Add files using upload-large-folder tool

attention_2_only_emb/final_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65238b445c26f43da67f2f54cecb176acdc8f4316c36230e1baccf453169754b
+size 2533545094

attention_2_only_emb/model_1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48e11d99e74e3ac615d5f6bd78b0f524e0ad1951fca5b223c9aec52ebb23596
+size 2533545094

attention_2_only_emb/model_10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e190ea29dd8119871d88bc6c120b49a4c3b6e9e979286dac7b464f9c42fb5454
+size 2533545094

attention_2_only_emb/model_11000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8a06de57e06be1e59112b19c52985b6e1e1905645464df7d675c61f8a62a67
+size 2533545094

attention_2_only_emb/model_13000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33dfd88af702c854bab079669a8dde4157c14ab4dbbea412e8382b1157fed607
+size 2533545094

attention_2_only_emb/model_14000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288665e9230d153d7a863e7a8e66cc3c48d5133ba629a788f8c8302f62bcf508
+size 2533545094

attention_2_only_emb/model_15000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65238b445c26f43da67f2f54cecb176acdc8f4316c36230e1baccf453169754b
+size 2533545094

attention_2_only_emb/model_4000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f831b13a1e989d024050ac81156cca927d96d40afd492847292ea167b8f97d8e
+size 2533545094

attention_2_only_emb/model_5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72b2ed53bbf3dbc3fc4711abcd9d661d0064760380d4c3f2ce7c6b59db76dbf
+size 2533545094

attention_2_only_emb/model_9000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4851e88488581a963da7b13d25b32cf82e0512d7a393bfbf957b3671ff379c7a
+size 2533545094

baseline/model_1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00edd9bd916b1d6059044c1e496b6c21775ba6e8cfc08fb54ea38a112cefeb4e
+size 2533545094

baseline/model_11000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2caffc4e634a9b5cc17988d11913c72e3a6eeede9a45f38257db62bff5f661
+size 2533545094

baseline/model_12000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e719eae49624f71ba9389bd9764c1cb5d07c0acf33a1220eb4f8dda73240b9b
+size 2533545094

baseline/model_13000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672bb2ac05b1618a7d748e23fa392f5197065cef854f22b6dce109b472470517
+size 2533545094

baseline/model_14000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4739b4a78103197ee542a1010ba48e38824f60f5ec00ce70a9ae33ca5f2e4343
+size 2533545094

baseline/model_2000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc43549f54dd1e2edc06ec8ea811fc48c5b51a83830ec22027266878f3657b91
+size 2533545094

baseline/model_3000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83671facca5fb99530b5c52bbd111dda3383639f4ef50f90bd7379aa1b37fae2
+size 2533545094

baseline/model_4000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb2010e8f368ae6fe61f89a9d71b8ee6a821a59727301688097911f2337d544
+size 2533545094

baseline/model_5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d88bc7652172e2291ad1e16d2326344a1f9651dec698d2f14ff2b8a909f82dc
+size 2533545094

baseline/model_6000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8417cded07b68977443fb14688e0a5d1fdfe3727a5a58da05dd5df10423795
+size 2533545094

baseline/model_7000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedb26968104d1fe2d880f5b4e0ebb006fbea3dde5ca3603f7606c07e0a4bed8
+size 2533545094

baseline/model_8000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d8381c12bd8d5c961d08860dfeac2a8cfbea2af8400b6d62bd2623c90258f5
+size 2533545094

baseline/model_9000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62dca90201b94b66ead46c71e3b2036bbe678cd38ab831997b6ce49b858773f
+size 2533545094

bigram_2/final_model/config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_1000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_1000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 1000,
+    "update_step": 1000,
+    "tokens_seen": 639025152,
+    "tokens_seen_before": 638386176,
+    "update_time": 2.892822504043579,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_10000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_10000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 10000,
+    "update_step": 10000,
+    "tokens_seen": 6389809152,
+    "tokens_seen_before": 6389170176,
+    "update_time": 2.8910531997680664,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_11000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_11000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 11000,
+    "update_step": 11000,
+    "tokens_seen": 7028785152,
+    "tokens_seen_before": 7028146176,
+    "update_time": 2.88981556892395,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_12000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_12000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 12000,
+    "update_step": 12000,
+    "tokens_seen": 7667761152,
+    "tokens_seen_before": 7667122176,
+    "update_time": 2.8912298679351807,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_14000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_14000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 14000,
+    "update_step": 14000,
+    "tokens_seen": 8945713152,
+    "tokens_seen_before": 8945074176,
+    "update_time": 2.8920021057128906,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_15000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_15000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 15000,
+    "update_step": 15000,
+    "tokens_seen": 9584689152,
+    "tokens_seen_before": 9584050176,
+    "update_time": 2.89182710647583,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_4000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_5000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_5000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 5000,
+    "update_step": 5000,
+    "tokens_seen": 3194929152,
+    "tokens_seen_before": 3194290176,
+    "update_time": 2.8917791843414307,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_6000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_6000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 6000,
+    "update_step": 6000,
+    "tokens_seen": 3833905152,
+    "tokens_seen_before": 3833266176,
+    "update_time": 2.892122983932495,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_7000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_7000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 7000,
+    "update_step": 7000,
+    "tokens_seen": 4472881152,
+    "tokens_seen_before": 4472242176,
+    "update_time": 2.8900256156921387,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_8000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_8000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 8000,
+    "update_step": 8000,
+    "tokens_seen": 5111857152,
+    "tokens_seen_before": 5111218176,
+    "update_time": 2.8911120891571045,
+    "wandb_id": "walilhuz"
+}

bigram_2/model_9000/model_config.json

@@ -0,0 +1,19 @@
+{
+    "architectures": [
+        "LLaMAForCausalLM"
+    ],
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 5376,
+    "initializer_range": 0.02,
+    "max_sequence_length": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 14,
+    "rms_norm_eps": 1e-05,
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 50257
+}

bigram_2/model_9000/training_state.json

@@ -0,0 +1,8 @@
+{
+    "global_step": 9000,
+    "update_step": 9000,
+    "tokens_seen": 5750833152,
+    "tokens_seen_before": 5750194176,
+    "update_time": 2.890213966369629,
+    "wandb_id": "walilhuz"
+}

bigram_2_full/final_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477b0b02d1fa370dd03a88359bf7784e17681740c07a6952b75b5bab9f5e333f
+size 2533545094

bigram_2_full/model_1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f696208f3842be6f4c26371224bc32cb8cb8f5a268c879be0dd18afef088b4f
+size 2533545094

bigram_2_full/model_10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808a7200d616e0ad374917803a0a3e5e53c4751e33bdf1761e5d421e603581cd
+size 2533545094