Model save

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: Qwen2-7B-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. -->
+
+# Qwen2-7B-spin-2k
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1115
+- Rewards/real: 6.6307
+- Rewards/generated: -5.6978
+- Rewards/accuracies: 1.0
+- Rewards/margins: 12.3284
+- Logps/generated: -348.4622
+- Logps/real: -123.6893
+- Logits/generated: -0.9537
+- Logits/real: -1.6166
+
+## 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
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
+| 0.1108        | 0.8   | 50   | 0.1115          | 6.6307       | -5.6978           | 1.0                | 12.3284         | -348.4622       | -123.6893  | -0.9537          | -1.6166     |
+
+
+### 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": 0.18373099305937368,
+    "train_runtime": 1010.4406,
+    "train_samples": 1995,
+    "train_samples_per_second": 1.974,
+    "train_steps_per_second": 0.061
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.43.3"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b2d2ad10f449039c17ada01131b02a6b3e616823ca52036fb2c266c7528854b
+oid sha256:7ee0f8d11a59657fb1e37eae1ef598510245e50f07be2b71424bc21742be6ffb
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e2f1af94f889ceb67961e7155547d4098e9810d75053932849ed82d263a538
+oid sha256:d21abc8ec5edf052a21cb394065b7ce070f9890804fa7821735172339897e908
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372914dc058e623c29905361f1f165c3c0b573350dbcbb6fc5d713c270f8d1ab
+oid sha256:3534152c43d873496f035727648ee134eb8e107f636862fc6771e93db18e13a1
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706d9311e15da5a31d32dd68bf2b65b9db26dc03f0bf50ee6edce57ac286aa1f
+oid sha256:74db9b8213276cbd4eaf70db929e32f3bff4d581f9324782b971fdbe3f9ed9c0
 size 1089994880

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.992,
+    "total_flos": 0.0,
+    "train_loss": 0.18373099305937368,
+    "train_runtime": 1010.4406,
+    "train_samples": 1995,
+    "train_samples_per_second": 1.974,
+    "train_steps_per_second": 0.061
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.992,
+  "eval_steps": 50,
+  "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": 98.16447669559693,
+      "learning_rate": 7.142857142857142e-08,
+      "logits/generated": -1.7165532112121582,
+      "logits/real": -1.9473252296447754,
+      "logps/generated": -275.8633728027344,
+      "logps/real": -119.67874145507812,
+      "loss": 0.8563,
+      "rewards/accuracies": 0.0,
+      "rewards/generated": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/real": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.433954312310394,
+      "learning_rate": 4.727272727272727e-07,
+      "logits/generated": -1.7268381118774414,
+      "logits/real": -1.6472580432891846,
+      "logps/generated": -287.07708740234375,
+      "logps/real": -172.39788818359375,
+      "loss": 0.5272,
+      "rewards/accuracies": 0.8472222089767456,
+      "rewards/generated": -0.3371984362602234,
+      "rewards/margins": 1.6153303384780884,
+      "rewards/real": 1.2781319618225098,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.0626183508441827,
+      "learning_rate": 3.818181818181818e-07,
+      "logits/generated": -1.3058226108551025,
+      "logits/real": -1.6506996154785156,
+      "logps/generated": -306.6280212402344,
+      "logps/real": -114.25825500488281,
+      "loss": 0.1169,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -2.2147715091705322,
+      "rewards/margins": 8.338987350463867,
+      "rewards/real": 6.124215602874756,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5086367809412861,
+      "learning_rate": 2.909090909090909e-07,
+      "logits/generated": -1.0788180828094482,
+      "logits/real": -1.9709659814834595,
+      "logps/generated": -329.04046630859375,
+      "logps/real": -102.8577880859375,
+      "loss": 0.1079,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -4.102789878845215,
+      "rewards/margins": 10.5944242477417,
+      "rewards/real": 6.491633415222168,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5442495957101562,
+      "learning_rate": 2e-07,
+      "logits/generated": -0.9625035524368286,
+      "logits/real": -1.762656807899475,
+      "logps/generated": -316.8744201660156,
+      "logps/real": -105.2821044921875,
+      "loss": 0.1084,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -4.126258373260498,
+      "rewards/margins": 10.838096618652344,
+      "rewards/real": 6.711838722229004,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.466220159360493,
+      "learning_rate": 1.0909090909090908e-07,
+      "logits/generated": -1.0104159116744995,
+      "logits/real": -1.8771381378173828,
+      "logps/generated": -325.93133544921875,
+      "logps/real": -100.94727325439453,
+      "loss": 0.1108,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -4.898512840270996,
+      "rewards/margins": 11.485854148864746,
+      "rewards/real": 6.58734130859375,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "eval_logits/generated": -0.9536736011505127,
+      "eval_logits/real": -1.6165881156921387,
+      "eval_logps/generated": -348.4621887207031,
+      "eval_logps/real": -123.68927764892578,
+      "eval_loss": 0.11147800087928772,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/generated": -5.697763442993164,
+      "eval_rewards/margins": 12.328431129455566,
+      "eval_rewards/real": 6.630667686462402,
+      "eval_runtime": 31.5183,
+      "eval_samples_per_second": 6.346,
+      "eval_steps_per_second": 0.412,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.403885105692105,
+      "learning_rate": 1.818181818181818e-08,
+      "logits/generated": -1.0189651250839233,
+      "logits/real": -1.817792296409607,
+      "logps/generated": -332.2081298828125,
+      "logps/real": -104.88079833984375,
+      "loss": 0.1131,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -5.417947769165039,
+      "rewards/margins": 11.97882080078125,
+      "rewards/real": 6.560873985290527,
+      "step": 60
+    },
+    {
+      "epoch": 0.992,
+      "step": 62,
+      "total_flos": 0.0,
+      "train_loss": 0.18373099305937368,
+      "train_runtime": 1010.4406,
+      "train_samples_per_second": 1.974,
+      "train_steps_per_second": 0.061
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 62,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "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
+}