Training in progress, epoch 1

config.json

@@ -1,39 +1,89 @@
 {
-  "_name_or_path": "gpt2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "apple/OpenELM-270M",
+  "activation_fn_name": "swish",
   "architectures": [
-    "GPT2LMHeadModel"
+    "OpenELMForCausalLM"
   ],
-  "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
-    }
+  "auto_map": {
+    "AutoConfig": "apple/OpenELM-270M--configuration_openelm.OpenELMConfig",
+    "AutoModelForCausalLM": "apple/OpenELM-270M--modeling_openelm.OpenELMForCausalLM"
   },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "ffn_dim_divisor": 256,
+  "ffn_multipliers": [
+    0.5,
+    0.73,
+    0.97,
+    1.2,
+    1.43,
+    1.67,
+    1.9,
+    2.13,
+    2.37,
+    2.6,
+    2.83,
+    3.07,
+    3.3,
+    3.53,
+    3.77,
+    4.0
+  ],
+  "ffn_with_glu": true,
+  "head_dim": 64,
+  "initializer_range": 0.02,
+  "max_context_length": 2048,
+  "model_dim": 1280,
+  "model_type": "openelm",
+  "normalization_layer_name": "rms_norm",
+  "normalize_qk_projections": true,
+  "num_gqa_groups": 4,
+  "num_kv_heads": [
+    3,
+    3,
+    3,
+    3,
+    3,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    5,
+    5,
+    5,
+    5
+  ],
+  "num_query_heads": [
+    12,
+    12,
+    12,
+    12,
+    12,
+    16,
+    16,
+    16,
+    16,
+    16,
+    16,
+    16,
+    20,
+    20,
+    20,
+    20
+  ],
+  "num_transformer_layers": 16,
+  "qkv_multipliers": [
+    0.5,
+    1.0
+  ],
+  "rope_freq_constant": 10000,
+  "rope_max_length": 4096,
+  "share_input_output_layers": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95f698bd01169b2a3ba9c483071bf9a5d736e01bf4a978517d2897b0b69c414
-size 497774208
+oid sha256:26e07f26db2f1f03bfb38881414958f4779d7fb2a62abea351fccd305ddabe27
+size 1086123184

special_tokens_map.json

@@ -1,23 +1,22 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,22 +1,41 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe293430f9b656c258bb2c3c373d6cf3cc14fc49fd79a71a29f31f22e8d0df4
+oid sha256:befe953eb5770a648fa8743e7d9662183afb2f3b45482688dab5f88fc604c572
 size 4920