Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38cd3ffb60870e6999d4a4d7e88e4c25ac601214e4ec45ff0da71caaf7ad639
+oid sha256:0d00fd03f932fc81cc6a9542774db216c4de51b826d6659308a1526460456405
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb65c6ebef4581b5c62d0b19121df9d1b84650d6d500e6f3bc11dc27a4083bec
+oid sha256:2e8fb6d51d5b7cdfb8b1a34554f44b0de0cfea8dc56d813da2761e51761b4ed9
 size 3250751759

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1bfb85ce804581adebfc2706a8dcf077ebdac1ccc8d1ace3d6d94b12fea6eb8
+oid sha256:1346d00bec4c91c9498f7c1dc0b17a0cecd974d82527f90ae2d992fa8e9a9ba5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a85cb0d3dbfac216e91594faef1951ed1f7da19008d4d6afe00c9b69114ee9
+oid sha256:f17813ad6b6d38939684710266971383f2f67146d0719de022656b9add668ecd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.989690721649485,
+  "epoch": 9.989690721649485,
   "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": 0.359,
       "eval_steps_per_second": 0.09,
       "step": 567
+    },
+    {
+      "epoch": 9.989690721649485,
+      "grad_norm": 0.8217560648918152,
+      "learning_rate": 5e-06,
+      "loss": 2.2438,
+      "step": 630
+    },
+    {
+      "epoch": 9.989690721649485,
+      "eval_gen_len": 254.562351,
+      "eval_loss": 2.350719690322876,
+      "eval_rouge1": 0.38903,
+      "eval_rouge2": 0.083623,
+      "eval_rougeL": 0.188043,
+      "eval_rougeLsum": 0.362468,
+      "eval_runtime": 3600.727,
+      "eval_samples_per_second": 0.35,
+      "eval_steps_per_second": 0.087,
+      "step": 630
     }
   ],
   "logging_steps": 500,
@@ -194,7 +214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.5885960285782016e+17,
+  "total_flos": 1.765106698420224e+17,
   "train_batch_size": 4,
   "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:b83d80a2dc1034628d03052e87e4deb26d0f0021b554ccb93e90a6110a7ef886
+oid sha256:234c2cc7654879a0af098377cf9006aee947d6b498ddde01c8620130370187ed
 size 5112