End of training

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 0.8285,
+    "eval_gen_len": 237.3961,
+    "eval_loss": 0.2942627966403961,
+    "eval_runtime": 43.6199,
+    "eval_samples": 414,
+    "eval_samples_per_second": 9.491,
+    "eval_steps_per_second": 0.16,
+    "predict_bleu": 0.8295,
+    "predict_gen_len": 236.6884,
+    "predict_loss": 0.30217134952545166,
+    "predict_runtime": 45.6559,
+    "predict_samples": 414,
+    "predict_samples_per_second": 9.068,
+    "predict_steps_per_second": 0.153,
+    "train_loss": 0.5014902756764339,
+    "train_runtime": 1218.7296,
+    "train_samples": 3312,
+    "train_samples_per_second": 27.176,
+    "train_steps_per_second": 0.427
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 0.8285,
+    "eval_gen_len": 237.3961,
+    "eval_loss": 0.2942627966403961,
+    "eval_runtime": 43.6199,
+    "eval_samples": 414,
+    "eval_samples_per_second": 9.491,
+    "eval_steps_per_second": 0.16
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 0.8295,
+    "predict_gen_len": 236.6884,
+    "predict_loss": 0.30217134952545166,
+    "predict_runtime": 45.6559,
+    "predict_samples": 414,
+    "predict_samples_per_second": 9.068,
+    "predict_steps_per_second": 0.153
+}

runs/Apr11_11-51-59_relela-04/events.out.tfevents.1681229878.relela-04.1098459.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009e0420e1a168fa8e0ee75417f8ba94e7bbbbf29675f1cee83b6feae5c995ff
+size 410

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.5014902756764339,
+    "train_runtime": 1218.7296,
+    "train_samples": 3312,
+    "train_samples_per_second": 27.176,
+    "train_steps_per_second": 0.427
+}

trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.4170507490634918,
+      "eval_runtime": 10.6441,
+      "eval_samples_per_second": 38.895,
+      "eval_steps_per_second": 0.658,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.3522029221057892,
+      "eval_runtime": 10.2206,
+      "eval_samples_per_second": 40.507,
+      "eval_steps_per_second": 0.685,
+      "step": 104
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.327457994222641,
+      "eval_runtime": 9.9368,
+      "eval_samples_per_second": 41.663,
+      "eval_steps_per_second": 0.704,
+      "step": 156
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.3160160779953003,
+      "eval_runtime": 10.0929,
+      "eval_samples_per_second": 41.019,
+      "eval_steps_per_second": 0.694,
+      "step": 208
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.3063710033893585,
+      "eval_runtime": 11.8097,
+      "eval_samples_per_second": 35.056,
+      "eval_steps_per_second": 0.593,
+      "step": 260
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.30116963386535645,
+      "eval_runtime": 8.1965,
+      "eval_samples_per_second": 50.509,
+      "eval_steps_per_second": 0.854,
+      "step": 312
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.29874515533447266,
+      "eval_runtime": 10.1156,
+      "eval_samples_per_second": 40.927,
+      "eval_steps_per_second": 0.692,
+      "step": 364
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.2959335446357727,
+      "eval_runtime": 9.8469,
+      "eval_samples_per_second": 42.044,
+      "eval_steps_per_second": 0.711,
+      "step": 416
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.2947290241718292,
+      "eval_runtime": 9.9973,
+      "eval_samples_per_second": 41.411,
+      "eval_steps_per_second": 0.7,
+      "step": 468
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.5085,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 0.2942627966403961,
+      "eval_runtime": 10.7975,
+      "eval_samples_per_second": 38.342,
+      "eval_steps_per_second": 0.648,
+      "step": 520
+    },
+    {
+      "epoch": 10.0,
+      "step": 520,
+      "total_flos": 1.008434279350272e+16,
+      "train_loss": 0.5014902756764339,
+      "train_runtime": 1218.7296,
+      "train_samples_per_second": 27.176,
+      "train_steps_per_second": 0.427
+    }
+  ],
+  "max_steps": 520,
+  "num_train_epochs": 10,
+  "total_flos": 1.008434279350272e+16,
+  "trial_name": null,
+  "trial_params": null
+}