Training in progress, step 480, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fb0b3c74d1ce9cad255087000265c31c25c76f4299532d8b88d85a4441a3e4
+oid sha256:eb2a93906c4f7e25f297087b5d118acb381dc3455c3b0e427daf8b7c1a4a018c
 size 4976698672

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5038c9de904dbea4e32315c794fa2074ecc92c50c8eb6195def7911e593e18d
+oid sha256:7f7c049136f803487282ec0e617d77b627a8998042e2c8af437fc4dc57b6d0d1
 size 4999802720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141f38f7b29ec3541b6db31c4ce70506e88378235faeb8284e0042bdb72ee8f2
+oid sha256:0ff95b7efcfb0d4d8d1e85c4cbdf6f2a5bef8cf96aa5049d319cb25f0110f517
 size 4915916176

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b86685c4b1f23b972380ed4f5d5cb1c2ea00d7ffa8cf4923514704537825099
+oid sha256:efef2c24ea48bab541befd9dc3933f088e89a1139a8f2474997caacf97b805d0
 size 1168138808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa98c4565c961954703f6a0050170f46f8bf17adb206bc140547154f733c23d1
+oid sha256:235123e41bf972e846c0458cbd60ad40fb411d42353e0b61237b9b543f3f24ca
 size 16311821444

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb81452b7889ec50c58e9c6cfe42bd41415f0b599131b3afe2d3e903774fb256
+oid sha256:1bd44ef18b3964269607bf5c6b6357cefe6facd470a29e030d2876d0d88465e6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc08998cd3131e9eceb26f149e13426c0c67832091c26bd1c251b4a9292ec95c
+oid sha256:b1eb1a41635f25b0841e574b17402cb850d5e67c16dbdc4c56b1aeab6b36b6f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11381272633212623,
+  "epoch": 0.12415933781686497,
   "eval_steps": 20,
-  "global_step": 440,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -499,6 +499,50 @@
       "eval_samples_per_second": 8.812,
       "eval_steps_per_second": 4.406,
       "step": 440
+    },
+    {
+      "epoch": 0.11639937920331092,
+      "grad_norm": 12.1875,
+      "learning_rate": 0.00019090065350491626,
+      "loss": 2.6585,
+      "step": 450
+    },
+    {
+      "epoch": 0.11898603207449561,
+      "grad_norm": 16.875,
+      "learning_rate": 0.0001903414081095315,
+      "loss": 3.4396,
+      "step": 460
+    },
+    {
+      "epoch": 0.11898603207449561,
+      "eval_loss": 2.9584171772003174,
+      "eval_runtime": 116.1807,
+      "eval_samples_per_second": 7.402,
+      "eval_steps_per_second": 3.701,
+      "step": 460
+    },
+    {
+      "epoch": 0.12157268494568028,
+      "grad_norm": 25.75,
+      "learning_rate": 0.00018976635558358722,
+      "loss": 2.9627,
+      "step": 470
+    },
+    {
+      "epoch": 0.12415933781686497,
+      "grad_norm": 15.9375,
+      "learning_rate": 0.00018917559654462474,
+      "loss": 2.8675,
+      "step": 480
+    },
+    {
+      "epoch": 0.12415933781686497,
+      "eval_loss": 2.8588883876800537,
+      "eval_runtime": 99.1718,
+      "eval_samples_per_second": 8.672,
+      "eval_steps_per_second": 4.336,
+      "step": 480
     }
   ],
   "logging_steps": 10,
@@ -518,7 +562,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.115405264519168e+16,
+  "total_flos": 8.853169379475456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null