Training in progress, step 60, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9505cbd1c71fa03bd7aa6e5610584fea463e8693b50cfc26ffa5e5d5e8ecb5
+oid sha256:05b9734940ff5efe87c90543759f0d12cd9967fad044ebb0406e0eb71316bbe7
 size 4956450288

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294e49d4e0151ff6ea8c7ae8fd3c7f751742dba5dc1a599b0003c7da1dee4b1d
+oid sha256:a8ed419a66bd781e7f552932fc7e8ee3b8e3b292c614dc3410acfdbe3812666d
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a13208817ea46f3bf98ef16495ccb741166331a2537849f5b45e1362c03504
+oid sha256:06b73db26795537b521c3f2c8271dabfc30ba29138aa577007d8d4b570abc9e8
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50d39405d88591ce6aca8b0b6c85c11b2a2f5ebf7c013d70f25e4f52dc10862
+oid sha256:dbbc0a86104f167e435d82d912099d9f4e8e28814d0b3054a66bc62faad66266
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece10f667957ef7fe2aeebd2123f03c13fd50eecfc57b402ef932838893258f0
+oid sha256:ab9aca62c8968a97eee76d9db5ace24bd5602b66748ad8ebaa3c5beb481c0acd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e6f1c8eecc99beebe49ddacdcfb6d698bb3dc1d6bf171871581f2a9a4940bf9
+oid sha256:4ecef8be965f4a8a3ed32d79c73f9a4a9b6fc06e37821a549724a0a8e8322513
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6933fdb81e79fb8d8cc03a2704a76076a84a3f1eeb0cb38a2be16ab7ccf10ff9
+oid sha256:a0d44c275e240e610f81071dc60b4fd4a20c4c4c06cc32abe80112f3f1a29d61
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9248d7f262b73b7b212e6bf7f6f66a12efea2182db378d6a810b44dc89e3400f
+oid sha256:73474ac15ab1f9e7ff2dbea9beffe9a6867347710a3cf2ee966c6a4a98243bef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0810810810810811,
+  "epoch": 1.6216216216216215,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 70.006,
       "eval_steps_per_second": 3.545,
       "step": 40
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 1.625,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 1.3332,
+      "step": 50
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0001973326597248006,
+      "loss": 1.343,
+      "step": 60
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "eval_loss": 2.093151092529297,
+      "eval_runtime": 22.3251,
+      "eval_samples_per_second": 67.234,
+      "eval_steps_per_second": 3.404,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.727713543343309e+16,
+  "total_flos": 4.091570315014963e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null