Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7edd57f2fcb36cd9276aa7825e61d4d5b4a28cc64d12dd2cab0f5b0fcf912e59
+oid sha256:02f444cdb66ea4842d2ffe0e2a9e2e651bc9faaab111ce083eadfedccdcd9b37
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b24d7c8d6a08cec2700513e2f47ca76989328c2fae272792b373688930b69685
+oid sha256:b6195721bb1eaffad813d47060edaf5b008f841b67118b6704011e6de9e0ab1b
 size 1113991930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2b170a520baa1ce18377bdacbbdccab7978596a4a772af3bdbdf4cfda617a7
+oid sha256:86b6289f04d8e738d0f6d339f3f40afb49e49d9ff6f957798e92c5b34d22baad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea71ae83c7c7225dab3ad1cd25f7d1e4568afb60e1409ed80a3f2d13fb5dd710
+oid sha256:956f4d9fff765ab8d3a69c2ffeb2c226be5aa26081b4c7d2419d640ea4e52671
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 24.8743,
-  "best_model_checkpoint": "my-model/checkpoint-3056",
-  "epoch": 2.0,
+  "best_metric": 26.0341,
+  "best_model_checkpoint": "my-model/checkpoint-4584",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 3056,
+  "global_step": 4584,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,6 +71,38 @@
       "eval_samples_per_second": 5.068,
       "eval_steps_per_second": 0.508,
       "step": 3056
+    },
+    {
+      "epoch": 2.2905759162303667,
+      "grad_norm": 6.1271209716796875,
+      "learning_rate": 2.136780104712042e-05,
+      "loss": 0.4727,
+      "step": 3500
+    },
+    {
+      "epoch": 2.6178010471204187,
+      "grad_norm": 5.5732316970825195,
+      "learning_rate": 1.7277486910994763e-05,
+      "loss": 0.6959,
+      "step": 4000
+    },
+    {
+      "epoch": 2.945026178010471,
+      "grad_norm": 5.73837423324585,
+      "learning_rate": 1.3187172774869111e-05,
+      "loss": 0.9382,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.44022798538208,
+      "eval_rouge1": 26.0341,
+      "eval_rouge2": 10.6222,
+      "eval_rougeL": 22.7685,
+      "eval_runtime": 417.9997,
+      "eval_samples_per_second": 5.251,
+      "eval_steps_per_second": 0.526,
+      "step": 4584
     }
   ],
   "logging_steps": 500,
@@ -90,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4662889498529792e+16,
+  "total_flos": 2.198245027118285e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null