End of training: uploading model

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "openai-community/openai-gpt",
+  "afn": "gelu",
+  "architectures": [
+    "OpenAIGPTLMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "openai-gpt",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 512,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "resid_pdrop": 0.1,
+  "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": "4.45.2",
+  "vocab_size": 40478
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d7c32f0334a0ce90a498cc79029f00361c28da876a7a58a409e196005718e5
+size 466153952

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164826cf6106f76cafc2baa9d57967a571af8b739a283c411b510cab8afdbcb8
+size 932396410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bcc13f10b1188ce8a0d9b98d73cf3f39a03086591cd9be44a83cd39f8c7398
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e662b3037da6f5546c7ca64e701dbaf1865be7586c229850bd45d1817f03a4
+size 1064

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "model_max_length": 512,
+  "tokenizer_class": "OpenAIGPTTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.9040439128875732,
+      "eval_runtime": 17.2228,
+      "eval_samples_per_second": 27.638,
+      "eval_steps_per_second": 3.484,
+      "step": 38
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.8737525939941406,
+      "eval_runtime": 20.5198,
+      "eval_samples_per_second": 23.197,
+      "eval_steps_per_second": 2.924,
+      "step": 76
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 1.8681073188781738,
+      "learning_rate": 6.140350877192982e-06,
+      "loss": 3.8733,
+      "step": 100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 114,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 235158582067200.0,
+  "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:bef6700f91a033e4b7dd8feb09d39654a5ca5d619d04ac39bf6ddaacb35df73f
+size 5176