End of training

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 19.0,
+    "eval_loss": 2.229624032974243,
+    "eval_rouge1": 0.0,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 0.0,
+    "eval_rougeLsum": 0.0,
+    "eval_runtime": 123.8218,
+    "eval_samples": 457,
+    "eval_samples_per_second": 3.691,
+    "eval_steps_per_second": 1.849,
+    "train_loss": 3.188586384726212,
+    "train_runtime": 2801.2903,
+    "train_samples": 3567,
+    "train_samples_per_second": 3.82,
+    "train_steps_per_second": 1.911
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 19.0,
+    "eval_loss": 2.229624032974243,
+    "eval_rouge1": 0.0,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 0.0,
+    "eval_rougeLsum": 0.0,
+    "eval_runtime": 123.8218,
+    "eval_samples": 457,
+    "eval_samples_per_second": 3.691,
+    "eval_steps_per_second": 1.849
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

runs/Feb24_10-06-36_cs-3090-02/events.out.tfevents.1677229346.cs-3090-02.120683.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c4fb526aa86dd811f1ef246279878618e00a3f19c75b967dee7c5b7a7ef3cf
+size 565

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.188586384726212,
+    "train_runtime": 2801.2903,
+    "train_samples": 3567,
+    "train_samples_per_second": 3.82,
+    "train_steps_per_second": 1.911
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 5352,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.53288490284006e-05,
+      "loss": 5.6622,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.06576980568012e-05,
+      "loss": 3.5766,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.598654708520179e-05,
+      "loss": 3.2077,
+      "step": 1500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.131539611360239e-05,
+      "loss": 3.0311,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6644245142002988e-05,
+      "loss": 2.9493,
+      "step": 2500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.197309417040359e-05,
+      "loss": 2.8781,
+      "step": 3000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7301943198804185e-05,
+      "loss": 2.8183,
+      "step": 3500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2630792227204785e-05,
+      "loss": 2.7417,
+      "step": 4000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.959641255605381e-06,
+      "loss": 2.6946,
+      "step": 4500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.2884902840059795e-06,
+      "loss": 2.6942,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "step": 5352,
+      "total_flos": 1.0169775338950656e+16,
+      "train_loss": 3.188586384726212,
+      "train_runtime": 2801.2903,
+      "train_samples_per_second": 3.82,
+      "train_steps_per_second": 1.911
+    }
+  ],
+  "max_steps": 5352,
+  "num_train_epochs": 3,
+  "total_flos": 1.0169775338950656e+16,
+  "trial_name": null,
+  "trial_params": null
+}