Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe01e300f8643a64c61c95d5bd2ad7a24d0656449a61c59adbba0be3df400bb
+oid sha256:18e226bfabb4fe37953d03ddbd4d68cb6331b76339a65c4652c13e68da7c732e
 size 959732416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722396805f72f69e17d77d25f49c1ffd5e62d9bd873d12c24dc1a795814b13a4
+oid sha256:f46b965df64512eadca15157f363bb6b9d956cdb921d1cf19f79f3e3de5b89f3
 size 1915006400

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a021a0be63196a5c519dcf5db6eb93af128af867e8fa23972d45d6a295260aef
+oid sha256:f10ca53587facccfd8ce6c38c8ee3d38f84b1cd52bf1939f663991a4aa3ab223
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a606e680bc86afd847529dd70a95fba19d7ed0518faff7d75b81a55c5474456c
+oid sha256:b6a37679919f879e26f31535286e088a72dcdededa90c5c4ca97536707dfcd97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5155123260103975,
+  "epoch": 3.35401643468053,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -243,6 +243,89 @@
       "learning_rate": 2.4844876739896027e-05,
       "loss": 0.069,
       "step": 15000
+    },
+    {
+      "epoch": 2.599362736877411,
+      "grad_norm": 0.22130186855793,
+      "learning_rate": 2.4006372631225894e-05,
+      "loss": 0.0732,
+      "step": 15500
+    },
+    {
+      "epoch": 2.683213147744424,
+      "grad_norm": 0.7159423828125,
+      "learning_rate": 2.3167868522555762e-05,
+      "loss": 0.0665,
+      "step": 16000
+    },
+    {
+      "epoch": 2.7670635586114374,
+      "grad_norm": 0.7721897959709167,
+      "learning_rate": 2.232936441388563e-05,
+      "loss": 0.065,
+      "step": 16500
+    },
+    {
+      "epoch": 2.8509139694784507,
+      "grad_norm": 0.2992958426475525,
+      "learning_rate": 2.1490860305215497e-05,
+      "loss": 0.0635,
+      "step": 17000
+    },
+    {
+      "epoch": 2.934764380345464,
+      "grad_norm": 0.4838363528251648,
+      "learning_rate": 2.0652356196545364e-05,
+      "loss": 0.0659,
+      "step": 17500
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 100.0,
+      "eval_loss": 0.0834273174405098,
+      "eval_rouge1": 1.8169,
+      "eval_rouge2": 1.2573,
+      "eval_rougeL": 1.8423,
+      "eval_rougeLsum": 1.8571,
+      "eval_runtime": 1629.4126,
+      "eval_samples_per_second": 0.814,
+      "eval_steps_per_second": 0.407,
+      "step": 17889
+    },
+    {
+      "epoch": 3.0186147912124768,
+      "grad_norm": 0.36135250329971313,
+      "learning_rate": 1.9813852087875232e-05,
+      "loss": 0.0577,
+      "step": 18000
+    },
+    {
+      "epoch": 3.10246520207949,
+      "grad_norm": 0.4394136667251587,
+      "learning_rate": 1.89753479792051e-05,
+      "loss": 0.0466,
+      "step": 18500
+    },
+    {
+      "epoch": 3.1863156129465033,
+      "grad_norm": 0.38663652539253235,
+      "learning_rate": 1.8136843870534967e-05,
+      "loss": 0.0488,
+      "step": 19000
+    },
+    {
+      "epoch": 3.2701660238135166,
+      "grad_norm": 0.6833186745643616,
+      "learning_rate": 1.7298339761864835e-05,
+      "loss": 0.0426,
+      "step": 19500
+    },
+    {
+      "epoch": 3.35401643468053,
+      "grad_norm": 0.2934403121471405,
+      "learning_rate": 1.6459835653194702e-05,
+      "loss": 0.0453,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -262,7 +345,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.4135558058216e+18,
+  "total_flos": 7.21801425313176e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null