Model save

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral-base-sftspin-2k
+  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-base-sftspin-2k
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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
+- total_train_batch_size: 16
+- 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": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.20190721225738525,
+    "train_runtime": 757.3333,
+    "train_samples": 2000,
+    "train_samples_per_second": 2.641,
+    "train_steps_per_second": 0.165
+}

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": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.20190721225738525,
+    "train_runtime": 757.3333,
+    "train_samples": 2000,
+    "train_samples_per_second": 2.641,
+    "train_steps_per_second": 0.165
+}

trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 239.1858166998272,
+      "learning_rate": 3.846153846153846e-08,
+      "logits/generated": -2.2126176357269287,
+      "logits/real": -2.479367733001709,
+      "logps/generated": -128.46270751953125,
+      "logps/real": -80.73978424072266,
+      "loss": 0.8095,
+      "rewards/accuracies": 0.0,
+      "rewards/generated": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/real": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 70.17698370139641,
+      "learning_rate": 3.8461538461538463e-07,
+      "logits/generated": -2.3260881900787354,
+      "logits/real": -2.471503257751465,
+      "logps/generated": -223.9189453125,
+      "logps/real": -140.8146209716797,
+      "loss": 0.5207,
+      "rewards/accuracies": 0.8055555820465088,
+      "rewards/generated": -1.674961805343628,
+      "rewards/margins": 1.8044724464416504,
+      "rewards/real": 0.12951046228408813,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 88.37326224017356,
+      "learning_rate": 4.6874999999999996e-07,
+      "logits/generated": -2.450636386871338,
+      "logits/real": -2.3606960773468018,
+      "logps/generated": -232.05966186523438,
+      "logps/real": -117.79029846191406,
+      "loss": 0.2281,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -5.391738414764404,
+      "rewards/margins": 6.387595176696777,
+      "rewards/real": 0.9958569407463074,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.440901528921371,
+      "learning_rate": 4.2410714285714283e-07,
+      "logits/generated": -2.7457003593444824,
+      "logits/real": -2.6319069862365723,
+      "logps/generated": -247.0005645751953,
+      "logps/real": -130.16738891601562,
+      "loss": 0.1927,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -6.554670810699463,
+      "rewards/margins": 7.878050804138184,
+      "rewards/real": 1.3233797550201416,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 11.777329586857231,
+      "learning_rate": 3.794642857142857e-07,
+      "logits/generated": -2.84816312789917,
+      "logits/real": -2.5522327423095703,
+      "logps/generated": -289.16925048828125,
+      "logps/real": -115.33210754394531,
+      "loss": 0.1915,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -6.927525520324707,
+      "rewards/margins": 8.304718971252441,
+      "rewards/real": 1.3771930932998657,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 64.00945422261239,
+      "learning_rate": 3.348214285714285e-07,
+      "logits/generated": -2.8668458461761475,
+      "logits/real": -2.6166741847991943,
+      "logps/generated": -303.78253173828125,
+      "logps/real": -128.0586395263672,
+      "loss": 0.1909,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.226629257202148,
+      "rewards/margins": 10.975615501403809,
+      "rewards/real": 1.7489855289459229,
+      "step": 50
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 64.92294716516143,
+      "learning_rate": 2.9017857142857143e-07,
+      "logits/generated": -2.7347352504730225,
+      "logits/real": -2.569279670715332,
+      "logps/generated": -243.7904815673828,
+      "logps/real": -120.55989837646484,
+      "loss": 0.1607,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -6.975653171539307,
+      "rewards/margins": 8.520237922668457,
+      "rewards/real": 1.5445842742919922,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 10.402116669483359,
+      "learning_rate": 2.4553571428571425e-07,
+      "logits/generated": -2.8186283111572266,
+      "logits/real": -2.7718710899353027,
+      "logps/generated": -250.1753387451172,
+      "logps/real": -132.1046142578125,
+      "loss": 0.1834,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -7.1443190574646,
+      "rewards/margins": 9.396718978881836,
+      "rewards/real": 2.252399444580078,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 25.16942649833656,
+      "learning_rate": 2.0089285714285714e-07,
+      "logits/generated": -2.5663483142852783,
+      "logits/real": -2.4327187538146973,
+      "logps/generated": -257.9368896484375,
+      "logps/real": -112.90299987792969,
+      "loss": 0.1565,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -7.920647621154785,
+      "rewards/margins": 9.483409881591797,
+      "rewards/real": 1.5627624988555908,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 38.89840446739152,
+      "learning_rate": 1.5624999999999999e-07,
+      "logits/generated": -2.746872663497925,
+      "logits/real": -2.486171245574951,
+      "logps/generated": -283.3935546875,
+      "logps/real": -120.43995666503906,
+      "loss": 0.1437,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -8.452750205993652,
+      "rewards/margins": 11.078439712524414,
+      "rewards/real": 2.62568998336792,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.359766183105411,
+      "learning_rate": 1.1160714285714285e-07,
+      "logits/generated": -2.6126272678375244,
+      "logits/real": -2.444281578063965,
+      "logps/generated": -253.35238647460938,
+      "logps/real": -109.86905670166016,
+      "loss": 0.1382,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -7.747033596038818,
+      "rewards/margins": 10.339635848999023,
+      "rewards/real": 2.592602252960205,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 65.35623513462569,
+      "learning_rate": 6.696428571428571e-08,
+      "logits/generated": -2.7898306846618652,
+      "logits/real": -2.5074455738067627,
+      "logps/generated": -299.50164794921875,
+      "logps/real": -120.06874084472656,
+      "loss": 0.1878,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.320104598999023,
+      "rewards/margins": 11.775839805603027,
+      "rewards/real": 2.455735445022583,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8.6316640130324,
+      "learning_rate": 2.2321428571428572e-08,
+      "logits/generated": -2.593653917312622,
+      "logits/real": -2.4506092071533203,
+      "logps/generated": -232.76126098632812,
+      "logps/real": -100.04011535644531,
+      "loss": 0.1218,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -7.186074256896973,
+      "rewards/margins": 9.549537658691406,
+      "rewards/real": 2.363464117050171,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "step": 125,
+      "total_flos": 0.0,
+      "train_loss": 0.20190721225738525,
+      "train_runtime": 757.3333,
+      "train_samples_per_second": 2.641,
+      "train_steps_per_second": 0.165
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 125,
+  "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
+}