Upload 13 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "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": "4.33.3"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2c22762eaf70ecf2fd77fc29b4424984cb6183337c1094c81af1d77e6f3059
+size 6192613541

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67adc3e4d4243a12abdd92ba37d4036c8204f1d70d05a1aa50dabd63bb190e14
+size 3096262685

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c59c6a8b3d97681d3db6a59d5dc7962190df567b36f03b0b71d2c360b12542
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4778dfdffcf7b3e84fb068c9a8f89d56d0f499df78c5826eed3fb3518813f0
+size 627

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2950,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.305084745762712e-05,
+      "loss": 0.0907,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.05301688611507416,
+      "eval_runtime": 22.0022,
+      "eval_samples_per_second": 6.727,
+      "eval_steps_per_second": 3.363,
+      "step": 590
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.610169491525424e-05,
+      "loss": 0.044,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.05314206704497337,
+      "eval_runtime": 22.0246,
+      "eval_samples_per_second": 6.72,
+      "eval_steps_per_second": 3.36,
+      "step": 1180
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.915254237288136e-05,
+      "loss": 0.0324,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.0601324662566185,
+      "eval_runtime": 22.0071,
+      "eval_samples_per_second": 6.725,
+      "eval_steps_per_second": 3.363,
+      "step": 1770
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.2203389830508473e-05,
+      "loss": 0.0215,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.07468509674072266,
+      "eval_runtime": 22.0212,
+      "eval_samples_per_second": 6.721,
+      "eval_steps_per_second": 3.36,
+      "step": 2360
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 1.5254237288135596e-05,
+      "loss": 0.0133,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.08810325711965561,
+      "eval_runtime": 22.015,
+      "eval_samples_per_second": 6.723,
+      "eval_steps_per_second": 3.361,
+      "step": 2950
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2950,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.567886864384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7619f81d0ad821dda3347259040a0586efa8906da1aff1cd38be231bf4e0c2f7
+size 4091