Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa3be07eedeacfda9abc58590d409a44e4f4c4ff1104f9b848fd0118a9615a74
+oid sha256:6d9c1cefb9a4eba5c37ddb3f1fd9c87aa220ebdd37d6dca8bf44e86197ef0b3f
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b592bf5a7c2a0a85aa8c7bbdc8e36b38577d7fe2fc7bf186f9c7b0963f7c2b
+oid sha256:378c103450b9f57a2150a1883a6da51ed2aa62d726a672f3ad438f5a1186f5fa
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdead6fb89febd0ec3fe4773ba2ee772b5ca6734d6e27d5e4932e94bc72716b
+oid sha256:50dd579ef1d2d932c3d7726ef0f6ec72d0e25b023ae2fd8b67112ac75e1041b9
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f287fe82b0f0f3218f7b83fe119f37c8a549c0dc54dc910ec57007a34567db89
+oid sha256:489c5c7b3eb8c654fb99b2307b26bef5ab573d173ac5583a0472f5ab307ed300
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1511800f0ad6c0ecda5e4471177e91a10ee2e1eb3f224a4914d4495f3524eb
+oid sha256:dd10e570fb10a3dddd222e4af27841df0902397065c880157d50ad88813e460c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.000766666666667,
+  "epoch": 9.001333333333333,
   "eval_steps": 500,
-  "global_step": 19500,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2738,6 +2738,76 @@
       "learning_rate": 8.450448069060103e-06,
       "loss": 0.7119151306152344,
       "step": 19500
+    },
+    {
+      "epoch": 4.0026,
+      "grad_norm": 1.5235882997512817,
+      "learning_rate": 8.378686280868617e-06,
+      "loss": 0.43539573669433596,
+      "step": 19550
+    },
+    {
+      "epoch": 4.004266666666667,
+      "grad_norm": 1.765830397605896,
+      "learning_rate": 8.30711222491678e-06,
+      "loss": 0.4487119674682617,
+      "step": 19600
+    },
+    {
+      "epoch": 4.005933333333333,
+      "grad_norm": 1.503596305847168,
+      "learning_rate": 8.235727930523598e-06,
+      "loss": 0.44962635040283205,
+      "step": 19650
+    },
+    {
+      "epoch": 4.0076,
+      "grad_norm": 1.5412774085998535,
+      "learning_rate": 8.164535421627828e-06,
+      "loss": 0.4337549591064453,
+      "step": 19700
+    },
+    {
+      "epoch": 4.009266666666667,
+      "grad_norm": 1.6753467321395874,
+      "learning_rate": 8.093536716730584e-06,
+      "loss": 0.43847557067871096,
+      "step": 19750
+    },
+    {
+      "epoch": 4.010933333333333,
+      "grad_norm": 1.709405541419983,
+      "learning_rate": 8.022733828838124e-06,
+      "loss": 0.49284374237060546,
+      "step": 19800
+    },
+    {
+      "epoch": 4.0126,
+      "grad_norm": 1.593888759613037,
+      "learning_rate": 7.952128765404746e-06,
+      "loss": 0.46281536102294923,
+      "step": 19850
+    },
+    {
+      "epoch": 4.014266666666667,
+      "grad_norm": 1.4703963994979858,
+      "learning_rate": 7.88172352827589e-06,
+      "loss": 0.6160999298095703,
+      "step": 19900
+    },
+    {
+      "epoch": 4.015933333333333,
+      "grad_norm": 1.6609055995941162,
+      "learning_rate": 7.81152011363138e-06,
+      "loss": 0.6013171768188477,
+      "step": 19950
+    },
+    {
+      "epoch": 5.0015,
+      "grad_norm": 2.0141754150390625,
+      "learning_rate": 7.741520511928819e-06,
+      "loss": 0.6710720825195312,
+      "step": 20000
     }
   ],
   "logging_steps": 50,
@@ -2757,7 +2827,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7155541919780127e+18,
+  "total_flos": 1.7630490710553477e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null