Upload folder using huggingface_hub

checkpoints/checkpoint-64-2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c423c4117a2b8f7a35bdc820d6787dc69b2c65189b7db40fea8b3f8733a74e
+size 14851088

checkpoints/checkpoint-64-2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508d6ef57784aab69536b43f2ce5cd90ebde1abaac9a1175a55235773c7f467d
+size 29695994

checkpoints/checkpoint-64-2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed2e591b77a8475236224c0177524db10370f13296177433e7087f6779de2cd
+size 14244

checkpoints/checkpoint-64-2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4bfb939478cd93b258d0e9adcb77783c572b76ca6aa183c4f0e89ec4087307
+size 1064

checkpoints/checkpoint-64-2/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.6,
+  "eval_steps": 8,
+  "global_step": 64,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.2,
+      "grad_norm": 4.114430904388428,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 1.4122,
+      "step": 8
+    },
+    {
+      "epoch": 3.2,
+      "eval_accuracy": 0.64,
+      "eval_loss": 1.3075119256973267,
+      "eval_runtime": 4.2426,
+      "eval_samples_per_second": 35.356,
+      "eval_steps_per_second": 0.707,
+      "step": 8
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 28.230571746826172,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 1.335,
+      "step": 16
+    },
+    {
+      "epoch": 6.4,
+      "eval_accuracy": 0.6533333333333333,
+      "eval_loss": 1.3095086812973022,
+      "eval_runtime": 4.2067,
+      "eval_samples_per_second": 35.657,
+      "eval_steps_per_second": 0.713,
+      "step": 16
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 9.932499885559082,
+      "learning_rate": 9.08098456178111e-06,
+      "loss": 1.3597,
+      "step": 24
+    },
+    {
+      "epoch": 9.6,
+      "eval_accuracy": 0.6333333333333333,
+      "eval_loss": 1.3208931684494019,
+      "eval_runtime": 4.5019,
+      "eval_samples_per_second": 33.319,
+      "eval_steps_per_second": 0.666,
+      "step": 24
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 24.279809951782227,
+      "learning_rate": 7.2286917788826926e-06,
+      "loss": 1.3312,
+      "step": 32
+    },
+    {
+      "epoch": 12.8,
+      "eval_accuracy": 0.6466666666666666,
+      "eval_loss": 1.301181674003601,
+      "eval_runtime": 5.083,
+      "eval_samples_per_second": 29.51,
+      "eval_steps_per_second": 0.59,
+      "step": 32
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.4543464183807373,
+      "learning_rate": 4.846024707219149e-06,
+      "loss": 1.334,
+      "step": 40
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.6466666666666666,
+      "eval_loss": 1.3118642568588257,
+      "eval_runtime": 4.3277,
+      "eval_samples_per_second": 34.66,
+      "eval_steps_per_second": 0.693,
+      "step": 40
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 14.416548728942871,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.3728,
+      "step": 48
+    },
+    {
+      "epoch": 19.2,
+      "eval_accuracy": 0.6333333333333333,
+      "eval_loss": 1.3421196937561035,
+      "eval_runtime": 10.4599,
+      "eval_samples_per_second": 14.34,
+      "eval_steps_per_second": 0.287,
+      "step": 48
+    },
+    {
+      "epoch": 22.4,
+      "grad_norm": 8.258885383605957,
+      "learning_rate": 7.489143213519301e-07,
+      "loss": 1.3078,
+      "step": 56
+    },
+    {
+      "epoch": 22.4,
+      "eval_accuracy": 0.6333333333333333,
+      "eval_loss": 1.3307832479476929,
+      "eval_runtime": 4.2226,
+      "eval_samples_per_second": 35.523,
+      "eval_steps_per_second": 0.71,
+      "step": 56
+    },
+    {
+      "epoch": 25.6,
+      "grad_norm": 6.2354302406311035,
+      "learning_rate": 9.48335631477948e-09,
+      "loss": 1.314,
+      "step": 64
+    },
+    {
+      "epoch": 25.6,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_loss": 1.2962980270385742,
+      "eval_runtime": 4.267,
+      "eval_samples_per_second": 35.153,
+      "eval_steps_per_second": 0.703,
+      "step": 64
+    }
+  ],
+  "logging_steps": 8,
+  "max_steps": 64,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 32,
+  "save_steps": 8,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-64-2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef62b387f1eaf68abc4cae37aee05599ba89174ec638501c69f44b25563cc88d
+size 5112