End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.15678054094314575,
+    "eval_runtime": 1.4699,
+    "eval_samples_per_second": 19.73,
+    "eval_steps_per_second": 0.68,
+    "total_flos": 6.263709224435712e+16,
+    "train_loss": 0.07444413304328919,
+    "train_runtime": 266.0056,
+    "train_samples_per_second": 9.473,
+    "train_steps_per_second": 0.075
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.15678054094314575,
+    "eval_runtime": 1.4699,
+    "eval_samples_per_second": 19.73,
+    "eval_steps_per_second": 0.68
+}

runs/May31_19-27-40_a4f48207357d/events.out.tfevents.1685561551.a4f48207357d.7155.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57702f9d24bdf0d4337de06e33b6ce2b49e217744391c93b634ce4e2c500cc7c
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 6.263709224435712e+16,
+    "train_loss": 0.07444413304328919,
+    "train_runtime": 266.0056,
+    "train_samples_per_second": 9.473,
+    "train_steps_per_second": 0.075
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "cfe-telmex-classification-finetuned-v2/checkpoint-4",
+  "epoch": 10.0,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.3748968243598938,
+      "eval_runtime": 2.1831,
+      "eval_samples_per_second": 13.284,
+      "eval_steps_per_second": 0.458,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.15678054094314575,
+      "eval_runtime": 1.1976,
+      "eval_samples_per_second": 24.214,
+      "eval_steps_per_second": 0.835,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.04947631061077118,
+      "eval_runtime": 1.1966,
+      "eval_samples_per_second": 24.234,
+      "eval_steps_per_second": 0.836,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.018764613196253777,
+      "eval_runtime": 1.1959,
+      "eval_samples_per_second": 24.249,
+      "eval_steps_per_second": 0.836,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.136,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.008702973835170269,
+      "eval_runtime": 1.262,
+      "eval_samples_per_second": 22.98,
+      "eval_steps_per_second": 0.792,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.005973159335553646,
+      "eval_runtime": 1.1978,
+      "eval_samples_per_second": 24.211,
+      "eval_steps_per_second": 0.835,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.006297494284808636,
+      "eval_runtime": 1.2767,
+      "eval_samples_per_second": 22.715,
+      "eval_steps_per_second": 0.783,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0038704965263605118,
+      "eval_runtime": 1.1931,
+      "eval_samples_per_second": 24.305,
+      "eval_steps_per_second": 0.838,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0018120368476957083,
+      "eval_runtime": 1.1758,
+      "eval_samples_per_second": 24.665,
+      "eval_steps_per_second": 0.851,
+      "step": 18
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0129,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0014965758891776204,
+      "eval_runtime": 1.2143,
+      "eval_samples_per_second": 23.883,
+      "eval_steps_per_second": 0.824,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "step": 20,
+      "total_flos": 6.263709224435712e+16,
+      "train_loss": 0.07444413304328919,
+      "train_runtime": 266.0056,
+      "train_samples_per_second": 9.473,
+      "train_steps_per_second": 0.075
+    }
+  ],
+  "max_steps": 20,
+  "num_train_epochs": 10,
+  "total_flos": 6.263709224435712e+16,
+  "trial_name": null,
+  "trial_params": null
+}