Upload 9 files

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b933eb783a99e61bb56c7166eb048e9e32ea03e570343980e5ffecb5dba32777
+size 500941440

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18da2c9155cd816360d678fb26f921486eac0d676d4bdfa7ee845ae774c8febe
+size 1001976762

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20fef646b31bd0da60e042930355f95bad6e9309ba53f239d47962584cee4ee
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9acc78a1984093d893ebbe2aa3e8c676c849c54208c1237140b3e76d9d7d85
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d7bffa60dee30450bbde43b505ba5d1aeb72b9b39eb756f6197faaaea51f34
+size 1064

trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.088139281828074,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0544069640914037,
+      "grad_norm": 1.3827155828475952,
+      "learning_rate": 4.913855640188611e-05,
+      "loss": 2.226,
+      "step": 100
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "grad_norm": 0.7897017002105713,
+      "learning_rate": 4.823177366702939e-05,
+      "loss": 1.2196,
+      "step": 200
+    },
+    {
+      "epoch": 0.1632208922742111,
+      "grad_norm": 1.1451177597045898,
+      "learning_rate": 4.732499093217265e-05,
+      "loss": 1.2182,
+      "step": 300
+    },
+    {
+      "epoch": 0.2176278563656148,
+      "grad_norm": 1.9186509847640991,
+      "learning_rate": 4.641820819731593e-05,
+      "loss": 1.2724,
+      "step": 400
+    },
+    {
+      "epoch": 0.2720348204570185,
+      "grad_norm": 1.4905147552490234,
+      "learning_rate": 4.5511425462459194e-05,
+      "loss": 1.1771,
+      "step": 500
+    },
+    {
+      "epoch": 0.3264417845484222,
+      "grad_norm": 1.3085367679595947,
+      "learning_rate": 4.460464272760247e-05,
+      "loss": 1.1407,
+      "step": 600
+    },
+    {
+      "epoch": 0.3808487486398259,
+      "grad_norm": 1.6310745477676392,
+      "learning_rate": 4.3697859992745737e-05,
+      "loss": 1.1146,
+      "step": 700
+    },
+    {
+      "epoch": 0.4352557127312296,
+      "grad_norm": 1.0869531631469727,
+      "learning_rate": 4.2791077257889015e-05,
+      "loss": 1.1015,
+      "step": 800
+    },
+    {
+      "epoch": 0.4896626768226333,
+      "grad_norm": 1.387512445449829,
+      "learning_rate": 4.1884294523032286e-05,
+      "loss": 1.0764,
+      "step": 900
+    },
+    {
+      "epoch": 0.544069640914037,
+      "grad_norm": 1.8865373134613037,
+      "learning_rate": 4.097751178817556e-05,
+      "loss": 1.079,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5984766050054406,
+      "grad_norm": 1.1464284658432007,
+      "learning_rate": 4.007072905331883e-05,
+      "loss": 1.1797,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6528835690968444,
+      "grad_norm": 1.3149100542068481,
+      "learning_rate": 3.91639463184621e-05,
+      "loss": 1.0676,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7072905331882481,
+      "grad_norm": 1.3868759870529175,
+      "learning_rate": 3.825716358360537e-05,
+      "loss": 1.1711,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7616974972796517,
+      "grad_norm": 1.046326994895935,
+      "learning_rate": 3.735038084874864e-05,
+      "loss": 1.1291,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8161044613710555,
+      "grad_norm": 0.825319230556488,
+      "learning_rate": 3.6443598113891914e-05,
+      "loss": 1.0609,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8705114254624592,
+      "grad_norm": 1.6592735052108765,
+      "learning_rate": 3.5536815379035185e-05,
+      "loss": 1.0676,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9249183895538629,
+      "grad_norm": 1.2844988107681274,
+      "learning_rate": 3.4630032644178456e-05,
+      "loss": 1.062,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9793253536452666,
+      "grad_norm": 1.3953850269317627,
+      "learning_rate": 3.372324990932173e-05,
+      "loss": 1.0538,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0337323177366704,
+      "grad_norm": 1.2760506868362427,
+      "learning_rate": 3.2816467174465e-05,
+      "loss": 0.968,
+      "step": 1900
+    },
+    {
+      "epoch": 1.088139281828074,
+      "grad_norm": 1.5799071788787842,
+      "learning_rate": 3.190968443960827e-05,
+      "loss": 0.9365,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5514,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2090336256000000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b92fad9c09a73aae21441d2f394f747f6e1203d0cca82e74f610a1fc8e8dd1
+size 5304