Training in progress, step 80, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b9734940ff5efe87c90543759f0d12cd9967fad044ebb0406e0eb71316bbe7
+oid sha256:748429cdef553d786d832b3cc546d2b44b9a495694a80ba8b3ee4019d6cea887
 size 4956450288

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ed419a66bd781e7f552932fc7e8ee3b8e3b292c614dc3410acfdbe3812666d
+oid sha256:9814eb376b423465c056add6094059acd7377a2fe16892876fc6b780c63da94c
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b73db26795537b521c3f2c8271dabfc30ba29138aa577007d8d4b570abc9e8
+oid sha256:f37e7deaa3edb702c8ad1dee16fb78b488a59140e8d014e398a29ed7bab44af3
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbbc0a86104f167e435d82d912099d9f4e8e28814d0b3054a66bc62faad66266
+oid sha256:43604538982ff9a123e6e380dab2fe2293aae265889999a4f6fade6bc120ab1b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9aca62c8968a97eee76d9db5ace24bd5602b66748ad8ebaa3c5beb481c0acd
+oid sha256:f41810925851712e1a7b810d5012d919f7365fc56c81634abbcbf5935c31817f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecef8be965f4a8a3ed32d79c73f9a4a9b6fc06e37821a549724a0a8e8322513
+oid sha256:dab0c898588cb646bb7e3e0b4e0551e77b1ace237b44529b5d5c68a3cd4d71cd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d44c275e240e610f81071dc60b4fd4a20c4c4c06cc32abe80112f3f1a29d61
+oid sha256:888b119a72374f2350a0b0589d5e49ddac65fba5e8b050ec8203eadf4f2f4839
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73474ac15ab1f9e7ff2dbea9beffe9a6867347710a3cf2ee966c6a4a98243bef
+oid sha256:776a540436bd1dedef12a8b7642374faac449931a1c15952fb54741875421490
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6216216216216215,
+  "epoch": 2.1621621621621623,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 67.234,
       "eval_steps_per_second": 3.404,
       "step": 60
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 1.3674,
+      "step": 70
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0001934564464599461,
+      "loss": 0.9356,
+      "step": 80
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "eval_loss": 2.402878999710083,
+      "eval_runtime": 21.51,
+      "eval_samples_per_second": 69.782,
+      "eval_steps_per_second": 3.533,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.091570315014963e+16,
+  "total_flos": 5.455427086686618e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null