Upload 13 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.49.0",
+  "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": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31056e353ca46905c294b451b8808867caeff9cb8f5b315bf27033ed90027b4c
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1026217301c8687e048011def58b0cb7fd3e59ae4e69dea6130f03088ffbd3b5
+size 995642298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2768285b45b2a0c05f6f50bbb8c0287fca6f62a8cde6d1b1f02151ac72ee8dc
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03550d16e77b042eb2dffd9a4ede29bff5c08f55de55b85c8b9309bcec0b7eda
+size 1064

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

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -108.79365539550781,
+      "eval_logits/rejected": -151.2770233154297,
+      "eval_logps/chosen": -267.2356872558594,
+      "eval_logps/rejected": -185.09524536132812,
+      "eval_loss": 0.6931471824645996,
+      "eval_rewards/accuracies": 0.0,
+      "eval_rewards/chosen": 0.0,
+      "eval_rewards/margins": 0.0,
+      "eval_rewards/rejected": 0.0,
+      "eval_runtime": 0.5516,
+      "eval_samples_per_second": 9.064,
+      "eval_steps_per_second": 1.813,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_logits/chosen": -108.78112030029297,
+      "eval_logits/rejected": -151.3362274169922,
+      "eval_logps/chosen": -268.0252380371094,
+      "eval_logps/rejected": -187.6125946044922,
+      "eval_loss": 0.6203721761703491,
+      "eval_rewards/accuracies": 0.6000000238418579,
+      "eval_rewards/chosen": -0.07895644754171371,
+      "eval_rewards/margins": 0.1727786362171173,
+      "eval_rewards/rejected": -0.2517350912094116,
+      "eval_runtime": 0.5661,
+      "eval_samples_per_second": 8.832,
+      "eval_steps_per_second": 1.766,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_logits/chosen": -108.68714904785156,
+      "eval_logits/rejected": -151.747314453125,
+      "eval_logps/chosen": -266.5977783203125,
+      "eval_logps/rejected": -185.63877868652344,
+      "eval_loss": 0.6367835402488708,
+      "eval_rewards/accuracies": 0.800000011920929,
+      "eval_rewards/chosen": 0.06378966569900513,
+      "eval_rewards/margins": 0.11814422905445099,
+      "eval_rewards/rejected": -0.05435454845428467,
+      "eval_runtime": 0.5628,
+      "eval_samples_per_second": 8.884,
+      "eval_steps_per_second": 1.777,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_logits/chosen": -109.2767333984375,
+      "eval_logits/rejected": -152.4813232421875,
+      "eval_logps/chosen": -267.413818359375,
+      "eval_logps/rejected": -187.46786499023438,
+      "eval_loss": 0.5958372950553894,
+      "eval_rewards/accuracies": 0.800000011920929,
+      "eval_rewards/chosen": -0.017816483974456787,
+      "eval_rewards/margins": 0.21944628655910492,
+      "eval_rewards/rejected": -0.23726272583007812,
+      "eval_runtime": 0.5642,
+      "eval_samples_per_second": 8.862,
+      "eval_steps_per_second": 1.772,
+      "step": 4
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617821ae5c8e289ffacbe507defd337c0d2fe8b314c628d9c8d81bd49616e214
+size 6136