Training in progress, step 520, checkpoint

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2a93906c4f7e25f297087b5d118acb381dc3455c3b0e427daf8b7c1a4a018c
+oid sha256:dc81f761cfc8bdce5d4645d596275ebae46f5b388451e19e4c8d7151b84c9715
 size 4976698672

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7c049136f803487282ec0e617d77b627a8998042e2c8af437fc4dc57b6d0d1
+oid sha256:e7da038dd672630df7e600441c36fa83e824a9e2fb99b73b2420909cbb2ad6eb
 size 4999802720

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff95b7efcfb0d4d8d1e85c4cbdf6f2a5bef8cf96aa5049d319cb25f0110f517
+oid sha256:92e5d26c381151ab0de50104b9e5ce82eabe494b836bd9ed820acb0c36701679
 size 4915916176

last-checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efef2c24ea48bab541befd9dc3933f088e89a1139a8f2474997caacf97b805d0
+oid sha256:8a091b0c39bd9b27ef31e5a41bbc9472016dcf757f5df52524848568afc94178
 size 1168138808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235123e41bf972e846c0458cbd60ad40fb411d42353e0b61237b9b543f3f24ca
+oid sha256:d1e282f5d03b3ef029829e361590621b745fcf0f26c09b36123475b88e1779ed
 size 16311821444

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd44ef18b3964269607bf5c6b6357cefe6facd470a29e030d2876d0d88465e6
+oid sha256:631bcc7b2b54adc0f8c13ccb364aeb8eebda651c6ce4485857a6aba1f8d727b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1eb1a41635f25b0841e574b17402cb850d5e67c16dbdc4c56b1aeab6b36b6f8
+oid sha256:3e6669863251bb7520c41ff8dcf5a27af1ba81a55e01b68c96831c6305cf7b27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12415933781686497,
+  "epoch": 0.13450594930160373,
   "eval_steps": 20,
-  "global_step": 480,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -543,6 +543,50 @@
       "eval_samples_per_second": 8.672,
       "eval_steps_per_second": 4.336,
       "step": 480
+    },
+    {
+      "epoch": 0.12674599068804968,
+      "grad_norm": 16.125,
+      "learning_rate": 0.00018856923435837022,
+      "loss": 2.8926,
+      "step": 490
+    },
+    {
+      "epoch": 0.12933264355923435,
+      "grad_norm": 19.875,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 2.6167,
+      "step": 500
+    },
+    {
+      "epoch": 0.12933264355923435,
+      "eval_loss": 3.3905065059661865,
+      "eval_runtime": 107.7161,
+      "eval_samples_per_second": 7.984,
+      "eval_steps_per_second": 3.992,
+      "step": 500
+    },
+    {
+      "epoch": 0.13191929643041903,
+      "grad_norm": 26.125,
+      "learning_rate": 0.00018731012763882133,
+      "loss": 3.4937,
+      "step": 510
+    },
+    {
+      "epoch": 0.13450594930160373,
+      "grad_norm": 14.9375,
+      "learning_rate": 0.00018665760341274505,
+      "loss": 3.0402,
+      "step": 520
+    },
+    {
+      "epoch": 0.13450594930160373,
+      "eval_loss": 2.930636167526245,
+      "eval_runtime": 97.9968,
+      "eval_samples_per_second": 8.776,
+      "eval_steps_per_second": 4.388,
+      "step": 520
     }
   ],
   "logging_steps": 10,
@@ -562,7 +606,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.853169379475456e+16,
+  "total_flos": 9.590933494431744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null