Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af3d004ead7bd9f2b3fcdd8f3e5c951915b554f29c0bb75b8708bd3dc3546218
+oid sha256:d38cd3ffb60870e6999d4a4d7e88e4c25ac601214e4ec45ff0da71caaf7ad639
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81dac7e37e6e57e6b7e353a38bceda27a57c96c42b043ea8ac6a99c9f3e09088
+oid sha256:eb65c6ebef4581b5c62d0b19121df9d1b84650d6d500e6f3bc11dc27a4083bec
 size 3250751759

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd1a24dfeabd055ee0f216a2a4a5eb04c36003528560addc63a0eea07ba9995
+oid sha256:c1bfb85ce804581adebfc2706a8dcf077ebdac1ccc8d1ace3d6d94b12fea6eb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38cc8c8f1d6ddf5fdad545376d9342a15ea697ffd9db1090beb18cf45f22174d
+oid sha256:c3a85cb0d3dbfac216e91594faef1951ed1f7da19008d4d6afe00c9b69114ee9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.989690721649485,
+  "epoch": 8.989690721649485,
   "eval_steps": 500,
-  "global_step": 504,
+  "global_step": 567,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -167,6 +167,26 @@
       "eval_samples_per_second": 0.36,
       "eval_steps_per_second": 0.09,
       "step": 504
+    },
+    {
+      "epoch": 8.989690721649485,
+      "grad_norm": 0.846682071685791,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 2.2639,
+      "step": 567
+    },
+    {
+      "epoch": 8.989690721649485,
+      "eval_gen_len": 254.744241,
+      "eval_loss": 2.3528521060943604,
+      "eval_rouge1": 0.389675,
+      "eval_rouge2": 0.083846,
+      "eval_rougeL": 0.187545,
+      "eval_rougeLsum": 0.361809,
+      "eval_runtime": 3507.2655,
+      "eval_samples_per_second": 0.359,
+      "eval_steps_per_second": 0.09,
+      "step": 567
     }
   ],
   "logging_steps": 500,
@@ -174,7 +194,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.4120853587361792e+17,
+  "total_flos": 1.5885960285782016e+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 sha256:74844d4222e4c5829b72546515e73c0abed8976e33c76df0add78cfcd23ce44c
+oid sha256:b83d80a2dc1034628d03052e87e4deb26d0f0021b554ccb93e90a6110a7ef886
 size 5112