Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 16,
+  "n_positions": 2048,
+  "pad_token_id": null,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.14.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b51646facbd1c6afee47be5fee20c04a9e87b32f8a8a72c00418e1e4a9e8d6
+size 1020429920

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e4ea01734696582c9ad9fa7e3e94a44e7afd73531ee86c32043e1e8eeb1d8a
+size 2040982667

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a15677c2db6cf1cb5dc0d0f09ddd3641bf61f5c3dfe47068cfa452e7644dc2
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76c017a8b7e020ae1aa79833a43f97bb41a8447650bfd23262d5bfaf6832c03
+size 1465

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 7265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06882312456985547,
+      "grad_norm": 0.6455472111701965,
+      "learning_rate": 0.00014969999999999998,
+      "loss": 4.89012646484375,
+      "step": 500
+    },
+    {
+      "epoch": 0.13764624913971094,
+      "grad_norm": 0.546249508857727,
+      "learning_rate": 0.00029969999999999997,
+      "loss": 2.893400146484375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20646937370956642,
+      "grad_norm": 0.43270039558410645,
+      "learning_rate": 0.00029532853869058343,
+      "loss": 2.0761533203125,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27529249827942187,
+      "grad_norm": 0.37517938017845154,
+      "learning_rate": 0.00028156901467649766,
+      "loss": 1.810734619140625,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3441156228492774,
+      "grad_norm": 0.3215874433517456,
+      "learning_rate": 0.0002595818572780397,
+      "loss": 1.6727777099609376,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41293874741913283,
+      "grad_norm": 0.3056698441505432,
+      "learning_rate": 0.00023074202754271595,
+      "loss": 1.5861005859375,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4817618719889883,
+      "grad_norm": 0.3129520118236542,
+      "learning_rate": 0.00019685301656235683,
+      "loss": 1.52688525390625,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5505849965588437,
+      "grad_norm": 0.2816142439842224,
+      "learning_rate": 0.00016003406463674675,
+      "loss": 1.479068115234375,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6194081211286993,
+      "grad_norm": 0.27311035990715027,
+      "learning_rate": 0.0001225876351444069,
+      "loss": 1.440277587890625,
+      "step": 4500
+    },
+    {
+      "epoch": 0.6882312456985548,
+      "grad_norm": 0.26458030939102173,
+      "learning_rate": 8.685543060681822e-05,
+      "loss": 1.4058232421875,
+      "step": 5000
+    },
+    {
+      "epoch": 0.7570543702684102,
+      "grad_norm": 0.2703981101512909,
+      "learning_rate": 5.5071954943262434e-05,
+      "loss": 1.3814718017578125,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8258774948382657,
+      "grad_norm": 0.2578605115413666,
+      "learning_rate": 2.9224779361777036e-05,
+      "loss": 1.3585260009765625,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8947006194081212,
+      "grad_norm": 0.2610727846622467,
+      "learning_rate": 1.0930250121614964e-05,
+      "loss": 1.34341748046875,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9635237439779766,
+      "grad_norm": 0.2619054615497589,
+      "learning_rate": 1.332410749269447e-06,
+      "loss": 1.3385958251953125,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 5.757369439129436e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a5aad5c6db01ba77f0e9072588b02831390f38ac2a919a65e36485da8f4f18
+size 5137