Upload ./ with huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "MBZUAI/LaMini-GPT-124M",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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 sha256:3a2362ea35975aa14b4dd84c6f5e08f1fa1bd33e44e30251cd32b4496749afab
+size 995610161

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0711f0bef1c10c1760751e910ed1ff6e801ffa3e24e5bf3733284e9293d4962
+size 510399593

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8466860d68ad793bb37892cc5bf42d89d1e09b2ea3f250bd3bb773d71f72d565
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479ccc61e4b3d8a6309c203f641dd666dcd2d4723fd0a225fd69388f6bf4cc8b
+size 623

trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.034327518289252,
+  "global_step": 12500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.190315315315316e-05,
+      "loss": 1.0104,
+      "step": 5000
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 4.375e-05,
+      "loss": 0.7628,
+      "step": 10000
+    }
+  ],
+  "max_steps": 17770,
+  "num_train_epochs": 10,
+  "total_flos": 3.9182830534656e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd714242149e0b2d426a71fc0772dd4224c8c6381ede384af584714177ad0f18
+size 3247