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-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-7B-v0.3-spin-2k
+
+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": 0.992,
+    "total_flos": 0.0,
+    "train_loss": 0.13708710526266404,
+    "train_runtime": 755.3343,
+    "train_samples": 2000,
+    "train_samples_per_second": 2.648,
+    "train_steps_per_second": 0.082
+}

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": 0.992,
+    "total_flos": 0.0,
+    "train_loss": 0.13708710526266404,
+    "train_runtime": 755.3343,
+    "train_samples": 2000,
+    "train_samples_per_second": 2.648,
+    "train_steps_per_second": 0.082
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.992,
+  "eval_steps": 200,
+  "global_step": 62,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 328.54480169525345,
+      "learning_rate": 7.142857142857142e-08,
+      "logits/generated": -2.9970192909240723,
+      "logits/real": -2.9409127235412598,
+      "logps/generated": -200.4732666015625,
+      "logps/real": -146.91488647460938,
+      "loss": 0.8215,
+      "rewards/accuracies": 0.0,
+      "rewards/generated": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/real": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.0569971256572375,
+      "learning_rate": 4.727272727272727e-07,
+      "logits/generated": -3.040783166885376,
+      "logits/real": -2.383355140686035,
+      "logps/generated": -287.240966796875,
+      "logps/real": -115.17728424072266,
+      "loss": 0.3046,
+      "rewards/accuracies": 0.8888888955116272,
+      "rewards/generated": -4.505245208740234,
+      "rewards/margins": 5.815672397613525,
+      "rewards/real": 1.3104275465011597,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.244047265455653,
+      "learning_rate": 3.818181818181818e-07,
+      "logits/generated": -3.106825590133667,
+      "logits/real": -2.8647141456604004,
+      "logps/generated": -315.6970520019531,
+      "logps/real": -105.74098205566406,
+      "loss": 0.1002,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -8.203957557678223,
+      "rewards/margins": 12.158824920654297,
+      "rewards/real": 3.9548678398132324,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.092728561264464,
+      "learning_rate": 2.909090909090909e-07,
+      "logits/generated": -3.0712592601776123,
+      "logits/real": -2.7888991832733154,
+      "logps/generated": -330.31231689453125,
+      "logps/real": -104.19857025146484,
+      "loss": 0.1041,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.65527057647705,
+      "rewards/margins": 13.683008193969727,
+      "rewards/real": 4.027737617492676,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.263061279314855,
+      "learning_rate": 2e-07,
+      "logits/generated": -3.1142191886901855,
+      "logits/real": -2.786735773086548,
+      "logps/generated": -334.98956298828125,
+      "logps/real": -82.46981048583984,
+      "loss": 0.0939,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -10.376106262207031,
+      "rewards/margins": 15.156408309936523,
+      "rewards/real": 4.780303001403809,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0747837434924614,
+      "learning_rate": 1.0909090909090908e-07,
+      "logits/generated": -3.1094648838043213,
+      "logits/real": -2.7698652744293213,
+      "logps/generated": -346.78778076171875,
+      "logps/real": -84.88047790527344,
+      "loss": 0.0895,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -11.16419792175293,
+      "rewards/margins": 15.87059211730957,
+      "rewards/real": 4.706392765045166,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.1961243450147478,
+      "learning_rate": 1.818181818181818e-08,
+      "logits/generated": -3.1298680305480957,
+      "logits/real": -2.925835371017456,
+      "logps/generated": -322.5990295410156,
+      "logps/real": -91.80424499511719,
+      "loss": 0.0912,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -9.97568130493164,
+      "rewards/margins": 15.569890975952148,
+      "rewards/real": 5.59420919418335,
+      "step": 60
+    },
+    {
+      "epoch": 0.992,
+      "step": 62,
+      "total_flos": 0.0,
+      "train_loss": 0.13708710526266404,
+      "train_runtime": 755.3343,
+      "train_samples_per_second": 2.648,
+      "train_steps_per_second": 0.082
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 62,
+  "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
+}