Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "google/flan-t5-xxl",
+  "base_model_name_or_path": "google/flan-t5-xl",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

last-checkpoint/global_step790/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be5091c1d4d363dd5d9eeb380cc1069ccee2d73d55ba4f8637006d5581477e4
+size 28315088

last-checkpoint/global_step790/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bcca6fce13123f8cd9ec374ddf906c7b7e17d2a43f60cb5a3f97cf206923c37
+size 28315088

last-checkpoint/global_step790/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64621a2d4d13b9e92b17253bfd2c4bfaab36e77444417075b812c0ad48aba63c
+size 2850543502

last-checkpoint/global_step790/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6f73fe9e7e2619f711c9811c18e0e7ca3757a4f3d858dd85f66e093697a8f9
+size 2850543310

last-checkpoint/latest

@@ -1 +1 @@
-global_step1581
+global_step790

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f232d8d672d6ff9e3cc5ac4ba64234b9f002d5e144a43ee183dc01871e2f10e5
+oid sha256:16a7aa1548464e6c880ebd42aba4c07ee57fb38feb25979f4c82c0f0bec9f0e6
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25f573f6bcb03f0bbfe93da192a1ab49ba692dcab33095de44fc91e5e4216a5
+oid sha256:38d40d71f540bdd7fdb4af7e756f13010eb6a96ab531b88e35903b066788ad63
 size 14512

last-checkpoint/trainer_state.json

@@ -1,56 +1,44 @@
 {
-  "best_metric": 2.2135026454925537,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581",
-  "epoch": 1.0,
+  "best_metric": 2.392251491546631,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-790",
+  "epoch": 0.9993674889310563,
   "eval_steps": 500,
-  "global_step": 1581,
+  "global_step": 790,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.0008497772211805019,
-      "loss": 2.4966,
-      "step": 500
-    },
     {
       "epoch": 0.63,
-      "learning_rate": 0.0009445572420019074,
-      "loss": 2.3574,
-      "step": 1000
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0009999999999999998,
-      "loss": 2.3094,
-      "step": 1500
+      "learning_rate": 8.49777221180502e-05,
+      "loss": 2.8794,
+      "step": 500
     },
     {
       "epoch": 1.0,
       "eval_bleu": 1.0,
       "eval_brevity_penalty": 1.0,
       "eval_length_ratio": 1.0,
-      "eval_loss": 2.2135026454925537,
+      "eval_loss": 2.392251491546631,
       "eval_precisions": [
         1.0,
         1.0,
         1.0,
         1.0
       ],
-      "eval_reference_length": 53394,
-      "eval_runtime": 2937.3471,
-      "eval_samples_per_second": 0.957,
-      "eval_steps_per_second": 0.12,
-      "eval_translation_length": 53394,
-      "step": 1581
+      "eval_reference_length": 53098,
+      "eval_runtime": 1401.0268,
+      "eval_samples_per_second": 2.006,
+      "eval_steps_per_second": 0.126,
+      "eval_translation_length": 53098,
+      "step": 790
     }
   ],
   "logging_steps": 500,
-  "max_steps": 15810,
-  "num_train_epochs": 10,
+  "max_steps": 23700,
+  "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 771945142419456.0,
+  "total_flos": 385850466631680.0,
   "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:da68e390908bbf17cdb4f041431915c87c2f3f6b8699cebf8dcb70aae5296d20
+oid sha256:7619c25d1f961a939120b81d521c14f9d13e3f5fcb5ceba87a0c9e7d8c62891c
 size 6648