End of training

README.md

@@ -2,11 +2,23 @@
 library_name: transformers
 tags:
 - generated_from_trainer
+datasets:
+- data/babylm
 metrics:
 - accuracy
 model-index:
 - name: base_seed-42_1e-3
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: data/babylm
+      type: data/babylm
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # base_seed-42_1e-3
 
-This model was trained from scratch on an unknown dataset.
+This model was trained from scratch on the data/babylm dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 - Accuracy: 0.0

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.0,
+    "eval_loss": NaN,
+    "eval_runtime": 107.3583,
+    "eval_samples": 45143,
+    "eval_samples_per_second": 420.489,
+    "eval_steps_per_second": 6.576,
+    "perplexity": NaN,
+    "total_flos": 2.43931266809856e+17,
+    "train_loss": 5.705915669502262e+18,
+    "train_runtime": 8918.7734,
+    "train_samples": 466779,
+    "train_samples_per_second": 1046.734,
+    "train_steps_per_second": 4.09
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.0,
+    "eval_loss": NaN,
+    "eval_runtime": 107.3583,
+    "eval_samples": 45143,
+    "eval_samples_per_second": 420.489,
+    "eval_steps_per_second": 6.576,
+    "perplexity": NaN
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.43931266809856e+17,
+    "train_loss": 5.705915669502262e+18,
+    "train_runtime": 8918.7734,
+    "train_samples": 466779,
+    "train_samples_per_second": 1046.734,
+    "train_steps_per_second": 4.09
+}

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": null,
+  "best_metric": Infinity,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 7296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5484335367107699,
+      "grad_norm": NaN,
+      "learning_rate": 3.121875e-05,
+      "loss": 4.163036072468851e+19,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 105.0094,
+      "eval_samples_per_second": 429.895,
+      "eval_steps_per_second": 6.723,
+      "step": 1824
+    },
+    {
+      "epoch": 1.0965243024610956,
+      "grad_norm": NaN,
+      "learning_rate": 6.246875000000001e-05,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6449578391718653,
+      "grad_norm": NaN,
+      "learning_rate": 9.371875000000001e-05,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 105.1985,
+      "eval_samples_per_second": 429.122,
+      "eval_steps_per_second": 6.711,
+      "step": 3648
+    },
+    {
+      "epoch": 2.193048604922191,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012496875,
+      "loss": 0.0,
+      "step": 4000
+    },
+    {
+      "epoch": 2.741482141632961,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015621875,
+      "loss": 0.0,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 106.8538,
+      "eval_samples_per_second": 422.474,
+      "eval_steps_per_second": 6.607,
+      "step": 5472
+    },
+    {
+      "epoch": 3.2895729073832864,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018746875,
+      "loss": 0.0,
+      "step": 6000
+    },
+    {
+      "epoch": 3.8380064440940562,
+      "grad_norm": NaN,
+      "learning_rate": 0.00021871875,
+      "loss": 0.0,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 107.8002,
+      "eval_samples_per_second": 418.765,
+      "eval_steps_per_second": 6.549,
+      "step": 7296
+    },
+    {
+      "epoch": 4.0,
+      "step": 7296,
+      "total_flos": 2.43931266809856e+17,
+      "train_loss": 5.705915669502262e+18,
+      "train_runtime": 8918.7734,
+      "train_samples_per_second": 1046.734,
+      "train_steps_per_second": 4.09
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 36480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.43931266809856e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}