add model weights and checkpoints

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: OpenAI license
 datasets: Microsoft/ChatBench
 language: en
 base_model: distilgpt2

checkpoint-1560/config.json

@@ -0,0 +1,46 @@
+{
+  "_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,
+  "pad_token_id": 50256,
+  "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": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-1560/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

checkpoint-1560/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51c0f6938c3da25cbbccf3db7389619eba378ee98d8fbd6ca00f989dd13614f
+size 327657928

checkpoint-1560/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2e661dbb7ea237a9a392114f7c0cf424fc010ed15834dd1933ba73980b9953
+size 655364939

checkpoint-1560/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49d7668609aeebb500fa1f9afb3eb242466b4fc288d90e791e235195fefd448
+size 15429

checkpoint-1560/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39184abc08b038f5da3f9f30b07db28cae224bf02c07962f2960f6dc33c84c14
+size 15429

checkpoint-1560/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f4efb4ef6fcd5a6880f687efbbd55da5527bb2c57882e593b4af4dbaca1043
+size 15429

checkpoint-1560/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4cbc6a1b8f4decdd56929e40bbbf34e540159fc93cabde87ec65170c5e909b
+size 15429

checkpoint-1560/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881e40e843583b1f863867f6c2a963ed359f55623e11a88129b36eba451469ab
+size 1383

checkpoint-1560/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf56008cfe9be3e3897fb451f2c77d53e0cfca751cea61314cdba3f16c1d976
+size 1465

checkpoint-1560/special_tokens_map.json

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

checkpoint-1560/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|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1560/trainer_state.json

@@ -0,0 +1,155 @@
+{
+  "best_global_step": 780,
+  "best_metric": 1.4478473663330078,
+  "best_model_checkpoint": "results/models/distilgpt2_split_3/checkpoint-780",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 2.1318576335906982,
+      "learning_rate": 4.689102564102564e-05,
+      "loss": 1.8462,
+      "step": 100
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 1.8293204307556152,
+      "learning_rate": 4.368589743589744e-05,
+      "loss": 1.5051,
+      "step": 200
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 2.407285690307617,
+      "learning_rate": 4.0480769230769236e-05,
+      "loss": 1.4097,
+      "step": 300
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 2.0177223682403564,
+      "learning_rate": 3.727564102564103e-05,
+      "loss": 1.3136,
+      "step": 400
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 1.5830180644989014,
+      "learning_rate": 3.4070512820512825e-05,
+      "loss": 1.2698,
+      "step": 500
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.6503092050552368,
+      "learning_rate": 3.0865384615384616e-05,
+      "loss": 1.2133,
+      "step": 600
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 1.608035922050476,
+      "learning_rate": 2.7660256410256413e-05,
+      "loss": 1.1817,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4478473663330078,
+      "eval_runtime": 14.1171,
+      "eval_samples_per_second": 370.259,
+      "eval_steps_per_second": 23.163,
+      "step": 780
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 1.399240493774414,
+      "learning_rate": 2.4455128205128204e-05,
+      "loss": 1.1556,
+      "step": 800
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 1.8416355848312378,
+      "learning_rate": 2.125e-05,
+      "loss": 1.1005,
+      "step": 900
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 1.4166646003723145,
+      "learning_rate": 1.8044871794871796e-05,
+      "loss": 1.0782,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4102564102564101,
+      "grad_norm": 1.3811384439468384,
+      "learning_rate": 1.483974358974359e-05,
+      "loss": 1.0568,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.5326135158538818,
+      "learning_rate": 1.1634615384615386e-05,
+      "loss": 1.0446,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.2560216188430786,
+      "learning_rate": 8.42948717948718e-06,
+      "loss": 1.0604,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 1.4168336391448975,
+      "learning_rate": 5.224358974358975e-06,
+      "loss": 1.0371,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 1.3679345846176147,
+      "learning_rate": 2.0192307692307692e-06,
+      "loss": 1.0274,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.4688283205032349,
+      "eval_runtime": 14.0926,
+      "eval_samples_per_second": 370.904,
+      "eval_steps_per_second": 23.204,
+      "step": 1560
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6521966894776320.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1560/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c32dd41a8369fb1de0d9c88ebf98453f3e9c428ee5572568b270ac107b3cdd
+size 5713

checkpoint-780/config.json

@@ -0,0 +1,46 @@
+{
+  "_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,
+  "pad_token_id": 50256,
+  "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": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-780/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

checkpoint-780/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c73128d51531ed56973d2600c126914bb9c060a07668e27e954917d42bc7f0
+size 327657928

checkpoint-780/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431cd49432f0ee23b154493cc4270a6c1108ddb405ccaa17082b620221beb343
+size 655364939

checkpoint-780/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0513a2baa362555a739508f5bcf66bc226cb73980c16f91e1e4719af8acf5e
+size 15429

checkpoint-780/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f81b34fbef8c58bad9b73383237ff3b398ca04efab5da30241d984cff9614e
+size 15429

checkpoint-780/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df45efa4b80d600b223e6c8723ba385ab51e1583537109bfbee205212d81958e
+size 15429

checkpoint-780/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5814355331b202952d09c81426e73235c388647c762f28dc47dd06637e1443
+size 15429

checkpoint-780/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ebc4f4eaf3317083143e7fd7aa804ff935640029ab9f1c0a6b07ac094c65427
+size 1383

checkpoint-780/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9413c54ddfa601f6097d71d5a210892c27a41aafd2f10fccfab127e437a9b27f
+size 1465

checkpoint-780/special_tokens_map.json

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

checkpoint-780/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|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-780/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_global_step": 780,
+  "best_metric": 1.4478473663330078,
+  "best_model_checkpoint": "results/models/distilgpt2_split_3/checkpoint-780",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 780,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 2.1318576335906982,
+      "learning_rate": 4.689102564102564e-05,
+      "loss": 1.8462,
+      "step": 100
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 1.8293204307556152,
+      "learning_rate": 4.368589743589744e-05,
+      "loss": 1.5051,
+      "step": 200
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 2.407285690307617,
+      "learning_rate": 4.0480769230769236e-05,
+      "loss": 1.4097,
+      "step": 300
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 2.0177223682403564,
+      "learning_rate": 3.727564102564103e-05,
+      "loss": 1.3136,
+      "step": 400
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 1.5830180644989014,
+      "learning_rate": 3.4070512820512825e-05,
+      "loss": 1.2698,
+      "step": 500
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.6503092050552368,
+      "learning_rate": 3.0865384615384616e-05,
+      "loss": 1.2133,
+      "step": 600
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 1.608035922050476,
+      "learning_rate": 2.7660256410256413e-05,
+      "loss": 1.1817,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4478473663330078,
+      "eval_runtime": 14.1171,
+      "eval_samples_per_second": 370.259,
+      "eval_steps_per_second": 23.163,
+      "step": 780
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3260983447388160.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-780/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c32dd41a8369fb1de0d9c88ebf98453f3e9c428ee5572568b270ac107b3cdd
+size 5713

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c73128d51531ed56973d2600c126914bb9c060a07668e27e954917d42bc7f0
+size 327657928