Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+base_model: facebook/opt-125m
+tags:
+- generated_from_trainer
+model-index:
+- name: opt-125m-sft-full
+  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. -->
+
+# opt-125m-sft-full
+
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7902
+
+## 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: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8664        | 0.62  | 4034 | 1.7902          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.62,
+    "eval_loss": 1.790170431137085,
+    "eval_runtime": 623.7378,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 37.051,
+    "eval_steps_per_second": 9.264,
+    "train_loss": 1.8920561942240952,
+    "train_runtime": 23913.723,
+    "train_samples": 207865,
+    "train_samples_per_second": 8.692,
+    "train_steps_per_second": 0.272
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": false,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.62,
+    "eval_loss": 1.790170431137085,
+    "eval_runtime": 623.7378,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 37.051,
+    "eval_steps_per_second": 9.264
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905a4e393a8eb378b0cc7c1621e7a9c468942428f7e819d3bcad8132b20904aa
+size 250501160

runs/Dec05_10-49-04_sebastian-dell/events.out.tfevents.1701769752.sebastian-dell.1140222.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0815f20d2598fe649fba5ab18dbb45ee66d34dc7c314c76fd0fd22c5b058ea55
+size 4364

runs/Dec05_10-49-57_sebastian-dell/events.out.tfevents.1701769806.sebastian-dell.1140510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f3040068d2169d74a492da8a8a40c40c73d7f598f530cd76aab5b9486c7404
+size 4364

runs/Dec05_10-51-07_sebastian-dell/events.out.tfevents.1701769876.sebastian-dell.1140907.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fb5fe6b4f52b569860eeae31a8993fa217e5d8efed42ac63cb599740ae1d05
+size 131608

runs/Dec05_10-51-07_sebastian-dell/events.out.tfevents.1701794414.sebastian-dell.1140907.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd2e2111295a9c875790c9c15a80ffa8a83b2a4b40588086b866bd00c136ac5
+size 359

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": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "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
+    }
+  },
+  "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": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.62,
+    "train_loss": 1.8920561942240952,
+    "train_runtime": 23913.723,
+    "train_samples": 207865,
+    "train_samples_per_second": 8.692,
+    "train_steps_per_second": 0.272
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e218450efaddc513d3a057395dbd67bda5e88cc36b2142d7ed7a453817f41c99
+size 5624