End of training

Browse files

Files changed (9) hide show

README.md +98 -0
config.json +29 -0
generation_config.json +7 -0
model.safetensors +3 -0
special_tokens_map.json +24 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +41 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,98 @@

+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+tags:
+- xcomet_xl_xxl
+- generated_from_trainer
+model-index:
+- name: cpo-xcomet-xl_xxl-inc7b-10p-shuff-1e-7-full-tiny
+  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. -->
+# cpo-xcomet-xl_xxl-inc7b-10p-shuff-1e-7-full-tiny
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the Unbabel/TowerAligned-v0.1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7960
+- Nll Loss: 1.0602
+- Logps/best: -102.8461
+- Rewards/chosen: -10.2846
+- Rewards/rejected: -9.6988
+- Rewards/accuracies: 0.4600
+- Rewards/margins: -0.5858
+- Logps/rejected: -96.9882
+- Logps/chosen: -102.8461
+- Logits/rejected: -1.8264
+- Logits/chosen: -1.9635
+## 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: 1e-07
+- train_batch_size: 1
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+### Training results
+| Training Loss | Epoch  | Step | Validation Loss | Nll Loss | Logps/best | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:----------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 2.9687        | 0.1063 | 100  | 2.8066          | 1.0659   | -103.3585  | -10.3358       | -9.7431          | 0.4540             | -0.5928         | -97.4308       | -103.3585    | -1.8274         | -1.9646       |
+| 3.0173        | 0.2127 | 200  | 2.8063          | 1.0656   | -103.3396  | -10.3340       | -9.7402          | 0.4560             | -0.5937         | -97.4022       | -103.3396    | -1.8275         | -1.9648       |
+| 2.8267        | 0.3190 | 300  | 2.8046          | 1.0650   | -103.2849  | -10.3285       | -9.7373          | 0.4540             | -0.5912         | -97.3725       | -103.2849    | -1.8273         | -1.9644       |
+| 2.9404        | 0.4254 | 400  | 2.8046          | 1.0644   | -103.2318  | -10.3232       | -9.7301          | 0.4600             | -0.5931         | -97.3013       | -103.2318    | -1.8271         | -1.9643       |
+| 3.3065        | 0.5317 | 500  | 2.8002          | 1.0637   | -103.1556  | -10.3156       | -9.7280          | 0.4600             | -0.5875         | -97.2803       | -103.1556    | -1.8268         | -1.9640       |
+| 2.9333        | 0.6381 | 600  | 2.8021          | 1.0633   | -103.1282  | -10.3128       | -9.7212          | 0.4560             | -0.5916         | -97.2122       | -103.1282    | -1.8271         | -1.9642       |
+| 3.2698        | 0.7444 | 700  | 2.8006          | 1.0627   | -103.0742  | -10.3074       | -9.7178          | 0.4580             | -0.5897         | -97.1777       | -103.0742    | -1.8268         | -1.9640       |
+| 2.7002        | 0.8508 | 800  | 2.8003          | 1.0624   | -103.0458  | -10.3046       | -9.7147          | 0.4580             | -0.5899         | -97.1470       | -103.0458    | -1.8269         | -1.9641       |
+| 3.0848        | 0.9571 | 900  | 2.7984          | 1.0620   | -103.0023  | -10.3002       | -9.7132          | 0.4580             | -0.5870         | -97.1324       | -103.0023    | -1.8267         | -1.9638       |
+| 2.9243        | 1.0635 | 1000 | 2.7987          | 1.0617   | -102.9805  | -10.2980       | -9.7086          | 0.4580             | -0.5895         | -97.0859       | -102.9805    | -1.8268         | -1.9639       |
+| 2.7945        | 1.1698 | 1100 | 2.7974          | 1.0615   | -102.9564  | -10.2956       | -9.7084          | 0.4580             | -0.5872         | -97.0842       | -102.9564    | -1.8267         | -1.9638       |
+| 2.7893        | 1.2762 | 1200 | 2.7979          | 1.0613   | -102.9413  | -10.2941       | -9.7061          | 0.4620             | -0.5880         | -97.0609       | -102.9413    | -1.8266         | -1.9638       |
+| 3.2162        | 1.3825 | 1300 | 2.7978          | 1.0611   | -102.9208  | -10.2921       | -9.7039          | 0.4540             | -0.5882         | -97.0387       | -102.9208    | -1.8266         | -1.9637       |
+| 2.8123        | 1.4889 | 1400 | 2.7980          | 1.0611   | -102.9247  | -10.2925       | -9.7032          | 0.4580             | -0.5893         | -97.0320       | -102.9247    | -1.8266         | -1.9637       |
+| 2.785         | 1.5952 | 1500 | 2.7973          | 1.0606   | -102.8798  | -10.2880       | -9.6993          | 0.4560             | -0.5887         | -96.9928       | -102.8798    | -1.8265         | -1.9636       |
+| 2.7997        | 1.7016 | 1600 | 2.7952          | 1.0606   | -102.8751  | -10.2875       | -9.7026          | 0.4600             | -0.5849         | -97.0257       | -102.8751    | -1.8267         | -1.9638       |
+| 2.6655        | 1.8079 | 1700 | 2.7956          | 1.0605   | -102.8628  | -10.2863       | -9.7005          | 0.4620             | -0.5858         | -97.0050       | -102.8628    | -1.8264         | -1.9635       |
+| 2.7597        | 1.9143 | 1800 | 2.7966          | 1.0605   | -102.8715  | -10.2871       | -9.6999          | 0.4540             | -0.5872         | -96.9991       | -102.8715    | -1.8267         | -1.9637       |
+| 2.9736        | 2.0206 | 1900 | 2.7955          | 1.0603   | -102.8511  | -10.2851       | -9.6990          | 0.4600             | -0.5861         | -96.9900       | -102.8511    | -1.8266         | -1.9637       |
+| 2.8977        | 2.1270 | 2000 | 2.7954          | 1.0603   | -102.8550  | -10.2855       | -9.6990          | 0.4560             | -0.5865         | -96.9901       | -102.8550    | -1.8270         | -1.9641       |
+| 2.7043        | 2.2333 | 2100 | 2.7961          | 1.0604   | -102.8632  | -10.2863       | -9.6997          | 0.4560             | -0.5867         | -96.9967       | -102.8632    | -1.8264         | -1.9635       |
+| 2.7693        | 2.3396 | 2200 | 2.7951          | 1.0604   | -102.8550  | -10.2855       | -9.6998          | 0.4600             | -0.5857         | -96.9983       | -102.8550    | -1.8263         | -1.9634       |
+| 2.6632        | 2.4460 | 2300 | 2.7943          | 1.0602   | -102.8407  | -10.2841       | -9.6989          | 0.4600             | -0.5851         | -96.9893       | -102.8407    | -1.8264         | -1.9635       |
+| 3.2451        | 2.5523 | 2400 | 2.7953          | 1.0602   | -102.8434  | -10.2843       | -9.6989          | 0.4580             | -0.5855         | -96.9885       | -102.8434    | -1.8264         | -1.9635       |
+| 2.7117        | 2.6587 | 2500 | 2.7955          | 1.0601   | -102.8357  | -10.2836       | -9.6962          | 0.4580             | -0.5873         | -96.9625       | -102.8357    | -1.8263         | -1.9634       |
+| 3.148         | 2.7650 | 2600 | 2.7967          | 1.0604   | -102.8636  | -10.2864       | -9.6985          | 0.4560             | -0.5878         | -96.9853       | -102.8636    | -1.8265         | -1.9636       |
+| 3.2951        | 2.8714 | 2700 | 2.7959          | 1.0602   | -102.8490  | -10.2849       | -9.6981          | 0.4620             | -0.5868         | -96.9812       | -102.8490    | -1.8263         | -1.9634       |
+| 2.8486        | 2.9777 | 2800 | 2.7960          | 1.0602   | -102.8461  | -10.2846       | -9.6988          | 0.4600             | -0.5858         | -96.9882       | -102.8461    | -1.8264         | -1.9635       |
+### Framework versions
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:aaba0e8afe6ec337e6de464697267d74a6d5447faafce8d6f98e4835b3bdd8dd
+size 2200119864

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": "[PAD]",
+  "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 +1,41 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbd442b451f333522d2ec4c6768e395dec10eb58001851057f66a124a0f3c7d
+size 5240