Model save

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- generated_from_trainer
+model-index:
+- name: Mistral-7B-v0.3-spin-10k
+  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. -->
+
+# Mistral-7B-v0.3-spin-10k
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
+
+## 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: 5e-07
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9936305732484076,
+    "total_flos": 0.0,
+    "train_loss": 0.13574646222285736,
+    "train_runtime": 880.1183,
+    "train_samples": 2499,
+    "train_samples_per_second": 2.839,
+    "train_steps_per_second": 0.089
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.3"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9936305732484076,
+    "total_flos": 0.0,
+    "train_loss": 0.13574646222285736,
+    "train_runtime": 880.1183,
+    "train_samples": 2499,
+    "train_samples_per_second": 2.839,
+    "train_steps_per_second": 0.089
+}

trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9936305732484076,
+  "eval_steps": 200,
+  "global_step": 78,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012738853503184714,
+      "grad_norm": 326.24651409169326,
+      "learning_rate": 6.25e-08,
+      "logits/generated": -2.93477463722229,
+      "logits/real": -2.4012675285339355,
+      "logps/generated": -208.99496459960938,
+      "logps/real": -155.2028045654297,
+      "loss": 0.8485,
+      "rewards/accuracies": 0.0,
+      "rewards/generated": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/real": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 1.9033893127091575,
+      "learning_rate": 4.857142857142857e-07,
+      "logits/generated": -2.951857089996338,
+      "logits/real": -2.5705060958862305,
+      "logps/generated": -259.4918212890625,
+      "logps/real": -112.88738250732422,
+      "loss": 0.3014,
+      "rewards/accuracies": 0.8888888955116272,
+      "rewards/generated": -3.585451364517212,
+      "rewards/margins": 5.119141101837158,
+      "rewards/real": 1.533690094947815,
+      "step": 10
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 1.1705308621808606,
+      "learning_rate": 4.142857142857143e-07,
+      "logits/generated": -3.0224690437316895,
+      "logits/real": -2.6734519004821777,
+      "logps/generated": -336.2292785644531,
+      "logps/real": -106.44221496582031,
+      "loss": 0.1083,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.065248489379883,
+      "rewards/margins": 12.609029769897461,
+      "rewards/real": 3.543780565261841,
+      "step": 20
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 1.1213361280852419,
+      "learning_rate": 3.4285714285714286e-07,
+      "logits/generated": -2.9410929679870605,
+      "logits/real": -2.7236175537109375,
+      "logps/generated": -319.44488525390625,
+      "logps/real": -107.4495849609375,
+      "loss": 0.1063,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.140058517456055,
+      "rewards/margins": 12.716639518737793,
+      "rewards/real": 3.5765795707702637,
+      "step": 30
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 1.2093625558735122,
+      "learning_rate": 2.714285714285714e-07,
+      "logits/generated": -2.910172462463379,
+      "logits/real": -2.6861648559570312,
+      "logps/generated": -336.0597229003906,
+      "logps/real": -129.8443145751953,
+      "loss": 0.1091,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.90638542175293,
+      "rewards/margins": 13.79242992401123,
+      "rewards/real": 3.886044979095459,
+      "step": 40
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 1.1396658722584625,
+      "learning_rate": 2e-07,
+      "logits/generated": -2.932140588760376,
+      "logits/real": -2.6356616020202637,
+      "logps/generated": -332.86029052734375,
+      "logps/real": -102.4961929321289,
+      "loss": 0.1021,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -10.24595832824707,
+      "rewards/margins": 14.124105453491211,
+      "rewards/real": 3.8781490325927734,
+      "step": 50
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 1.1099085601056409,
+      "learning_rate": 1.2857142857142855e-07,
+      "logits/generated": -2.9857165813446045,
+      "logits/real": -2.729072332382202,
+      "logps/generated": -337.9509582519531,
+      "logps/real": -105.97525787353516,
+      "loss": 0.0955,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -10.29601764678955,
+      "rewards/margins": 14.421841621398926,
+      "rewards/real": 4.125824928283691,
+      "step": 60
+    },
+    {
+      "epoch": 0.89171974522293,
+      "grad_norm": 1.1918732387706044,
+      "learning_rate": 5.714285714285714e-08,
+      "logits/generated": -2.9917495250701904,
+      "logits/real": -2.670356035232544,
+      "logps/generated": -335.4694519042969,
+      "logps/real": -97.86441040039062,
+      "loss": 0.1021,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -10.20665168762207,
+      "rewards/margins": 13.933235168457031,
+      "rewards/real": 3.726583480834961,
+      "step": 70
+    },
+    {
+      "epoch": 0.9936305732484076,
+      "step": 78,
+      "total_flos": 0.0,
+      "train_loss": 0.13574646222285736,
+      "train_runtime": 880.1183,
+      "train_samples_per_second": 2.839,
+      "train_steps_per_second": 0.089
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 78,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}