Training in progress, step 15469

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "roneneldan/TinyStories-33M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      2
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 4,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hidden_weight=10.0, hs_loss_fn=mse, learning_rate=4e-05/events.out.tfevents.1723755484.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15655ec94b85c48748f0671ba5872ac5cee64fdbad4536cbcd65ee771eddb1c
+size 6097

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hidden_weight=10.0, hs_loss_fn=raw_mse, learning_rate=4e-05/events.out.tfevents.1723755322.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096e42741475d4ff99b423664d0b90442fc8033c88a5381b39bbcd009efc43bf
+size 6101

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hs_loss_fn=mse, hs_weight=10.0, learning_rate=4e-05/events.out.tfevents.1723755774.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5011cd4d020decf82039c47df84d9aedf43b781ad60b6da4beed69c692e4c5dd
+size 6093

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hs_loss_fn=raw_mse, hs_weight=10.0, learning_rate=4e-05/events.out.tfevents.1723755667.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ba65a56891f93ad170a6355d89279d46333e5ddf9b41895c73ff6b8f1ba4ae
+size 6353

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hs_loss_fn=raw_mse, hs_weight=10.0, learning_rate=4e-05/events.out.tfevents.1723757364.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f8b054d1819376f2cd49dd04470d1e6e7dc04bd2373d0837c27844b4e49ee4
+size 6408

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hs_loss_fn=raw_mse, hs_weight=10.0, learning_rate=4e-05/events.out.tfevents.1723757811.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bfc59c466f59bd6c2fb3648512542c994215488b91c6ff083770adafeab55a
+size 4177665

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02ce05c35c068733e13716baf730143d5b4cf82b3f116c13fb1171d9c8626b0
+size 137033984

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "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|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "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 sha256:2f3bcdfc6299d53e04e9f7abfff93822cd19595d30f9e4b1dbe90bd6bb8b0519
+size 1017948104