Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-sft-full-8
+  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. -->
+
+# zephyr-7b-sft-full-8
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2612
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3456        | 0.0813 | 10   | 1.2612          |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.1.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.08130081300813008,
+    "total_flos": 1.3980126869979136e+16,
+    "train_loss": 1.5060624361038208,
+    "train_runtime": 361.6153,
+    "train_samples": 61134,
+    "train_samples_per_second": 3.54,
+    "train_steps_per_second": 0.028
+}

runs/Aug06_19-14-32_ip-172-31-4-23/events.out.tfevents.1722971685.ip-172-31-4-23.3956788.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb9a38ddea46047002231551c008c75573f7788e051fcaafc88e341ac9bca47
-size 6255
+oid sha256:89d60a27976b0b1eebc94a8673014ef49000552adbb9d4ef7641f1baffddd80c
+size 6869

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.08130081300813008,
+    "total_flos": 1.3980126869979136e+16,
+    "train_loss": 1.5060624361038208,
+    "train_runtime": 361.6153,
+    "train_samples": 61134,
+    "train_samples_per_second": 3.54,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08130081300813008,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008130081300813009,
+      "grad_norm": 13.1743803024292,
+      "learning_rate": 2e-05,
+      "loss": 1.3419,
+      "step": 1
+    },
+    {
+      "epoch": 0.04065040650406504,
+      "grad_norm": 23.33847999572754,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 1.7476,
+      "step": 5
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 6.350980281829834,
+      "learning_rate": 0.0,
+      "loss": 1.3456,
+      "step": 10
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "eval_loss": 1.2611583471298218,
+      "eval_runtime": 7.3824,
+      "eval_samples_per_second": 35.083,
+      "eval_steps_per_second": 0.677,
+      "step": 10
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "step": 10,
+      "total_flos": 1.3980126869979136e+16,
+      "train_loss": 1.5060624361038208,
+      "train_runtime": 361.6153,
+      "train_samples_per_second": 3.54,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3980126869979136e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}