Training in progress, step 100, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c9311f17b632d216095e4d5931d56cdc53c3d92ceddbd43f832361e3ba80e7
+oid sha256:64b37deaf920b8381eae0d06baae22833fc0e96251982c087dec65923b1cd311
 size 4995335576

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a811774024d37ebfd9d0599b034618ce7f1ae85b999eafcf1e61c3f77ff84ae9
+oid sha256:84a836ea05e357969d2a141cccec6cd7ec6671771b2b33afcba2fc08fd5428b6
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33399416f26c080a1123dec2edfb2bdc08a4a6fca6afe747e35009ede5e0f35
+oid sha256:826f026c2db75df00591e6c8cdcb55abd295cfab875bad1a85bc7c261e4b4cc4
 size 6961290854

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f845cccc365f42082caa7da8e604f0c659004980fe3b3663dcc7e14c2ca04bce
+oid sha256:d2f73e2ab92ed2314dc8e34e2c9a86c2bd8f2a48f49f9ce7c42ffccc444e0e9b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc2365c0dcf059a80feab8740ee48b0ab99d23a36a4fcdd0867be4b5ceb6e9e
+oid sha256:edab11ab9164a8c1e91fde82983060d22f74114a0388c4e5f7d1919ae5183d3e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfa48462bc67143df2cd639a35fe858a2249d5fc29a8dbef955d03c6c86c4f8
+oid sha256:1676d02a11ee5a81cb4b9811d1ee8050a6fd51250ad90acc01ba9a7d1ea1295e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b88a2d1f28d47a4c4e8ea38eec6b15121f358a10dad34451756b36840a679ec
+oid sha256:477127038fa627ccd8cc28b1e1e3eafd4f5ab2572d0d466ae60a5f66ea0ea5f6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5258a10d326b43bb322f9f7412c08a5d462c4dd53d2018b15d95caea3824d34f
+oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 2.5,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 106.194,
       "eval_steps_per_second": 5.377,
       "step": 80
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.80078125,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 0.4202,
+      "step": 90
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.86328125,
+      "learning_rate": 0.00019264940672148018,
+      "loss": 0.4238,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.4824252128601074,
+      "eval_runtime": 14.1808,
+      "eval_samples_per_second": 105.847,
+      "eval_steps_per_second": 5.359,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.514971359418778e+16,
+  "total_flos": 8.14881997586432e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null