End of training

README.md

@@ -1,12 +1,11 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: JackFram/llama-68m
+base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
 tags:
 - axolotl
 - generated_from_trainer
 model-index:
-- name: 4ada8092-cc1e-445c-9260-a580ef2586ae
+- name: dab16ec4-4ddf-4ee5-8888-3dc2a83f0f86
   results: []
 ---
 
@@ -18,19 +17,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 axolotl version: `0.4.1`
 ```yaml
-base_model: JackFram/llama-68m
+base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
 batch_size: 32
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
 - data_files:
-  - ff3a521d02fa72b2_train_data.json
+  - f4a61305a746447c_train_data.json
   ds_type: json
   format: custom
-  path: /workspace/input_data/ff3a521d02fa72b2_train_data.json
+  path: /workspace/input_data/f4a61305a746447c_train_data.json
   type:
-    field_instruction: context
-    field_output: question
+    field_instruction: sentence1
+    field_output: sentence2
     format: '{instruction}'
     no_input_format: '{instruction}'
     system_format: '{system}'
@@ -40,7 +39,7 @@ flash_attention: true
 gpu_memory_limit: 80GiB
 gradient_checkpointing: true
 group_by_length: true
-hub_model_id: willtensora/4ada8092-cc1e-445c-9260-a580ef2586ae
+hub_model_id: willtensora/dab16ec4-4ddf-4ee5-8888-3dc2a83f0f86
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
@@ -56,15 +55,13 @@ sample_packing: false
 save_steps: 40
 save_total_limit: 1
 sequence_len: 2048
-special_tokens:
-  pad_token: </s>
 tokenizer_type: LlamaTokenizerFast
 train_on_inputs: false
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
 wandb_mode: online
-wandb_name: JackFram/llama-68m-/workspace/input_data/ff3a521d02fa72b2_train_data.json
+wandb_name: trl-internal-testing/tiny-random-LlamaForCausalLM-/workspace/input_data/f4a61305a746447c_train_data.json
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: default
@@ -75,11 +72,9 @@ xformers_attention: true
 
 </details><br>
 
-# 4ada8092-cc1e-445c-9260-a580ef2586ae
+# dab16ec4-4ddf-4ee5-8888-3dc2a83f0f86
 
-This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2208
+This model is a fine-tuned version of [trl-internal-testing/tiny-random-LlamaForCausalLM](https://huggingface.co/trl-internal-testing/tiny-random-LlamaForCausalLM) on the None dataset.
 
 ## Model description
 
@@ -108,24 +103,13 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 10
-- training_steps: 205
+- training_steps: 13
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.0006 | 1    | 6.7193          |
-| 1.5212        | 0.0122 | 20   | 1.0774          |
-| 0.7826        | 0.0244 | 40   | 0.6352          |
-| 0.5492        | 0.0366 | 60   | 0.4713          |
-| 0.3663        | 0.0488 | 80   | 0.3924          |
-| 0.3533        | 0.0610 | 100  | 0.3112          |
-| 0.2434        | 0.0732 | 120  | 0.2761          |
-| 0.2989        | 0.0854 | 140  | 0.2445          |
-| 0.2464        | 0.0976 | 160  | 0.2251          |
-| 0.2233        | 0.1098 | 180  | 0.2203          |
-| 0.2213        | 0.1220 | 200  | 0.2208          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.01  | 1    | 10.3686         |
 
 
 ### Framework versions

generation_config.json

@@ -2,7 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "do_sample": true,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
+  "eos_token_id": 1,
+  "pad_token_id": 2,
   "transformers_version": "4.46.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432d9ed4d450961d63ceeda6070006f3b7eae9f4bfd1ec6ba4cd115f7bdb6b5a
-size 136067757
+oid sha256:70872e8af35c48abf8dc8a0f41f28f7673e23a762cd5f5a4707b0788bf617ebf
+size 2071661