رفع النموذج النهائي مع جميع الملفات للتجربة أو إعادة التدريب

config.json

@@ -0,0 +1,38 @@
+{
+  "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": "4.55.4",
+  "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": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45be989d3511f4d94fad2552286260011ad42f09985f600f654c42455c17cf06
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d68a7966fa57efce40bba244718f5b105a1c0b270e535c5a1a9df4479a91188
+size 995644811

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8327635f702c9652852e8a4ff3ae273f89cd085970f61e237f78662d199e34dd
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ccff13654eb643cada7d9b3c064203a1528bc3b6806d14ae61b19deceb9580
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6341bc67914d50adde2854d0ef31de777e24a2c75bcad6c093b0d2b4db7708
+size 1465

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 +1,206 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3699849693606197,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018499248468030985,
+      "grad_norm": 2.7567262649536133,
+      "learning_rate": 9.9e-06,
+      "loss": 2.3993,
+      "step": 100
+    },
+    {
+      "epoch": 0.03699849693606197,
+      "grad_norm": 2.469092845916748,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 1.8863,
+      "step": 200
+    },
+    {
+      "epoch": 0.05549774540409296,
+      "grad_norm": 2.287935256958008,
+      "learning_rate": 1.987638906230491e-05,
+      "loss": 1.6964,
+      "step": 300
+    },
+    {
+      "epoch": 0.07399699387212394,
+      "grad_norm": 2.158879518508911,
+      "learning_rate": 1.9751529529279564e-05,
+      "loss": 1.6172,
+      "step": 400
+    },
+    {
+      "epoch": 0.09249624234015492,
+      "grad_norm": 2.3301937580108643,
+      "learning_rate": 1.9626669996254215e-05,
+      "loss": 1.5604,
+      "step": 500
+    },
+    {
+      "epoch": 0.09249624234015492,
+      "eval_loss": 1.5311822891235352,
+      "eval_runtime": 836.5935,
+      "eval_samples_per_second": 22.154,
+      "eval_steps_per_second": 11.077,
+      "step": 500
+    },
+    {
+      "epoch": 0.11099549080818592,
+      "grad_norm": 1.958460807800293,
+      "learning_rate": 1.950181046322887e-05,
+      "loss": 1.5221,
+      "step": 600
+    },
+    {
+      "epoch": 0.1294947392762169,
+      "grad_norm": 2.088949680328369,
+      "learning_rate": 1.9376950930203523e-05,
+      "loss": 1.5003,
+      "step": 700
+    },
+    {
+      "epoch": 0.14799398774424788,
+      "grad_norm": 2.262972593307495,
+      "learning_rate": 1.9252091397178178e-05,
+      "loss": 1.4501,
+      "step": 800
+    },
+    {
+      "epoch": 0.16649323621227888,
+      "grad_norm": 1.8716174364089966,
+      "learning_rate": 1.912723186415283e-05,
+      "loss": 1.4359,
+      "step": 900
+    },
+    {
+      "epoch": 0.18499248468030985,
+      "grad_norm": 1.6942836046218872,
+      "learning_rate": 1.9002372331127483e-05,
+      "loss": 1.4317,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18499248468030985,
+      "eval_loss": 1.4133305549621582,
+      "eval_runtime": 838.9381,
+      "eval_samples_per_second": 22.092,
+      "eval_steps_per_second": 11.046,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20349173314834085,
+      "grad_norm": 2.1511948108673096,
+      "learning_rate": 1.8877512798102137e-05,
+      "loss": 1.4053,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22199098161637185,
+      "grad_norm": 1.7339736223220825,
+      "learning_rate": 1.875265326507679e-05,
+      "loss": 1.3915,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24049023008440282,
+      "grad_norm": 1.9543105363845825,
+      "learning_rate": 1.8627793732051446e-05,
+      "loss": 1.3825,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2589894785524338,
+      "grad_norm": 1.7334178686141968,
+      "learning_rate": 1.8502934199026097e-05,
+      "loss": 1.3708,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2774887270204648,
+      "grad_norm": 1.5893480777740479,
+      "learning_rate": 1.837807466600075e-05,
+      "loss": 1.3594,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2774887270204648,
+      "eval_loss": 1.3516819477081299,
+      "eval_runtime": 838.2447,
+      "eval_samples_per_second": 22.11,
+      "eval_steps_per_second": 11.055,
+      "step": 1500
+    },
+    {
+      "epoch": 0.29598797548849576,
+      "grad_norm": 1.9415546655654907,
+      "learning_rate": 1.8253215132975405e-05,
+      "loss": 1.3602,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3144872239565268,
+      "grad_norm": 1.6256144046783447,
+      "learning_rate": 1.812835559995006e-05,
+      "loss": 1.3297,
+      "step": 1700
+    },
+    {
+      "epoch": 0.33298647242455776,
+      "grad_norm": 1.6166146993637085,
+      "learning_rate": 1.800349606692471e-05,
+      "loss": 1.3273,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3514857208925887,
+      "grad_norm": 1.7110105752944946,
+      "learning_rate": 1.7878636533899365e-05,
+      "loss": 1.2984,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3699849693606197,
+      "grad_norm": 1.4126442670822144,
+      "learning_rate": 1.7753777000874016e-05,
+      "loss": 1.3113,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3699849693606197,
+      "eval_loss": 1.3114128112792969,
+      "eval_runtime": 836.695,
+      "eval_samples_per_second": 22.151,
+      "eval_steps_per_second": 11.076,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 16218,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6722690048e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b589167ffa8a5961cb77283dec1a9d9b8eafe41c4a04742013a7a0d742c3efb
+size 5713