Training in progress, step 12375

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=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=mse, hs_weight=2.0, learning_rate=0.0004, lr_scheduler_kwargs=__num_cycles___4_, lr_scheduler_type=cosine_with_restarts, max/events.out.tfevents.1723832096.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3638a62703bfed4644b7f2046743f09a6003fde66c69b4d108e080974f60abd0
+size 5185087

logs/attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=mse, hs_weight=2.0, learning_rate=0.0004, lr_scheduler_type=cosine_with_restarts, max_grad_norm=None, num_cycles=4, optim=pa/events.out.tfevents.1723830066.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af118807ba41db3dd611d56d1fe8b70b053ed4abfbaaf83274e239aa8c6c9f6
+size 4809226

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dfea5361764269b261b7bed75573bc5f866f868a496b5eeb6a9ef5d9600cd1a
+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 sha256:92aff456c150a4d9506132557c4348d28144722c442e735e1dc664c76cb9cc23
+size 1017948232