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:d6eee27d7a2421267eecc52386b4fb20ed08f8a0363c316ecc298f565211fb75
+oid sha256:3386ec02a2b7bea6bb19aa3b89f772a86e795a71c25462c254873c98dc5991a9
 size 4956450288

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8860418c1961ee50f013b520aa96456f4c7534137e321c8e16e82137e11b6880
+oid sha256:f304b73b211aed60cee3cd459d8169a0ea8306471c835da5c77aca97fd7e3487
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb115d56ce4ddf08c92865867ec77ec79c8963d90f995f079a3f6edb6359e3e
+oid sha256:fdfc360c5c6478a49ef469cbdcc65c4cc3252aa510215bd39da1cb8897899ab6
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43604538982ff9a123e6e380dab2fe2293aae265889999a4f6fade6bc120ab1b
+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:f41810925851712e1a7b810d5012d919f7365fc56c81634abbcbf5935c31817f
+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:dab0c898588cb646bb7e3e0b4e0551e77b1ace237b44529b5d5c68a3cd4d71cd
+oid sha256:1676d02a11ee5a81cb4b9811d1ee8050a6fd51250ad90acc01ba9a7d1ea1295e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888b119a72374f2350a0b0589d5e49ddac65fba5e8b050ec8203eadf4f2f4839
+oid sha256:477127038fa627ccd8cc28b1e1e3eafd4f5ab2572d0d466ae60a5f66ea0ea5f6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776a540436bd1dedef12a8b7642374faac449931a1c15952fb54741875421490
+oid sha256:898092e0bf0f6dbc7c89ddc78136fe76ce924561e71751216da91be467d8b5d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1621621621621623,
+  "epoch": 2.7027027027027026,
   "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": 68.357,
       "eval_steps_per_second": 3.461,
       "step": 80
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00019090065350491626,
+      "loss": 0.5299,
+      "step": 90
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 1.6328125,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.5366,
+      "step": 100
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "eval_loss": 2.5047948360443115,
+      "eval_runtime": 21.3568,
+      "eval_samples_per_second": 70.282,
+      "eval_steps_per_second": 3.559,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.455427086686618e+16,
+  "total_flos": 6.819283858358272e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null