Training in progress, epoch 0

config.json

@@ -0,0 +1,125 @@
+{
+  "_name_or_path": "../../data/OpenELM-1_1B-SFT-1",
+  "activation_fn_name": "swish",
+  "architectures": [
+    "OpenELMForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_openelm.OpenELMConfig",
+    "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "ffn_dim_divisor": 256,
+  "ffn_multipliers": [
+    0.5,
+    0.63,
+    0.76,
+    0.89,
+    1.02,
+    1.15,
+    1.28,
+    1.41,
+    1.54,
+    1.67,
+    1.8,
+    1.93,
+    2.06,
+    2.19,
+    2.31,
+    2.44,
+    2.57,
+    2.7,
+    2.83,
+    2.96,
+    3.09,
+    3.22,
+    3.35,
+    3.48,
+    3.61,
+    3.74,
+    3.87,
+    4.0
+  ],
+  "ffn_with_glu": true,
+  "head_dim": 64,
+  "initializer_range": 0.02,
+  "max_context_length": 2048,
+  "model_dim": 2048,
+  "model_type": "openelm",
+  "normalization_layer_name": "rms_norm",
+  "normalize_qk_projections": true,
+  "num_gqa_groups": 4,
+  "num_kv_heads": [
+    4,
+    4,
+    4,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    6,
+    6,
+    6,
+    6,
+    6,
+    6,
+    6,
+    6,
+    7,
+    7,
+    7,
+    7,
+    7,
+    7,
+    8,
+    8,
+    8,
+    8
+  ],
+  "num_query_heads": [
+    16,
+    16,
+    16,
+    20,
+    20,
+    20,
+    20,
+    20,
+    20,
+    20,
+    24,
+    24,
+    24,
+    24,
+    24,
+    24,
+    24,
+    24,
+    28,
+    28,
+    28,
+    28,
+    28,
+    28,
+    32,
+    32,
+    32,
+    32
+  ],
+  "num_transformer_layers": 28,
+  "qkv_multipliers": [
+    0.5,
+    1.0
+  ],
+  "rope_freq_constant": 10000,
+  "rope_max_length": 4096,
+  "share_input_output_layers": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be836baaacb9a5f813e608e4d849bfc4d075fb174961a37aa6bf4b43f54f8bb
+size 2159808696

runs/Sep17_08-26-30_xe8545-a100-29/events.out.tfevents.1726554472.xe8545-a100-29.8992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81857e5b2918bcc7b4a66d69e91a5f7fb0bf476c28c85dbcd509dbe88f22bc2
+size 6667

runs/Sep20_09-49-50_xe8545-a100-29/events.out.tfevents.1726818850.xe8545-a100-29.128656.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79192f976a2c3a200e3bde43402d108b5715df50a04f41f8c03d7a9dc4a108c
+size 85502

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "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

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "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": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf8efbd579435b40acda2065d64af78048348b10b59a95db4ff52b8b87aef58
+size 7096