Training in progress, step 624

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert/distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 50257
+}

logs/per_device_train_batch_size=8, run_name=refactor_distillation_objective/events.out.tfevents.1726111010.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992b26e63fa2e605bd8a077c6847a4c62e66625d7394577ff43e014290f1dc86
+size 5398

logs/per_device_train_batch_size=8, run_name=refactor_distillation_objective/events.out.tfevents.1726111180.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0010ab7ce2391d1582daaba8c87b8e51c12b9139c82f1ae415a5f5f111f9cfbf
+size 5398

logs/per_device_train_batch_size=8, run_name=refactor_distillation_objective/events.out.tfevents.1726111329.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee3b2417cd20d561ea39886d5709facdac69c6860a2d2b8da19aaf254419496
+size 25189

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726104209.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06317a189982405fa0a1eaf747b003f4544de17fcdb5480c516cd918e08de4f
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726104498.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83c07cebcdce0d121480fdbbb24f7a335f15866fd595b6d2fe2b56218976a49
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726104681.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d0926fded51f2cfa0e3824ea20b6ece6061226a4cbc956cbeaaa5794b659f5
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726104788.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855fffb6b4cedae1a1a2ee394adaf00ffd1e45621fd75b4bee2501f12d90b258
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726109394.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebddfb37426b43ddaf0469ff3069dade776b6f51cec77c8d9df823e47979e8d
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726110518.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf916a5905a5abe6c1fe56217349fdc6fa6e12be79d87bcfc8176210ce4f733
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726110686.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eccdce6d4f1ab8aaf2b471630f1f8853d8c28a5424a07511c9af464a1dc0670
+size 5368

logs/run_name=refactor_distillation_objective/events.out.tfevents.1726110933.46d00238c241

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29aaae44ac4844995797ee5b7cc8eb136387346209fa96cc93fbf24862ba6837
+size 5368

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b53c006b38cb605502d4a401f45e0a8ed86dcea158b60948b10ac6cafcbe98e
+size 163832792

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cb1355f17871943919748210e754670ed53b6cdeb1c48cc613e5ee0d4eb8f5
+size 5368