End of training

README.md

@@ -0,0 +1,71 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: runs
+  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. -->
+
+# runs
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1137
+- Accuracy: 0.0000
+
+## 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: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 48
+- seed: 444
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_ratio: 0.3
+- training_steps: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.03  | 10   | 4.7890          | 0.1380   |
+| 4.9326        | 0.05  | 20   | 4.4600          | 0.1310   |
+| 4.9326        | 0.08  | 30   | 4.1364          | 0.0172   |
+| 4.1299        | 0.11  | 40   | 3.7156          | 0.0010   |
+| 4.1299        | 0.13  | 50   | 3.3965          | 0.0002   |
+| 3.4428        | 0.16  | 60   | 3.2530          | 0.0002   |
+| 3.4428        | 0.19  | 70   | 3.1727          | 0.0000   |
+| 3.1873        | 0.21  | 80   | 3.1316          | 0.0000   |
+| 3.1873        | 0.24  | 90   | 3.1165          | 0.0000   |
+| 3.1176        | 0.26  | 100  | 3.1137          | 0.0000   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.26,
+    "train_loss": 3.762029037475586,
+    "train_runtime": 467.4517,
+    "train_samples_per_second": 10.268,
+    "train_steps_per_second": 0.214
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 262
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778a4bc236c5fd3e5d2efe707aaedf489a383b17b1700aa405dc4bcce2f0ad7e
+size 126945264

runs/Feb11_11-26-36_MacBook-Pro-sunsetsobserver.local/events.out.tfevents.1707647197.MacBook-Pro-sunsetsobserver.local.91650.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a198491c1df49be35f607fa537dfb5da0acd9fa6894dcc5c1c534655c67e24
+size 130

runs/Feb19_23-08-36_node851/events.out.tfevents.1708380519.node851.11924.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b907aa510505c0198599e02846aa8a235ede5498d5bbe16bbc2290130540ffc
+size 8491

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.26,
+    "train_loss": 3.762029037475586,
+    "train_runtime": 467.4517,
+    "train_samples_per_second": 10.268,
+    "train_steps_per_second": 0.214
+}

trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_metric": 3.1137237548828125,
+  "best_model_checkpoint": "runs/checkpoint-100",
+  "epoch": 0.26455026455026454,
+  "eval_steps": 10,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.13795485020402745,
+      "eval_loss": 4.789039134979248,
+      "eval_runtime": 37.8471,
+      "eval_samples_per_second": 122.969,
+      "eval_steps_per_second": 2.563,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 4.9326,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.13097405669206658,
+      "eval_loss": 4.460000991821289,
+      "eval_runtime": 37.702,
+      "eval_samples_per_second": 123.442,
+      "eval_steps_per_second": 2.573,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.017237469923391858,
+      "eval_loss": 4.136398792266846,
+      "eval_runtime": 37.8214,
+      "eval_samples_per_second": 123.052,
+      "eval_steps_per_second": 2.565,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 4.1299,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.001030985287561302,
+      "eval_loss": 3.7156336307525635,
+      "eval_runtime": 37.596,
+      "eval_samples_per_second": 123.79,
+      "eval_steps_per_second": 2.58,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.0002322747955471305,
+      "eval_loss": 3.3965370655059814,
+      "eval_runtime": 37.6834,
+      "eval_samples_per_second": 123.503,
+      "eval_steps_per_second": 2.574,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.112604669781572e-05,
+      "loss": 3.4428,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.0001927115061956962,
+      "eval_loss": 3.253018617630005,
+      "eval_runtime": 37.7176,
+      "eval_samples_per_second": 123.391,
+      "eval_steps_per_second": 2.572,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 3.530917221687149e-05,
+      "eval_loss": 3.1727356910705566,
+      "eval_runtime": 37.8548,
+      "eval_samples_per_second": 122.943,
+      "eval_steps_per_second": 2.562,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 3.1873,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 3.211858436594937e-05,
+      "eval_loss": 3.131649971008301,
+      "eval_runtime": 37.7677,
+      "eval_samples_per_second": 123.227,
+      "eval_steps_per_second": 2.568,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 2.4248467667008132e-05,
+      "eval_loss": 3.116509437561035,
+      "eval_runtime": 37.6259,
+      "eval_samples_per_second": 123.691,
+      "eval_steps_per_second": 2.578,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0,
+      "loss": 3.1176,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 2.2546820813182997e-05,
+      "eval_loss": 3.1137237548828125,
+      "eval_runtime": 37.9061,
+      "eval_samples_per_second": 122.777,
+      "eval_steps_per_second": 2.559,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "step": 100,
+      "total_flos": 933745862246400.0,
+      "train_loss": 3.762029037475586,
+      "train_runtime": 467.4517,
+      "train_samples_per_second": 10.268,
+      "train_steps_per_second": 0.214
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 933745862246400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1063fe7503a610b9cb5a878c7f044eed67bcbe59de58ca3b4f51d055c93ed9a4
+size 4664