Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd46c74284ba73b1189e2b45420e99399bb6205659df2d2c1b122e35dda7736f
+oid sha256:7edd57f2fcb36cd9276aa7825e61d4d5b4a28cc64d12dd2cab0f5b0fcf912e59
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79564fb6cc7e990450c02dc917f0c75912df3a4125a5bac3ef68dfb81133c309
+oid sha256:b24d7c8d6a08cec2700513e2f47ca76989328c2fae272792b373688930b69685
 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 sha256:55dc22eb808a1fd1052bfc779bf751672ec8d853af74b32b8aa1627bdf5827cf
+oid sha256:ea71ae83c7c7225dab3ad1cd25f7d1e4568afb60e1409ed80a3f2d13fb5dd710
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 24.8013,
-  "best_model_checkpoint": "my-model/checkpoint-1528",
-  "epoch": 1.0,
+  "best_metric": 24.8743,
+  "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,
@@ -39,6 +39,38 @@
       "eval_samples_per_second": 5.049,
       "eval_steps_per_second": 0.506,
       "step": 1528
+    },
+    {
+      "epoch": 1.3089005235602094,
+      "grad_norm": 3.42366361618042,
+      "learning_rate": 3.3638743455497386e-05,
+      "loss": 0.0539,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6361256544502618,
+      "grad_norm": 3.776289701461792,
+      "learning_rate": 2.954842931937173e-05,
+      "loss": 0.0727,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9633507853403143,
+      "grad_norm": 5.072182655334473,
+      "learning_rate": 2.545811518324607e-05,
+      "loss": 0.1352,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.219298839569092,
+      "eval_rouge1": 24.8743,
+      "eval_rouge2": 9.8439,
+      "eval_rougeL": 21.6411,
+      "eval_runtime": 433.0859,
+      "eval_samples_per_second": 5.068,
+      "eval_steps_per_second": 0.508,
+      "step": 3056
     }
   ],
   "logging_steps": 500,
@@ -58,7 +90,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7327420304523264.0,
+  "total_flos": 1.4662889498529792e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null