Upload folder using huggingface_hub

Browse files

Files changed (16) hide show

.gitattributes +3 -0
amd135m_bf16.gguf +3 -0
amd135m_fp16.gguf +3 -0
amd135m_q8.gguf +3 -0
config.json +31 -0
generation_config.json +8 -0
model.safetensors +3 -0
optimizer.pt +3 -0
rng_state.pth +3 -0
scheduler.pt +3 -0
special_tokens_map.json +24 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +42 -0
trainer_state.json +327 -0
training_args.bin +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+amd135m_bf16.gguf filter=lfs diff=lfs merge=lfs -text
+amd135m_fp16.gguf filter=lfs diff=lfs merge=lfs -text
+amd135m_q8.gguf filter=lfs diff=lfs merge=lfs -text

amd135m_bf16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d253fa3a820e4008472e19eb0cbdc3ae5c69d010a067efca750fd1d3f968a40a
+size 268980896

amd135m_fp16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b4f722a85580d76f4851dd42ef943466d188de71ef0c2a59fc500ea5786c66
+size 268980896

amd135m_q8.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0db09b0c65f1ec6bcf8a13b3b450e28125655171acb6a5b47e1611db9d7c205
+size 143274656

config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "_name_or_path": "amd/AMD-Llama-135m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "unsloth_version": "2024.9.post4",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8333515d755729417f5593c2e776d216570f10f24d3948b2ad4eb052199f2bb6
+size 268224136

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:82d7feffe8983a20cd78a492dc69106cb475b16433273760a597034b8b9be8e6
+size 438114938

rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb47fd93045e0132eea1d4b710b51bcf56b3a502519f3c15df6e295c4cc3a52
+size 1064

special_tokens_map.json ADDED Viewed

	@@ -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.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,42 @@

+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,327 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 21249,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023530519083250975,
+      "grad_norm": 1.6875,
+      "learning_rate": 4.882347404583745e-05,
+      "loss": 0.9427,
+      "step": 500
+    },
+    {
+      "epoch": 0.04706103816650195,
+      "grad_norm": 1.75,
+      "learning_rate": 4.76469480916749e-05,
+      "loss": 0.8108,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07059155724975293,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.647042213751235e-05,
+      "loss": 0.7777,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0941220763330039,
+      "grad_norm": 1.6171875,
+      "learning_rate": 4.52938961833498e-05,
+      "loss": 0.7551,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11765259541625488,
+      "grad_norm": 1.4765625,
+      "learning_rate": 4.411737022918726e-05,
+      "loss": 0.7373,
+      "step": 2500
+    },
+    {
+      "epoch": 0.14118311449950585,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.294084427502471e-05,
+      "loss": 0.727,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16471363358275684,
+      "grad_norm": 1.84375,
+      "learning_rate": 4.1764318320862164e-05,
+      "loss": 0.718,
+      "step": 3500
+    },
+    {
+      "epoch": 0.1882441526660078,
+      "grad_norm": 1.7265625,
+      "learning_rate": 4.0587792366699614e-05,
+      "loss": 0.7153,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2117746717492588,
+      "grad_norm": 1.5625,
+      "learning_rate": 3.9411266412537063e-05,
+      "loss": 0.7067,
+      "step": 4500
+    },
+    {
+      "epoch": 0.23530519083250975,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.823474045837451e-05,
+      "loss": 0.7037,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2588357099157607,
+      "grad_norm": 1.8203125,
+      "learning_rate": 3.705821450421196e-05,
+      "loss": 0.6984,
+      "step": 5500
+    },
+    {
+      "epoch": 0.2823662289990117,
+      "grad_norm": 1.609375,
+      "learning_rate": 3.588168855004941e-05,
+      "loss": 0.6954,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3058967480822627,
+      "grad_norm": 1.5859375,
+      "learning_rate": 3.470516259588686e-05,
+      "loss": 0.6948,
+      "step": 6500
+    },
+    {
+      "epoch": 0.3294272671655137,
+      "grad_norm": 1.515625,
+      "learning_rate": 3.352863664172432e-05,
+      "loss": 0.6908,
+      "step": 7000
+    },
+    {
+      "epoch": 0.35295778624876467,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.235211068756177e-05,
+      "loss": 0.6873,
+      "step": 7500
+    },
+    {
+      "epoch": 0.3764883053320156,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.117558473339922e-05,
+      "loss": 0.6876,
+      "step": 8000
+    },
+    {
+      "epoch": 0.4000188244152666,
+      "grad_norm": 1.5703125,
+      "learning_rate": 2.999905877923667e-05,
+      "loss": 0.6879,
+      "step": 8500
+    },
+    {
+      "epoch": 0.4235493434985176,
+      "grad_norm": 1.5859375,
+      "learning_rate": 2.882253282507412e-05,
+      "loss": 0.6862,
+      "step": 9000
+    },
+    {
+      "epoch": 0.4470798625817686,
+      "grad_norm": 1.8359375,
+      "learning_rate": 2.7646006870911574e-05,
+      "loss": 0.6829,
+      "step": 9500
+    },
+    {
+      "epoch": 0.4706103816650195,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.6469480916749024e-05,
+      "loss": 0.6852,
+      "step": 10000
+    },
+    {
+      "epoch": 0.4941409007482705,
+      "grad_norm": 1.5,
+      "learning_rate": 2.5292954962586474e-05,
+      "loss": 0.681,
+      "step": 10500
+    },
+    {
+      "epoch": 0.5176714198315214,
+      "grad_norm": 1.59375,
+      "learning_rate": 2.4116429008423927e-05,
+      "loss": 0.6798,
+      "step": 11000
+    },
+    {
+      "epoch": 0.5412019389147724,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.2939903054261376e-05,
+      "loss": 0.6803,
+      "step": 11500
+    },
+    {
+      "epoch": 0.5647324579980234,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.176337710009883e-05,
+      "loss": 0.6799,
+      "step": 12000
+    },
+    {
+      "epoch": 0.5882629770812744,
+      "grad_norm": 1.875,
+      "learning_rate": 2.0586851145936283e-05,
+      "loss": 0.6761,
+      "step": 12500
+    },
+    {
+      "epoch": 0.6117934961645254,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.9410325191773732e-05,
+      "loss": 0.675,
+      "step": 13000
+    },
+    {
+      "epoch": 0.6353240152477764,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8233799237611182e-05,
+      "loss": 0.6785,
+      "step": 13500
+    },
+    {
+      "epoch": 0.6588545343310274,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.7057273283448632e-05,
+      "loss": 0.6782,
+      "step": 14000
+    },
+    {
+      "epoch": 0.6823850534142784,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.5880747329286085e-05,
+      "loss": 0.6761,
+      "step": 14500
+    },
+    {
+      "epoch": 0.7059155724975293,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.4704221375123536e-05,
+      "loss": 0.6795,
+      "step": 15000
+    },
+    {
+      "epoch": 0.7294460915807802,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.3527695420960988e-05,
+      "loss": 0.6774,
+      "step": 15500
+    },
+    {
+      "epoch": 0.7529766106640312,
+      "grad_norm": 1.5546875,
+      "learning_rate": 1.2351169466798439e-05,
+      "loss": 0.6777,
+      "step": 16000
+    },
+    {
+      "epoch": 0.7765071297472822,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.1174643512635889e-05,
+      "loss": 0.6746,
+      "step": 16500
+    },
+    {
+      "epoch": 0.8000376488305332,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.998117558473342e-06,
+      "loss": 0.6782,
+      "step": 17000
+    },
+    {
+      "epoch": 0.8235681679137842,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.821591604310792e-06,
+      "loss": 0.6776,
+      "step": 17500
+    },
+    {
+      "epoch": 0.8470986869970352,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.645065650148241e-06,
+      "loss": 0.6782,
+      "step": 18000
+    },
+    {
+      "epoch": 0.8706292060802862,
+      "grad_norm": 1.609375,
+      "learning_rate": 6.468539695985694e-06,
+      "loss": 0.6754,
+      "step": 18500
+    },
+    {
+      "epoch": 0.8941597251635371,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.292013741823145e-06,
+      "loss": 0.6757,
+      "step": 19000
+    },
+    {
+      "epoch": 0.9176902442467881,
+      "grad_norm": 1.6015625,
+      "learning_rate": 4.1154877876605964e-06,
+      "loss": 0.6765,
+      "step": 19500
+    },
+    {
+      "epoch": 0.941220763330039,
+      "grad_norm": 1.5625,
+      "learning_rate": 2.938961833498047e-06,
+      "loss": 0.6747,
+      "step": 20000
+    },
+    {
+      "epoch": 0.96475128241329,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.7624358793354984e-06,
+      "loss": 0.677,
+      "step": 20500
+    },
+    {
+      "epoch": 0.988281801496541,
+      "grad_norm": 1.65625,
+      "learning_rate": 5.859099251729494e-07,
+      "loss": 0.6804,
+      "step": 21000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 21249,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.787078596423629e+17,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2916aefa37ef47e27ff2c952d0fffee6d84589454b757c68252e87aafeb3cc
+size 5432