Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e165614c217b762f552934561d88155cf0e7cc4d5a5298b404fd39e3d22d5e08
+oid sha256:4c2a8d90aa234ac44475d39409dfbfa4fdb26f65d52a62de6861c428091b8ec8
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e911663be690fcc16c588d5b34cf04dda3344d52a411d30cb50207ba0266d71
+oid sha256:e24858682d1d6129b19e305ab6bb61cdca3709f8c6b2b91eaf6b426db53a7515
 size 1113991930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59624509e89bbc9b94c591ed4735982e33caa7e6875690c4ff16d1a97717d87c
+oid sha256:ef2b170a520baa1ce18377bdacbbdccab7978596a4a772af3bdbdf4cfda617a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac9643ef164647dd74d17c68b79347a9f51627588cd7ec3dd1a18bf83f7e68f
+oid sha256:be41d27c52015159c12ea1a39d342a8acabee4a3e8b9b9a41f77607cbb01aef6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6116,
-  "best_model_checkpoint": "my-model/checkpoint-1528",
-  "epoch": 1.0,
+  "best_metric": 3.0744,
+  "best_model_checkpoint": "my-model/checkpoint-3056",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 1528,
+  "global_step": 3056,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -40,6 +40,39 @@
       "eval_samples_per_second": 5.2,
       "eval_steps_per_second": 0.521,
       "step": 1528
+    },
+    {
+      "epoch": 1.3089005235602094,
+      "grad_norm": 3.5784597396850586,
+      "learning_rate": 2.8184991273996508e-05,
+      "loss": 0.0605,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6361256544502618,
+      "grad_norm": 3.948634624481201,
+      "learning_rate": 2.273123909249564e-05,
+      "loss": 0.1013,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9633507853403143,
+      "grad_norm": 5.947019577026367,
+      "learning_rate": 1.7277486910994763e-05,
+      "loss": 0.2594,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.7294816970825195,
+      "eval_rouge1": 3.0744,
+      "eval_rouge2": 0.2582,
+      "eval_rougeL": 3.0319,
+      "eval_rougeLsum": 3.0448,
+      "eval_runtime": 416.9983,
+      "eval_samples_per_second": 5.264,
+      "eval_steps_per_second": 0.528,
+      "step": 3056
     }
   ],
   "logging_steps": 500,
@@ -59,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7327420304523264.0,
+  "total_flos": 1.4662889498529792e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null