Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48563b44d44362320f067d34ff92f47e2456bde4f2317ee93b23dabf1b45729
+oid sha256:8f094722188717075439138e1e791728eb83dc89ede5725094ba20a9394827cb
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5dc22ec383dbcee021a17c4623070dde01a829463bd7b6d6d98d76a1a52d83
+oid sha256:13798eed199d0e8f7d444eff9af7f40acdebc84529bd74f913cce85929e905b5
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04a9f6de7412b2745ad1e05df32de31ca01887f6c3263f961d3bee484ab3809
+oid sha256:0eaa843a45d8e738cee2ae0531250a101659f24a1b6fb71ecb838949839be942
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e80f5d18253859eb582d273afcfab47d6dbe284f74a1acab6df29c9bd8e3ef5d
+oid sha256:946dbb58346f352ba6907add2b54217151d2cb0118b1f9eb15982ba30ba98cc3
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748ed266e9432323e41e747f49e84d108918da883711ff6e01c8135af1c286fd
+oid sha256:4c62f46b6ecdcc9452fbe00042ae2d6095daf65d97a17c5763e0d0ed253cea52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.23076923076923,
+  "epoch": 23.076923076923077,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 251.904,
       "eval_steps_per_second": 4.028,
       "step": 250
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.400390625,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 9.3153,
+      "step": 260
+    },
+    {
+      "epoch": 20.76923076923077,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 9.2905,
+      "step": 270
+    },
+    {
+      "epoch": 21.53846153846154,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 9.2678,
+      "step": 280
+    },
+    {
+      "epoch": 22.307692307692307,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 9.2496,
+      "step": 290
+    },
+    {
+      "epoch": 23.076923076923077,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 9.2338,
+      "step": 300
+    },
+    {
+      "epoch": 23.076923076923077,
+      "eval_loss": 9.241479873657227,
+      "eval_runtime": 5.2815,
+      "eval_samples_per_second": 284.199,
+      "eval_steps_per_second": 4.544,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -249,7 +292,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 102289637376000.0,
+  "total_flos": 122747564851200.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null