Upload folder using huggingface_hub

README.md

@@ -0,0 +1,17 @@
+# sentiment_prompt_1_model
+
+## Model Description
+This model is a fine-tuned version of `EleutherAI/pythia-410m` trained on `dair-ai/emotion` data.
+
+## Dataset Details
+- Dataset Configuration: unsplit
+- Dataset Name: dair-ai/emotion
+- Prompt: analyze the sentiment of the given text: {text}
+{label}
+
+## 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: 4.04 GB

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e86c95eeb62dd0ff8cd8c14221d12bdf8db01bed58e1dd0c59240867d94769
+size 810702192

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f504e1e3f33d7af4d5bb5f71703aca9b5a740ccb117c796d65229a17ccb6f1
+size 1621580026

ram_usage_log.txt

@@ -0,0 +1,4 @@
+Total RAM: 186.68 GB
+Available RAM: 155.76 GB
+Used RAM: 28.88 GB
+RAM Usage Percentage: 16.6%

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 sha256:3fd330c71330ca5dfdd289cbd452c1e86b567510cb45bbbeadf00e962e2b0d1b
+size 1064

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 24750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.9587628865979382e-05,
+      "loss": 1.1421,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.8762886597938147e-05,
+      "loss": 0.153,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.793814432989691e-05,
+      "loss": 0.1516,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.7113402061855672e-05,
+      "loss": 0.1508,
+      "step": 4000
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.6288659793814433e-05,
+      "loss": 0.149,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.5463917525773197e-05,
+      "loss": 0.147,
+      "step": 6000
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.4639175257731958e-05,
+      "loss": 0.1473,
+      "step": 7000
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.3814432989690723e-05,
+      "loss": 0.1459,
+      "step": 8000
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.2989690721649485e-05,
+      "loss": 0.1463,
+      "step": 9000
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.2164948453608248e-05,
+      "loss": 0.1444,
+      "step": 10000
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.134020618556701e-05,
+      "loss": 0.1458,
+      "step": 11000
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.0515463917525775e-05,
+      "loss": 0.1446,
+      "step": 12000
+    },
+    {
+      "epoch": 0.5252525252525253,
+      "grad_norm": 1.25,
+      "learning_rate": 9.690721649484536e-06,
+      "loss": 0.1454,
+      "step": 13000
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 2.65625,
+      "learning_rate": 8.865979381443299e-06,
+      "loss": 0.1454,
+      "step": 14000
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.041237113402063e-06,
+      "loss": 0.1456,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.216494845360825e-06,
+      "loss": 0.1469,
+      "step": 16000
+    },
+    {
+      "epoch": 0.6868686868686869,
+      "grad_norm": 1.296875,
+      "learning_rate": 6.391752577319588e-06,
+      "loss": 0.1466,
+      "step": 17000
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.567010309278351e-06,
+      "loss": 0.147,
+      "step": 18000
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "grad_norm": 1.90625,
+      "learning_rate": 4.742268041237113e-06,
+      "loss": 0.1477,
+      "step": 19000
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 1.3359375,
+      "learning_rate": 3.917525773195877e-06,
+      "loss": 0.1461,
+      "step": 20000
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 1.625,
+      "learning_rate": 3.0927835051546395e-06,
+      "loss": 0.1485,
+      "step": 21000
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.3671875,
+      "learning_rate": 2.268041237113402e-06,
+      "loss": 0.1473,
+      "step": 22000
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1.4432989690721649e-06,
+      "loss": 0.1463,
+      "step": 23000
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 1.1875,
+      "learning_rate": 6.185567010309279e-07,
+      "loss": 0.1461,
+      "step": 24000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 24750,
+  "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": 1.0760739618816e+17,
+  "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:d7eaf1a6dbfa8bdd6295b8ad03c703ba7f38d2d2d0ecf415cdca68154d832532
+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