Training in progress, epoch 0

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "end_token_id": 50256,
+  "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,
+  "pad_token_id": 50256,
+  "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": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8187fff8988b69590e7f8cc68e68a998b0d2e99f7caa6b4308316c27116d0869
+size 326120926

runs/Dec31_01-44-55_a100-2gpus-spot-cuda12-150gb-1/events.out.tfevents.1703987118.a100-2gpus-spot-cuda12-150gb-1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94766b53c477953b09bbf1c43d98e66c6dc990e8f7055739a47b5d47534974d
+size 5768

runs/Dec31_01-44-55_a100-2gpus-spot-cuda12-150gb-1/events.out.tfevents.1703987451.a100-2gpus-spot-cuda12-150gb-1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42367bf011f91c0bcd8c94fe47eb86c30114b9f9d81bf9191495a2a1af77f264
+size 3792

runs/Dec31_01-53-22_a100-2gpus-spot-cuda12-150gb-1/events.out.tfevents.1703987626.a100-2gpus-spot-cuda12-150gb-1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5073633497c32834aa7bed2fb85895ae4b9d53883f0feb927f5c01c8c44acd52
+size 5768

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450af106047ebef75cf657012af2d3e707abf262d73a3d20d30be505549bbc8f
+size 6200