Hello gpt-qa

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "flax-community/gpt2-medium-persian",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 6,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 5,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "pad_token_id": 1,
+  "predict_special_tokens": true,
+  "resid_pdrop": 0.1,
+  "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": 256,
+      "min_length": 32,
+      "top_k": 50,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713c4de95949544ece528027ee762f59a128baf0ed4b9db9da6ca99429469c3e
+size 1443528665

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56dc1acc04c811f07b8561c4e92f3e1130743be543ae36174f6a5aee298231c
+size 1418594792

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "pad_token": "<pad>", "special_tokens_map_file": null, "name_or_path": "flax-community/gpt2-medium-persian", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9998406882268602,
+  "global_step": 9414,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.4875e-05,
+      "loss": 4.2616,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 2.4269070625305176,
+      "eval_runtime": 59.5268,
+      "eval_samples_per_second": 10.936,
+      "eval_steps_per_second": 10.936,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.9850000000000006e-05,
+      "loss": 1.9451,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.3068270683288574,
+      "eval_runtime": 59.0527,
+      "eval_samples_per_second": 11.024,
+      "eval_steps_per_second": 11.024,
+      "step": 2000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.329646614513084e-05,
+      "loss": 1.5082,
+      "step": 3000
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.131048560142517,
+      "eval_runtime": 59.5847,
+      "eval_samples_per_second": 10.926,
+      "eval_steps_per_second": 10.926,
+      "step": 3000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 3.6559212301052064e-05,
+      "loss": 1.1402,
+      "step": 4000
+    },
+    {
+      "epoch": 1.27,
+      "eval_loss": 1.0661729574203491,
+      "eval_runtime": 59.6476,
+      "eval_samples_per_second": 10.914,
+      "eval_steps_per_second": 10.914,
+      "step": 4000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.9815214459131374e-05,
+      "loss": 1.0806,
+      "step": 5000
+    },
+    {
+      "epoch": 1.59,
+      "eval_loss": 1.0320521593093872,
+      "eval_runtime": 59.5322,
+      "eval_samples_per_second": 10.935,
+      "eval_steps_per_second": 10.935,
+      "step": 5000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.3071216617210683e-05,
+      "loss": 1.0331,
+      "step": 6000
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 1.0125774145126343,
+      "eval_runtime": 58.9824,
+      "eval_samples_per_second": 11.037,
+      "eval_steps_per_second": 11.037,
+      "step": 6000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.6327218775289993e-05,
+      "loss": 0.8337,
+      "step": 7000
+    },
+    {
+      "epoch": 2.23,
+      "eval_loss": 1.0233821868896484,
+      "eval_runtime": 59.1959,
+      "eval_samples_per_second": 10.997,
+      "eval_steps_per_second": 10.997,
+      "step": 7000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 9.589964931211222e-06,
+      "loss": 0.7498,
+      "step": 8000
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.0264060497283936,
+      "eval_runtime": 59.237,
+      "eval_samples_per_second": 10.99,
+      "eval_steps_per_second": 10.99,
+      "step": 8000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.852711087132452e-06,
+      "loss": 0.7291,
+      "step": 9000
+    },
+    {
+      "epoch": 2.87,
+      "eval_loss": 1.0013467073440552,
+      "eval_runtime": 59.1148,
+      "eval_samples_per_second": 11.012,
+      "eval_steps_per_second": 11.012,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "step": 9414,
+      "total_flos": 9795205750726656.0,
+      "train_loss": 1.4433987489647233,
+      "train_runtime": 7416.9186,
+      "train_samples_per_second": 2.539,
+      "train_steps_per_second": 1.269
+    }
+  ],
+  "max_steps": 9414,
+  "num_train_epochs": 3,
+  "total_flos": 9795205750726656.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e398317235c15315fdcc2e1dac04c9bc69070f57b45724d368fe39ba3e65e1c7
+size 2735