First model version

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "./models/GPT-SW3/gpt-sw3-1.3b",
+  "activation_function": "gelu",
+  "apply_query_key_layer_scaling": true,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.01,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 2048,
+  "n_head": 32,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "normalize_attention_scores": true,
+  "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,
+  "tokenizer_class": "GPTSw3Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": false,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0",
+  "use_cache": false
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9617a598fbd7667c7a78bc15b14405c64980a82ccb8dc20aca71fc6d6779c83a
+size 10751127593

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2982c7a7bf826d1b995437b2655e39498e3d1c4ed17125dbc9f0fa63a2bb6d96
+size 5476248649

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c672af696938b9291cd36150807e52ff020a1679f83b21f7760163efdd7e1bf5
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc95b508acc43782ce53498e0ad90507a699c09b1452ef7ccf2e247b7d5df105
+size 623

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8036913731674553,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 7.78816199376947e-06,
+      "loss": 2.8614,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.557632398753894e-05,
+      "loss": 0.7943,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.9626168224299065e-05,
+      "loss": 0.7679,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.8760816891658016e-05,
+      "loss": 0.7359,
+      "step": 2000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.7895465559016964e-05,
+      "loss": 0.6255,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.7030114226375908e-05,
+      "loss": 0.5942,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.616476289373486e-05,
+      "loss": 0.5809,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5299411561093806e-05,
+      "loss": 0.5899,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.4434060228452753e-05,
+      "loss": 0.5161,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.3568708895811699e-05,
+      "loss": 0.4241,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.2703357563170648e-05,
+      "loss": 0.4283,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.1838006230529595e-05,
+      "loss": 0.4283,
+      "step": 6000
+    }
+  ],
+  "max_steps": 12840,
+  "num_train_epochs": 6,
+  "total_flos": 2.2763010362425344e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033505512da25435e71045d85690dbf30497f6bc018b3d5c14f46680b0ff68b0
+size 3503