Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e769a8adc6851c571d318f9f8d597aa021ab357ebcd61e613e6346460833779a
+oid sha256:df0614e6ae0c4cca08ec46a3a0eca5c114c29487c73131333ee0ac8747dbc354
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81abb427d2bb19813d0e17c56caed64154b36100906c45a8547cd38afbae3d5
+oid sha256:c375252e989676c82361bf75c9e05f8625ab364d94f54619de39642b83371a55
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404667d89973760348cc653c442f08c243df998777422cd0dd9b4e5b7b18505d
+oid sha256:a3206cfea353705871f16d46e55ccf93893b489d46b83fd7ba2c4d45d71b93a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466256ee71b0a044b429768d7371618a1dc77becfc275f201cdc2e4d1e676296
+oid sha256:30c8d100410f3813df39e9f84e8d440fdc3cad2e6c15e5ee2bb73e18d8c8af53
 size 1064

last-checkpoint/trainer_state.json

@@ -1,102 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1640,
+  "global_step": 328,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_gen_len": 11.120274914089347,
-      "eval_loss": 24.898656845092773,
-      "eval_rouge1": 29.9366,
-      "eval_rouge2": 22.9687,
-      "eval_rougeL": 26.9975,
-      "eval_rougeLsum": 27.1774,
-      "eval_runtime": 152.4326,
-      "eval_samples_per_second": 1.909,
-      "eval_steps_per_second": 0.243,
-      "step": 328
-    },
-    {
-      "epoch": 1.52,
-      "learning_rate": 2e-05,
-      "loss": 25.467,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_gen_len": 0.0,
-      "eval_loss": 1.3504424095153809,
-      "eval_rouge1": 51.142,
-      "eval_rouge2": 49.8705,
-      "eval_rougeL": 51.1588,
-      "eval_rougeLsum": 51.1528,
-      "eval_runtime": 153.7577,
-      "eval_samples_per_second": 1.893,
-      "eval_steps_per_second": 0.241,
-      "step": 656
-    },
-    {
-      "epoch": 3.0,
-      "eval_gen_len": 14.927835051546392,
-      "eval_loss": 0.8221376538276672,
-      "eval_rouge1": 19.5594,
-      "eval_rouge2": 12.7325,
-      "eval_rougeL": 16.4586,
-      "eval_rougeLsum": 16.7605,
-      "eval_runtime": 157.0696,
-      "eval_samples_per_second": 1.853,
-      "eval_steps_per_second": 0.236,
-      "step": 984
-    },
-    {
-      "epoch": 3.05,
-      "learning_rate": 1.1228070175438597e-05,
-      "loss": 1.8759,
-      "step": 1000
-    },
-    {
-      "epoch": 4.0,
-      "eval_gen_len": 14.109965635738831,
-      "eval_loss": 0.7782504558563232,
-      "eval_rouge1": 21.8348,
-      "eval_rouge2": 14.9645,
-      "eval_rougeL": 18.7764,
-      "eval_rougeLsum": 19.0709,
-      "eval_runtime": 155.486,
-      "eval_samples_per_second": 1.872,
-      "eval_steps_per_second": 0.238,
-      "step": 1312
-    },
-    {
-      "epoch": 4.57,
-      "learning_rate": 2.456140350877193e-06,
-      "loss": 0.8715,
-      "step": 1500
-    },
-    {
-      "epoch": 5.0,
-      "eval_gen_len": 13.051546391752577,
-      "eval_loss": 0.766891360282898,
-      "eval_rouge1": 24.6538,
-      "eval_rouge2": 17.821,
-      "eval_rougeL": 21.5884,
-      "eval_rougeLsum": 21.9045,
-      "eval_runtime": 157.0206,
-      "eval_samples_per_second": 1.853,
+      "eval_gen_len": 15.577319587628866,
+      "eval_loss": 8.096635818481445,
+      "eval_rouge1": 16.5418,
+      "eval_rouge2": 10.3523,
+      "eval_rougeL": 13.972,
+      "eval_rougeLsum": 14.1918,
+      "eval_runtime": 157.1024,
+      "eval_samples_per_second": 1.852,
       "eval_steps_per_second": 0.236,
-      "step": 1640
+      "step": 328
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1640,
-  "num_train_epochs": 5,
+  "max_steps": 3936,
+  "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 1.229071090286592e+16,
+  "total_flos": 2458142180573184.0,
   "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:b5c8949174dd9b49837d8ec609d2b880bd4fe35d9d9291ea4e7c0991d5dcd240
+oid sha256:83aee626fbc0f5035f17ef0b0e15a14a8afcb9d45d851b7bf8dc1e10d0cdf477
 size 4728