Upload folder using huggingface_hub

.gitattributes

@@ -0,0 +1,2 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+optimizer.pt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "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": "4.45.0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0babfe95faee265d9d577fe2c56d57a9b4c5e68eb45a4725029da76c9390da22
+size 1426462208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d871bdcaf06084e3588a76936a4a0f38f2be601a3808b153e7b50db116c96d9
+size 2853107898

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.046627524414171784,
+  "eval_steps": 500,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004662752441417178,
+      "grad_norm": 1.3671598434448242,
+      "learning_rate": 4.976690900545356e-05,
+      "loss": 4.8243,
+      "step": 10000
+    },
+    {
+      "epoch": 0.009325504882834356,
+      "grad_norm": 1.3568960428237915,
+      "learning_rate": 4.953384132466932e-05,
+      "loss": 3.7236,
+      "step": 20000
+    },
+    {
+      "epoch": 0.013988257324251536,
+      "grad_norm": 1.4119852781295776,
+      "learning_rate": 4.930079695764729e-05,
+      "loss": 3.4332,
+      "step": 30000
+    },
+    {
+      "epoch": 0.018651009765668712,
+      "grad_norm": 1.1216883659362793,
+      "learning_rate": 4.906772927686305e-05,
+      "loss": 3.2825,
+      "step": 40000
+    },
+    {
+      "epoch": 0.023313762207085892,
+      "grad_norm": 1.2323102951049805,
+      "learning_rate": 4.883468490984102e-05,
+      "loss": 3.1866,
+      "step": 50000
+    },
+    {
+      "epoch": 0.02797651464850307,
+      "grad_norm": 0.9565121531486511,
+      "learning_rate": 4.860161722905678e-05,
+      "loss": 3.1126,
+      "step": 60000
+    },
+    {
+      "epoch": 0.03263926708992025,
+      "grad_norm": 1.1173287630081177,
+      "learning_rate": 4.836861948955917e-05,
+      "loss": 3.0577,
+      "step": 70000
+    },
+    {
+      "epoch": 0.037302019531337424,
+      "grad_norm": 1.4626446962356567,
+      "learning_rate": 4.813555180877493e-05,
+      "loss": 3.0145,
+      "step": 80000
+    },
+    {
+      "epoch": 0.041964771972754604,
+      "grad_norm": 1.0016125440597534,
+      "learning_rate": 4.790246081422848e-05,
+      "loss": 2.973,
+      "step": 90000
+    },
+    {
+      "epoch": 0.046627524414171784,
+      "grad_norm": 1.3417049646377563,
+      "learning_rate": 4.766941644720645e-05,
+      "loss": 2.9423,
+      "step": 100000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 2144656,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 100000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.465742773984821e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}