Training in progress, step 320, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950a28166b99b03380da725625d682e26376fd823ffdd0f845cebfdd4112813d
+oid sha256:36f4d7f40c1dfe0aa7d2a4231f75acffd5b79eac451b993d900c03c6ce59780c
 size 988097824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3d1feecf8c52cee61ddb95849c19f8bb882b55d08361ff23f8d428046ef45f
+oid sha256:2d5e27fe47302e41aa4c52cfdfbfad74d9a01ea643642284793e240fbc32572f
 size 1004201914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c2c319c7b10ce33dca632aa356a109e5a073cbf472df4317095638a845243c9
+oid sha256:7e82378552851182019f2c32ac7056e72bc481ae56bec95a5072e9bd4898d2ad
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c62a55660a1eb1266b3d1a0ae5b8693ab4bab13aed51b378af525518a65073e
+oid sha256:d2c4d52716d0b15349a19b71270c292451324106dbb42d8a60b878dc962ff5d3
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ce7a81926468993595cb9f4c1a61959231861f3b2a87ab2d3cd8d652546062
+oid sha256:9a0b9ba4048c8e75b028f96a9fdcb748a3661202e3a2650b862287ba2fca6855
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68949b4bf61389a1d66a804854406bb76492ab0cd46b5ae4d2fe1cfe23a0dbe
+oid sha256:bed3a979b774c8cacd490da31053292ae90bad1a76d793f3a7a6fbfd9ed50ddd
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73cad919b6567aec09f5bb0a5f2626e9c42d537188e8d11bc8fc59ef4c7aec4
+oid sha256:e62a31dc4ab1a0f66e3aa2022c8aa7b7e528f30887ac8d363d9c8fe971f0aa17
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0628265fff507b91a810dd0b509b493725c456b0210bd519bd22782de6e59b94
+oid sha256:bd67f44c1b9b11ae3b1ae36097f4ddb763ca3afb82bcf1c555f73f0f036a28c9
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2165c40ba4cb7ed659ea1645c26da4f103c876e80e1871f568c27fa478e7ea
+oid sha256:a9cde9132c6235ff6effcf02af494a1b7895d8c18f7fa29fe7f82368931ab98e
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72378b422c760a245744c395267ff4aad881cbbc24778fad1551ccad564c69d
+oid sha256:b872f40b35a9deed3e8f1cefec7429d733e19916cb7fda73422a385ad32aac93
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a24828cdaa43aab0fc6d70393065a456392f09e6ce498b44708f3b6084ccd6
+oid sha256:b87d3d77c5edb705ca109c194bdd88542b644ea60309ca727331b4859a982237
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.054474708171206226,
+  "epoch": 0.0622568093385214,
   "eval_steps": 20,
-  "global_step": 280,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -323,6 +323,50 @@
       "eval_samples_per_second": 208.094,
       "eval_steps_per_second": 6.514,
       "step": 280
+    },
+    {
+      "epoch": 0.05642023346303502,
+      "grad_norm": 6.78125,
+      "learning_rate": 0.00012418110275386028,
+      "loss": 1.7687,
+      "step": 290
+    },
+    {
+      "epoch": 0.058365758754863814,
+      "grad_norm": 9.875,
+      "learning_rate": 0.00011916220986604296,
+      "loss": 1.7693,
+      "step": 300
+    },
+    {
+      "epoch": 0.058365758754863814,
+      "eval_loss": 1.725274920463562,
+      "eval_runtime": 98.7543,
+      "eval_samples_per_second": 185.045,
+      "eval_steps_per_second": 5.792,
+      "step": 300
+    },
+    {
+      "epoch": 0.06031128404669261,
+      "grad_norm": 7.0625,
+      "learning_rate": 0.00011409266840272685,
+      "loss": 1.7644,
+      "step": 310
+    },
+    {
+      "epoch": 0.0622568093385214,
+      "grad_norm": 5.5,
+      "learning_rate": 0.00010898587791726955,
+      "loss": 1.6371,
+      "step": 320
+    },
+    {
+      "epoch": 0.0622568093385214,
+      "eval_loss": 1.6797202825546265,
+      "eval_runtime": 89.056,
+      "eval_samples_per_second": 205.197,
+      "eval_steps_per_second": 6.423,
+      "step": 320
     }
   ],
   "logging_steps": 10,
@@ -342,7 +386,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.940475298276966e+16,
+  "total_flos": 4.503400340887962e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null