Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- autotrain
+- text-generation
+library_name: transformers
+widget:
+  - messages:
+      - role: user
+        content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

checkpoint-2710/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "openai-community/gpt2-large",
+  "activation_function": "gelu_new",
+  "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_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "float32",
+  "transformers_version": "4.39.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

checkpoint-2710/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.39.0"
+}

checkpoint-2710/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a15ef31765c9e9b172ebcb64d85327c9d4484629d79ea9ff6cf3b7483a8003d
+size 3096165928

checkpoint-2710/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8875ba32cbc2f0b30a4d320eed065f6a0ea8e3514e66371c5aa021de354919
+size 6192613990

checkpoint-2710/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45793735436f7e4a8a81f44f5ce0c8a4cc9dde9192db3ab6853a12db0f4332e5
+size 14244

checkpoint-2710/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53209d3b04f2f87654e5fe11597929f698f1fdb8df2f753da6225f7ac79a2eb4
+size 1064

checkpoint-2710/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2710/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2710/trainer_state.json

@@ -0,0 +1,785 @@
+{
+  "best_metric": 1.8915482759475708,
+  "best_model_checkpoint": "gpt2-large-open-assistant-guanaco/checkpoint-2710",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2710,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.1778407096862793,
+      "learning_rate": 1.845018450184502e-05,
+      "loss": 2.4702,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.888936996459961,
+      "learning_rate": 3.690036900369004e-05,
+      "loss": 2.379,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.8794102668762207,
+      "learning_rate": 5.535055350553506e-05,
+      "loss": 2.4576,
+      "step": 75
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9237180948257446,
+      "learning_rate": 7.380073800738008e-05,
+      "loss": 2.431,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.3720157146453857,
+      "learning_rate": 9.22509225092251e-05,
+      "loss": 2.5555,
+      "step": 125
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.955418348312378,
+      "learning_rate": 0.00011070110701107013,
+      "loss": 2.405,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.923417091369629,
+      "learning_rate": 0.00012915129151291514,
+      "loss": 2.4429,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.6975607872009277,
+      "learning_rate": 0.00014760147601476016,
+      "loss": 2.2604,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.038263320922852,
+      "learning_rate": 0.00016605166051660516,
+      "loss": 2.5249,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.835350513458252,
+      "learning_rate": 0.0001845018450184502,
+      "loss": 2.7203,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.5644915103912354,
+      "learning_rate": 0.0001996719967199672,
+      "loss": 2.6386,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.2700071334838867,
+      "learning_rate": 0.0001976219762197622,
+      "loss": 2.4893,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.0536715984344482,
+      "learning_rate": 0.0001955719557195572,
+      "loss": 2.5939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.561672329902649,
+      "learning_rate": 0.0001935219352193522,
+      "loss": 2.7238,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.4834322929382324,
+      "learning_rate": 0.0001914719147191472,
+      "loss": 2.4672,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.6992969512939453,
+      "learning_rate": 0.00018942189421894222,
+      "loss": 2.5833,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.595070719718933,
+      "learning_rate": 0.00018737187371873718,
+      "loss": 2.5067,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.07468318939209,
+      "learning_rate": 0.00018532185321853219,
+      "loss": 2.483,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.283381462097168,
+      "learning_rate": 0.0001832718327183272,
+      "loss": 2.6612,
+      "step": 475
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.5583351850509644,
+      "learning_rate": 0.0001812218122181222,
+      "loss": 2.3414,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2439337968826294,
+      "learning_rate": 0.0001791717917179172,
+      "loss": 2.4414,
+      "step": 525
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4025323390960693,
+      "learning_rate": 0.0001771217712177122,
+      "loss": 2.3685,
+      "step": 550
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.5767055749893188,
+      "learning_rate": 0.00017507175071750718,
+      "loss": 2.3423,
+      "step": 575
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.2068151235580444,
+      "learning_rate": 0.0001730217302173022,
+      "loss": 2.465,
+      "step": 600
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.0946199893951416,
+      "learning_rate": 0.00017097170971709717,
+      "loss": 2.288,
+      "step": 625
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.315215826034546,
+      "learning_rate": 0.00016892168921689218,
+      "loss": 2.4756,
+      "step": 650
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3037053346633911,
+      "learning_rate": 0.0001668716687166872,
+      "loss": 2.6019,
+      "step": 675
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.2501168251037598,
+      "learning_rate": 0.00016482164821648217,
+      "loss": 2.3108,
+      "step": 700
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.4587308168411255,
+      "learning_rate": 0.00016277162771627715,
+      "loss": 2.4512,
+      "step": 725
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.4319279193878174,
+      "learning_rate": 0.00016072160721607216,
+      "loss": 2.5111,
+      "step": 750
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.6068148612976074,
+      "learning_rate": 0.00015867158671586717,
+      "loss": 2.4429,
+      "step": 775
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2128015756607056,
+      "learning_rate": 0.00015662156621566218,
+      "loss": 2.4457,
+      "step": 800
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2929550409317017,
+      "learning_rate": 0.00015457154571545717,
+      "loss": 2.2653,
+      "step": 825
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.0177528858184814,
+      "learning_rate": 0.00015252152521525215,
+      "loss": 2.2931,
+      "step": 850
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.533103346824646,
+      "learning_rate": 0.00015047150471504716,
+      "loss": 2.2601,
+      "step": 875
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1346125602722168,
+      "learning_rate": 0.00014842148421484217,
+      "loss": 2.3318,
+      "step": 900
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0939571857452393,
+      "learning_rate": 0.00014637146371463715,
+      "loss": 2.249,
+      "step": 925
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.225317120552063,
+      "learning_rate": 0.00014432144321443216,
+      "loss": 2.4674,
+      "step": 950
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.3087507486343384,
+      "learning_rate": 0.00014227142271422714,
+      "loss": 2.298,
+      "step": 975
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.26546049118042,
+      "learning_rate": 0.00014022140221402215,
+      "loss": 2.3119,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.2002321481704712,
+      "learning_rate": 0.00013817138171381713,
+      "loss": 2.1619,
+      "step": 1025
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.589195728302002,
+      "learning_rate": 0.00013612136121361214,
+      "loss": 2.2499,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1953868865966797,
+      "learning_rate": 0.00013407134071340715,
+      "loss": 2.1875,
+      "step": 1075
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.0502057075500488,
+      "learning_rate": 0.00013202132021320216,
+      "loss": 2.259,
+      "step": 1100
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.4274191856384277,
+      "learning_rate": 0.00012997129971299714,
+      "loss": 2.2288,
+      "step": 1125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.33050537109375,
+      "learning_rate": 0.00012792127921279213,
+      "loss": 2.1854,
+      "step": 1150
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.1274808645248413,
+      "learning_rate": 0.00012587125871258714,
+      "loss": 2.0351,
+      "step": 1175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2254371643066406,
+      "learning_rate": 0.00012382123821238214,
+      "loss": 2.2282,
+      "step": 1200
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.305560827255249,
+      "learning_rate": 0.00012177121771217713,
+      "loss": 2.1982,
+      "step": 1225
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0613969564437866,
+      "learning_rate": 0.00011972119721197212,
+      "loss": 2.1863,
+      "step": 1250
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.2470930814743042,
+      "learning_rate": 0.00011767117671176713,
+      "loss": 2.0909,
+      "step": 1275
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.4893149137496948,
+      "learning_rate": 0.00011562115621156213,
+      "loss": 2.1255,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.1325526237487793,
+      "learning_rate": 0.00011357113571135711,
+      "loss": 2.1233,
+      "step": 1325
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.153321385383606,
+      "learning_rate": 0.00011152111521115212,
+      "loss": 2.2209,
+      "step": 1350
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.1444792747497559,
+      "learning_rate": 0.00010947109471094712,
+      "loss": 2.1678,
+      "step": 1375
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.9731519222259521,
+      "learning_rate": 0.00010742107421074213,
+      "loss": 2.186,
+      "step": 1400
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.3069313764572144,
+      "learning_rate": 0.00010537105371053711,
+      "loss": 2.0522,
+      "step": 1425
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.3358750343322754,
+      "learning_rate": 0.0001033210332103321,
+      "loss": 1.9899,
+      "step": 1450
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0077296495437622,
+      "learning_rate": 0.00010127101271012711,
+      "loss": 2.1628,
+      "step": 1475
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.1938546895980835,
+      "learning_rate": 9.922099220992211e-05,
+      "loss": 2.1514,
+      "step": 1500
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1697758436203003,
+      "learning_rate": 9.71709717097171e-05,
+      "loss": 2.1637,
+      "step": 1525
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.0194048881530762,
+      "learning_rate": 9.51209512095121e-05,
+      "loss": 2.2062,
+      "step": 1550
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9525765180587769,
+      "learning_rate": 9.30709307093071e-05,
+      "loss": 2.157,
+      "step": 1575
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.3280248641967773,
+      "learning_rate": 9.102091020910209e-05,
+      "loss": 2.0966,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2190978527069092,
+      "learning_rate": 8.89708897088971e-05,
+      "loss": 1.9294,
+      "step": 1625
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9637733697891235,
+      "learning_rate": 8.692086920869208e-05,
+      "loss": 2.0513,
+      "step": 1650
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0733612775802612,
+      "learning_rate": 8.48708487084871e-05,
+      "loss": 2.0574,
+      "step": 1675
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.1949636936187744,
+      "learning_rate": 8.282082820828209e-05,
+      "loss": 2.1535,
+      "step": 1700
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.285975694656372,
+      "learning_rate": 8.077080770807709e-05,
+      "loss": 2.0739,
+      "step": 1725
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.0896881818771362,
+      "learning_rate": 7.872078720787208e-05,
+      "loss": 2.0279,
+      "step": 1750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.0036427974700928,
+      "learning_rate": 7.667076670766709e-05,
+      "loss": 1.9592,
+      "step": 1775
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.148842453956604,
+      "learning_rate": 7.462074620746207e-05,
+      "loss": 1.9549,
+      "step": 1800
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.4055249691009521,
+      "learning_rate": 7.257072570725708e-05,
+      "loss": 2.1193,
+      "step": 1825
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.7423416972160339,
+      "learning_rate": 7.052070520705208e-05,
+      "loss": 2.0627,
+      "step": 1850
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.8528961539268494,
+      "learning_rate": 6.847068470684707e-05,
+      "loss": 1.9821,
+      "step": 1875
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.220268726348877,
+      "learning_rate": 6.642066420664207e-05,
+      "loss": 2.0314,
+      "step": 1900
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.8227468132972717,
+      "learning_rate": 6.437064370643707e-05,
+      "loss": 1.924,
+      "step": 1925
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.149190068244934,
+      "learning_rate": 6.232062320623206e-05,
+      "loss": 1.8974,
+      "step": 1950
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.2299059629440308,
+      "learning_rate": 6.027060270602707e-05,
+      "loss": 2.0567,
+      "step": 1975
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.226804256439209,
+      "learning_rate": 5.822058220582206e-05,
+      "loss": 2.0881,
+      "step": 2000
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.1045171022415161,
+      "learning_rate": 5.6170561705617064e-05,
+      "loss": 1.9007,
+      "step": 2025
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.82816481590271,
+      "learning_rate": 5.412054120541206e-05,
+      "loss": 2.0032,
+      "step": 2050
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9694753289222717,
+      "learning_rate": 5.207052070520706e-05,
+      "loss": 2.0872,
+      "step": 2075
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9572305679321289,
+      "learning_rate": 5.002050020500205e-05,
+      "loss": 2.112,
+      "step": 2100
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0792776346206665,
+      "learning_rate": 4.797047970479705e-05,
+      "loss": 2.0145,
+      "step": 2125
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.3833109140396118,
+      "learning_rate": 4.592045920459205e-05,
+      "loss": 2.1392,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8226168155670166,
+      "learning_rate": 4.3870438704387046e-05,
+      "loss": 2.0964,
+      "step": 2175
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.5212799310684204,
+      "learning_rate": 4.182041820418204e-05,
+      "loss": 2.0599,
+      "step": 2200
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.015734314918518,
+      "learning_rate": 3.9770397703977044e-05,
+      "loss": 2.0029,
+      "step": 2225
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.9501891732215881,
+      "learning_rate": 3.772037720377204e-05,
+      "loss": 2.0123,
+      "step": 2250
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9258189797401428,
+      "learning_rate": 3.5670356703567036e-05,
+      "loss": 1.9087,
+      "step": 2275
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.998928964138031,
+      "learning_rate": 3.362033620336203e-05,
+      "loss": 2.0364,
+      "step": 2300
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.24564790725708,
+      "learning_rate": 3.1570315703157035e-05,
+      "loss": 1.8917,
+      "step": 2325
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0782575607299805,
+      "learning_rate": 2.952029520295203e-05,
+      "loss": 1.9744,
+      "step": 2350
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2584232091903687,
+      "learning_rate": 2.747027470274703e-05,
+      "loss": 1.9452,
+      "step": 2375
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.038710355758667,
+      "learning_rate": 2.5420254202542026e-05,
+      "loss": 1.8455,
+      "step": 2400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.0375022888183594,
+      "learning_rate": 2.3370233702337025e-05,
+      "loss": 1.9034,
+      "step": 2425
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.314627766609192,
+      "learning_rate": 2.132021320213202e-05,
+      "loss": 2.0162,
+      "step": 2450
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.096312165260315,
+      "learning_rate": 1.927019270192702e-05,
+      "loss": 2.0927,
+      "step": 2475
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0984846353530884,
+      "learning_rate": 1.722017220172202e-05,
+      "loss": 1.8629,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.209221363067627,
+      "learning_rate": 1.5170151701517015e-05,
+      "loss": 1.9085,
+      "step": 2525
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.2675678730010986,
+      "learning_rate": 1.3120131201312013e-05,
+      "loss": 1.9813,
+      "step": 2550
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.2204258441925049,
+      "learning_rate": 1.1070110701107012e-05,
+      "loss": 1.8332,
+      "step": 2575
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0811994075775146,
+      "learning_rate": 9.02009020090201e-06,
+      "loss": 1.7946,
+      "step": 2600
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.219846248626709,
+      "learning_rate": 6.9700697006970075e-06,
+      "loss": 1.8714,
+      "step": 2625
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1557291746139526,
+      "learning_rate": 4.920049200492005e-06,
+      "loss": 1.7837,
+      "step": 2650
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.845923125743866,
+      "learning_rate": 2.870028700287003e-06,
+      "loss": 1.8496,
+      "step": 2675
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9930481314659119,
+      "learning_rate": 8.200082000820008e-07,
+      "loss": 1.8581,
+      "step": 2700
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8915482759475708,
+      "eval_runtime": 97.9153,
+      "eval_samples_per_second": 2.911,
+      "eval_steps_per_second": 1.46,
+      "step": 2710
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2710,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.35853879967744e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2710/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cc466fd18dfb7c394a2a1288f323cff10b0010bcb009b9a2dd7e4198d3ba10
+size 4984

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "openai-community/gpt2-large",
+  "activation_function": "gelu_new",
+  "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_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "float32",
+  "transformers_version": "4.39.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.39.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a15ef31765c9e9b172ebcb64d85327c9d4484629d79ea9ff6cf3b7483a8003d
+size 3096165928

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cc466fd18dfb7c394a2a1288f323cff10b0010bcb009b9a2dd7e4198d3ba10
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "openai-community/gpt2-large",
+    "project_name": "gpt2-large-open-assistant-guanaco",
+    "data_path": "timdettmers/openassistant-guanaco",
+    "train_split": "train",
+    "valid_split": "test",
+    "add_eos_token": false,
+    "block_size": -1,
+    "model_max_length": 1024,
+    "padding": null,
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": null,
+    "lr": 0.0002,
+    "epochs": 1,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": null,
+    "quantization": null,
+    "target_modules": null,
+    "merge_adapter": false,
+    "peft": false,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "prompt",
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "push_to_hub": true,
+    "repo_id": "sovitrath/gpt2_large_openassistant_guanaco_qlora",
+    "username": null
+}