Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a32c11b2fb9e8f9be437ae777852874d5b3d39f012c85e8f3068fd7bea13655
+oid sha256:1d1608622aa3bf8e636cb9289e279cbf26895f4b5da4cafbc449b8797e80b28d
 size 990345064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac243d32e4216b4a31276a7a8b8c33baf6d0756fc6e6a121ed04cea7fbc6871
+oid sha256:f66aa6ad25785b378b052a9b77f9746cb3e1cb6df51c40c6214e8ca87fe9096e
 size 2371450

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0fcda0f19ccbac05fc69dd708540f3814211b30ba78bbaef6a48f09d32f02b
+oid sha256:4e4cd1573d9e8d060ece0d71e748152995885fe7b8aefe7af35f7aebd957ed8d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffebe1a820dfa3feb9cc3e77fdf4616940616e975f277a2807eff02042148049
+oid sha256:994c8cdfb5648b7ecc56a03fec6c3daa3fe34d4ff179bf3c5b9a49027dbd6fe1
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.989933709796219,
+  "epoch": 9.989933709796219,
   "eval_steps": 500,
-  "global_step": 567,
+  "global_step": 630,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,26 @@
       "eval_samples_per_second": 0.328,
       "eval_steps_per_second": 0.164,
       "step": 567
+    },
+    {
+      "epoch": 9.989933709796219,
+      "grad_norm": 0.24972490966320038,
+      "learning_rate": 0.0,
+      "loss": 2.5162,
+      "step": 630
+    },
+    {
+      "epoch": 9.989933709796219,
+      "eval_gen_len": 253.612391,
+      "eval_loss": 2.3985466957092285,
+      "eval_rouge1": 0.255173,
+      "eval_rouge2": 0.041657,
+      "eval_rougeL": 0.161811,
+      "eval_rougeLsum": 0.230633,
+      "eval_runtime": 3701.9783,
+      "eval_samples_per_second": 0.34,
+      "eval_steps_per_second": 0.17,
+      "step": 630
     }
   ],
   "logging_steps": 500,
@@ -194,7 +214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1.0556082393867878e+17,
+  "total_flos": 1.1660459051896013e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177fefbba51081613f609ca570036d01f795cfd6e17c3370a3c09ff5131f613d
+oid sha256:1a6eee61668305c3c50d237bb03f03ac294ba8ceb3dff29ce2e012958e4351c1
 size 5112