Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b513f65f071693a24c26f6acfe08868c10cef392b47b5791724718504c59b11c
+oid sha256:0321845aa554c15389dd24dff69e92c7373fc5b04cb68327a41cdc98bbcd31ba
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f7e75f38e31f3caf6295d2c7a27b005bc90135c402a683980ad863b9088acd
+oid sha256:62afe7d04b548ec8eec3d1689d7d8c3e8d969ad62a70b280216e862ba19c8547
 size 1113991930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61452000e70e2b50dbac9e487e1828eeb816725960673eeb14278e12e0cf6cb5
+oid sha256:59624509e89bbc9b94c591ed4735982e33caa7e6875690c4ff16d1a97717d87c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e029cb676b84aed4d4462a36ff279a302dfdcc098c603c675801d47eb56104
+oid sha256:9ac9643ef164647dd74d17c68b79347a9f51627588cd7ec3dd1a18bf83f7e68f
 size 1064

last-checkpoint/tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

last-checkpoint/trainer_state.json

@@ -1,146 +1,50 @@
 {
-  "best_metric": 26.4112,
-  "best_model_checkpoint": "my-model/checkpoint-6112",
-  "epoch": 4.0,
+  "best_metric": 25.1709,
+  "best_model_checkpoint": "my-model/checkpoint-1528",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 6112,
+  "global_step": 1528,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.32722513089005234,
-      "grad_norm": 1.6467379331588745,
-      "learning_rate": 4.5909685863874345e-05,
-      "loss": 0.0168,
+      "grad_norm": 0.9616150856018066,
+      "learning_rate": 4.454624781849913e-05,
+      "loss": 0.0158,
       "step": 500
     },
     {
       "epoch": 0.6544502617801047,
-      "grad_norm": 1.3730037212371826,
-      "learning_rate": 4.181937172774869e-05,
-      "loss": 0.0246,
+      "grad_norm": 2.0808584690093994,
+      "learning_rate": 3.909249563699826e-05,
+      "loss": 0.0223,
       "step": 1000
     },
     {
       "epoch": 0.981675392670157,
-      "grad_norm": 1.1599562168121338,
-      "learning_rate": 3.7729057591623044e-05,
-      "loss": 0.0308,
+      "grad_norm": 1.145504117012024,
+      "learning_rate": 3.3638743455497386e-05,
+      "loss": 0.0271,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_loss": 5.495022296905518,
-      "eval_rouge1": 24.8013,
-      "eval_rouge2": 9.5895,
-      "eval_rougeL": 21.5936,
-      "eval_runtime": 434.7617,
-      "eval_samples_per_second": 5.049,
-      "eval_steps_per_second": 0.506,
+      "eval_loss": 5.483295917510986,
+      "eval_rouge1": 25.1709,
+      "eval_rouge2": 10.0024,
+      "eval_rougeL": 21.9926,
+      "eval_runtime": 372.8877,
+      "eval_samples_per_second": 5.886,
+      "eval_steps_per_second": 0.59,
       "step": 1528
-    },
-    {
-      "epoch": 1.3089005235602094,
-      "grad_norm": 3.42366361618042,
-      "learning_rate": 3.3638743455497386e-05,
-      "loss": 0.0539,
-      "step": 2000
-    },
-    {
-      "epoch": 1.6361256544502618,
-      "grad_norm": 3.776289701461792,
-      "learning_rate": 2.954842931937173e-05,
-      "loss": 0.0727,
-      "step": 2500
-    },
-    {
-      "epoch": 1.9633507853403143,
-      "grad_norm": 5.072182655334473,
-      "learning_rate": 2.545811518324607e-05,
-      "loss": 0.1352,
-      "step": 3000
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 5.219298839569092,
-      "eval_rouge1": 24.8743,
-      "eval_rouge2": 9.8439,
-      "eval_rougeL": 21.6411,
-      "eval_runtime": 433.0859,
-      "eval_samples_per_second": 5.068,
-      "eval_steps_per_second": 0.508,
-      "step": 3056
-    },
-    {
-      "epoch": 2.2905759162303667,
-      "grad_norm": 6.1271209716796875,
-      "learning_rate": 2.136780104712042e-05,
-      "loss": 0.4727,
-      "step": 3500
-    },
-    {
-      "epoch": 2.6178010471204187,
-      "grad_norm": 5.5732316970825195,
-      "learning_rate": 1.7277486910994763e-05,
-      "loss": 0.6959,
-      "step": 4000
-    },
-    {
-      "epoch": 2.945026178010471,
-      "grad_norm": 5.73837423324585,
-      "learning_rate": 1.3187172774869111e-05,
-      "loss": 0.9382,
-      "step": 4500
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 3.44022798538208,
-      "eval_rouge1": 26.0341,
-      "eval_rouge2": 10.6222,
-      "eval_rougeL": 22.7685,
-      "eval_runtime": 417.9997,
-      "eval_samples_per_second": 5.251,
-      "eval_steps_per_second": 0.526,
-      "step": 4584
-    },
-    {
-      "epoch": 3.2722513089005236,
-      "grad_norm": 5.353453159332275,
-      "learning_rate": 9.096858638743457e-06,
-      "loss": 0.9969,
-      "step": 5000
-    },
-    {
-      "epoch": 3.599476439790576,
-      "grad_norm": 5.323329925537109,
-      "learning_rate": 5.006544502617801e-06,
-      "loss": 1.0924,
-      "step": 5500
-    },
-    {
-      "epoch": 3.9267015706806285,
-      "grad_norm": 6.1474175453186035,
-      "learning_rate": 9.162303664921465e-07,
-      "loss": 1.2208,
-      "step": 6000
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 3.21282958984375,
-      "eval_rouge1": 26.4112,
-      "eval_rouge2": 10.9605,
-      "eval_rougeL": 23.0258,
-      "eval_runtime": 417.2936,
-      "eval_samples_per_second": 5.26,
-      "eval_steps_per_second": 0.527,
-      "step": 6112
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6112,
+  "max_steps": 4584,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -149,12 +53,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.930549272296653e+16,
+  "total_flos": 7327420304523264.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408bb8b25e44f1ecf1923d9e22dabb6474162771a082c1a83b55da4bd5267fc0
+oid sha256:9454715524d57fa2a7a3e1d17cb27d9ba1a09c66d019637bdd23107b92238a57
 size 6968