Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b92103137cd61e0dc3624c48a99aa17d9a1709f54bc2d45a73e99dacff80678
+oid sha256:3c9dea7e0903546fc702e14b5e8cffb65840ae6e8cf092f0d985b0926d5c852d
 size 2279458540

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd341d74c3a5f3b7c56ddb5aa35da92c0d45732ff5a1340c7633f620216f6193
+oid sha256:4e362aaad5ceb943bd3d01244e3de820206c445ae1e90d07c493feb9eacb3166
 size 5843037

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be11f626f18e70679d686f55f124f6dc4d5ce6b2b1affeb2e77834c47d54d46
+oid sha256:fb69a35600d079817784df352c5431115e11921569c3cb0603d761ddc97be2da
 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": 0.266,
       "eval_steps_per_second": 0.133,
       "step": 567
+    },
+    {
+      "epoch": 9.989933709796219,
+      "grad_norm": 0.7076959609985352,
+      "learning_rate": 0.0,
+      "loss": 2.6674,
+      "step": 630
+    },
+    {
+      "epoch": 9.989933709796219,
+      "eval_gen_len": 253.127085,
+      "eval_loss": 2.6109044551849365,
+      "eval_rouge1": 0.272545,
+      "eval_rouge2": 0.040774,
+      "eval_rougeL": 0.161934,
+      "eval_rougeLsum": 0.23992,
+      "eval_runtime": 4926.8155,
+      "eval_samples_per_second": 0.256,
+      "eval_steps_per_second": 0.128,
+      "step": 630
     }
   ],
   "logging_steps": 500,
@@ -194,7 +214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1.0590609444175872e+17,
+  "total_flos": 1.1755641495984538e+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 sha256:4bf3c2f86bca10c6cd673f34e5cbd6f87aa755c2a9ffc33a2f6748f334b1be97
+oid sha256:4e46a248f8e820b04792c6a7bdd1790b750c91063592b6f5ac545c5ae9b42bc4
 size 5112