Training in progress, epoch 1, checkpoint

checkpoint-10/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eeecf463da622ccf14842969df7287560061d79e2a45259d31e7ff666b2bb02
+size 1214121120

checkpoint-10/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.817715644836426,
+      "learning_rate": 0.0,
+      "loss": 2.4596,
+      "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.894565105438232,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.468,
+      "step": 2
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.599151134490967,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 2.4369,
+      "step": 3
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.634383678436279,
+      "learning_rate": 0.0001,
+      "loss": 2.4219,
+      "step": 4
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.405484676361084,
+      "learning_rate": 9.997377845227576e-05,
+      "loss": 2.3884,
+      "step": 5
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.227508068084717,
+      "learning_rate": 9.989514131188559e-05,
+      "loss": 2.3539,
+      "step": 6
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.989192247390747,
+      "learning_rate": 9.97641710583307e-05,
+      "loss": 2.3132,
+      "step": 7
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.904679775238037,
+      "learning_rate": 9.958100506132127e-05,
+      "loss": 2.2919,
+      "step": 8
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.8267431259155273,
+      "learning_rate": 9.934583543669453e-05,
+      "loss": 2.2709,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.6127519607543945,
+      "learning_rate": 9.905890884491195e-05,
+      "loss": 2.2313,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1856,
+      "eval_loss": 2.2107839584350586,
+      "eval_runtime": 18.3869,
+      "eval_samples_per_second": 543.864,
+      "eval_steps_per_second": 0.109,
+      "step": 10
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8791579e23520b4bd71b23dd7de782fc70967c05dcdd1d44ffc944f00ab7f116
+size 5777