version of `EleutherAI/pythia-410m` trained on `tatsu-lab/alpaca` data.
+
+## Dataset Details
+- Dataset Configuration: None
+- Dataset Name: tatsu-lab/alpaca
+- Prompt: {instruction}
+{input}
+{output}
+
+## Training Details
+- Base Model: EleutherAI/pythia-410m
+- Training Parameters:
+  - Learning Rate: 2e-05
+  - Batch Size: 1
+  - Epochs: 1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.48.0"
+}

gpu_memory_log.txt

@@ -0,0 +1,2 @@
+Current GPU Memory allocated: 2.37 GB
+Max GPU Memory allocated: 4.06 GB

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d580821d1e4b25d698f0df97d8121ad5d91d8cb4986ed9ff5552d33a95e700
+size 810702192

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3197a0688cd8bbdbdfc64db8f67c7b85a8fbc6a0ae4d2760ce54dcdb6154d4dd
+size 1621580026

ram_usage_log.txt

@@ -0,0 +1,4 @@
+Total RAM: 186.68 GB
+Available RAM: 144.00 GB
+Used RAM: 38.55 GB
+RAM Usage Percentage: 22.9%

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e79184a62b068ce886e3cf6b77d680712c8fe43cfbc9fc53fd4467e09009c5
+size 1064

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999786329351937,
+  "eval_steps": 500,
+  "global_step": 11700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08546825922523023,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.910714285714286e-05,
+      "loss": 1.1855,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17093651845046046,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.7321428571428572e-05,
+      "loss": 0.2975,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2564047776756907,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.553571428571429e-05,
+      "loss": 0.3029,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3418730369009209,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.375e-05,
+      "loss": 0.2983,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4273412961261511,
+      "grad_norm": 11.1875,
+      "learning_rate": 1.1964285714285716e-05,
+      "loss": 0.2896,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5128095553513814,
+      "grad_norm": 5.375,
+      "learning_rate": 1.0178571428571429e-05,
+      "loss": 0.2888,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5982778145766117,
+      "grad_norm": 2.890625,
+      "learning_rate": 8.392857142857144e-06,
+      "loss": 0.2868,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6837460738018418,
+      "grad_norm": 5.1875,
+      "learning_rate": 6.607142857142858e-06,
+      "loss": 0.2861,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7692143330270721,
+      "grad_norm": 3.9375,
+      "learning_rate": 4.821428571428572e-06,
+      "loss": 0.2897,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8546825922523023,
+      "grad_norm": 4.875,
+      "learning_rate": 3.0357142857142856e-06,
+      "loss": 0.2873,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9401508514775325,
+      "grad_norm": 6.21875,
+      "learning_rate": 1.25e-06,
+      "loss": 0.279,
+      "step": 11000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 11700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.0868950925312e+16,
+  "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 sha256:08a68c4d2d72e04ca5f16ac17ac4550e4d4b6d4c97f37f634d5b930d89af2f1a
+size 5304

training_config.yaml

@@ -0,0 +1,9 @@
+model_name: "EleutherAI/pythia-410m"
+learning_rate: 2.0e-5
+batch_size: 1
+num_epochs: 1
+warmup_steps: 500
+logging_steps: 1000
+# eval_steps: 2000
+save_steps: 1000
+gradient_accumulation_steps: 4