Upload ./ with huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "MBZUAI/LaMini-GPT-774M",
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "4.20.1",
+  "use_cache": false,
+  "vocab_size": 50258
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885c2094f4b09c85accee562c99f3d3a61cae9b070e2e59c2a769fdcce9ed030
+size 6192513077

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c2ab09aadf7c38cf33bf03798b6fc11bc5a56d3d109742090b713878f15f79
+size 3134036617

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169b4ab88f7671b7f367bcb7651bdcd9065127a6128a0d175979ac545364a631
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2b6e9c1347e28d86675cb1800fb1df7ef5bb26a25547ec553145e502ff902f
+size 623

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.658536585365854,
+  "global_step": 19500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.063614186526554e-05,
+      "loss": 0.9314,
+      "step": 5000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 8.125351848376806e-05,
+      "loss": 0.6435,
+      "step": 10000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.18708951022706e-05,
+      "loss": 0.5023,
+      "step": 15000
+    }
+  ],
+  "max_steps": 53300,
+  "num_train_epochs": 10,
+  "total_flos": 1.697286170345472e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33d5e3e527355b12ec1190e535877d4b2c247c2d3485ed61d0247851d1c1c9e
+size 3247