llama-7b model finetuned using TIM (fixemb) for trial

README.md

@@ -1,3 +1,57 @@
 ---
-license: unlicense
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: wmt_llama2-7b_sft_reward_mtst3_fixemb
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wmt_llama2-7b_sft_reward_mtst3_fixemb
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) using TIM method.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 5000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0a0+gitf8b6084
+- Datasets 2.14.7
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.98,
+    "max_memory_allocated (GB)": 82.87,
+    "memory_allocated (GB)": 23.35,
+    "total_memory_available (GB)": 94.57,
+    "train_loss": 0.19149471794962883,
+    "train_runtime": 16857.8956,
+    "train_samples": 5000,
+    "train_samples_per_second": 37.964,
+    "train_steps_per_second": 0.297
+}

gaudi_config.json

@@ -0,0 +1,10 @@
+{
+  "autocast_bf16_ops": null,
+  "autocast_fp32_ops": null,
+  "optimum_version": "1.16.2",
+  "transformers_version": "4.34.1",
+  "use_dynamic_shapes": false,
+  "use_fused_adam": true,
+  "use_fused_clip_norm": true,
+  "use_torch_autocast": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7f25f450a36cb3bb87656fe6e76bf98c7a70220a53c9a540d319446e8f2134
+size 13476955250

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.98,
+    "max_memory_allocated (GB)": 82.87,
+    "memory_allocated (GB)": 23.35,
+    "total_memory_available (GB)": 94.57,
+    "train_loss": 0.19149471794962883,
+    "train_runtime": 16857.8956,
+    "train_samples": 5000,
+    "train_samples_per_second": 37.964,
+    "train_steps_per_second": 0.297
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8313ed8a2c768a95e2e222dbe794af1bc9a58be91319e2817a135037638fbd75
+size 7096