Upload 13 files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|ASSISTANT|>": 50258,
+  "<|USER|>": 50257,
+  "[PAD]": 50259
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.2795707751154331,
+    "train_runtime": 1588.3255,
+    "train_samples": 10068,
+    "train_samples_per_second": 6.339,
+    "train_steps_per_second": 0.396
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "Locutusque/gpt2-large-conversational-retrain",
+  "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": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50260
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f96088b8d626145422e75587fe059255dccd845419f29599ff6ceb71230a4d8
+size 3096181288

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|USER|>",
+    "<|ASSISTANT|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|USER|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|ASSISTANT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|USER|>",
+    "<|ASSISTANT|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 256,
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.2795707751154331,
+    "train_runtime": 1588.3255,
+    "train_samples": 10068,
+    "train_samples_per_second": 6.339,
+    "train_steps_per_second": 0.396
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 5.941265106201172,
+  "best_model_checkpoint": "./output_dir/checkpoint-629",
+  "epoch": 0.9996027016289233,
+  "eval_steps": 50.0,
+  "global_step": 629,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.205087440381559e-05,
+      "loss": 1.0216,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 8.410174880763116e-05,
+      "loss": 0.3662,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 7.615262321144675e-05,
+      "loss": 0.3092,
+      "step": 150
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.820349761526232e-05,
+      "loss": 0.2477,
+      "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.0254372019077906e-05,
+      "loss": 0.2119,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.2305246422893485e-05,
+      "loss": 0.2179,
+      "step": 300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.4356120826709064e-05,
+      "loss": 0.2081,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.640699523052464e-05,
+      "loss": 0.1972,
+      "step": 400
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.8457869634340222e-05,
+      "loss": 0.193,
+      "step": 450
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.05087440381558e-05,
+      "loss": 0.1779,
+      "step": 500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2559618441971382e-05,
+      "loss": 0.1359,
+      "step": 550
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.610492845786963e-06,
+      "loss": 0.1441,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu-1": 22.0522,
+      "eval_bleu-2": 5.8235,
+      "eval_bleu-3": 3.8638,
+      "eval_bleu-4": 3.3488,
+      "eval_gen_len": 116.6172,
+      "eval_loss": 5.941265106201172,
+      "eval_runtime": 10.8851,
+      "eval_samples_per_second": 1.102,
+      "eval_steps_per_second": 1.102,
+      "step": 629
+    },
+    {
+      "epoch": 1.0,
+      "step": 629,
+      "total_flos": 1.09505141538816e+16,
+      "train_loss": 0.2795707751154331,
+      "train_runtime": 1588.3255,
+      "train_samples_per_second": 6.339,
+      "train_steps_per_second": 0.396
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 629,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.09505141538816e+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:c1631e75648fc8ac7786098f5039728689e297f25a7ed1d7d660bb6f47cd0bfc
+size 5048