Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615b2afd3bc142e08bf251a928f84b4e1cea9ae26762fc89ba0a4736dba7eb66
+oid sha256:5957954f25406e9df797421489d9b120ac7feff52692d5e5c70038c879f86412
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfeca88de39ac397647f995ea8cde7b1fb6e6871fa362fb780526f82a902479
+oid sha256:6ee0d0e9122e67a2d2d94315cf19cbd6a916fcb06556d38abe0ccc77fd7feae8
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb1461e40c7e08171c25a0bc2bf64964397ea8cc712bb88016a59954d83db2d
+oid sha256:dbcbab03d5bb70bb2a3066017b02040dc9b35585ddf112a4be38eb15410f67d9
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2a89a85e1c8ac7ee9b5678d857a4d99090faa37a24489f44839e0801dfe16a
+oid sha256:e9567d76a2efaa946d19913fd9fe6f6f70f6f7101d7dcb8866c09743534f2d4d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.16,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -482,6 +482,164 @@
       "eval_samples_per_second": 83.4,
       "eval_steps_per_second": 0.667,
       "step": 6000
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 0.14931881427764893,
+      "learning_rate": 0.0019718035350990712,
+      "loss": 3.7169,
+      "step": 6100
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.14251381158828735,
+      "learning_rate": 0.0019702227914230566,
+      "loss": 3.6929,
+      "step": 6200
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 0.14251849055290222,
+      "learning_rate": 0.001968599607059059,
+      "loss": 3.7018,
+      "step": 6300
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.15696577727794647,
+      "learning_rate": 0.0019669340530104207,
+      "loss": 3.7034,
+      "step": 6400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.14737001061439514,
+      "learning_rate": 0.001965226202133872,
+      "loss": 3.6889,
+      "step": 6500
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.13667502999305725,
+      "learning_rate": 0.0019634761291363427,
+      "loss": 3.6935,
+      "step": 6600
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 0.13390734791755676,
+      "learning_rate": 0.0019616839105716954,
+      "loss": 3.7032,
+      "step": 6700
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.14834214746952057,
+      "learning_rate": 0.0019598496248373755,
+      "loss": 3.6657,
+      "step": 6800
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 0.1314767599105835,
+      "learning_rate": 0.001957973352170984,
+      "loss": 3.673,
+      "step": 6900
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.15161661803722382,
+      "learning_rate": 0.001956055174646765,
+      "loss": 3.6713,
+      "step": 7000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.3484422700587084,
+      "eval_loss": 3.6349546909332275,
+      "eval_runtime": 12.1265,
+      "eval_samples_per_second": 82.464,
+      "eval_steps_per_second": 0.66,
+      "step": 7000
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 0.12710200250148773,
+      "learning_rate": 0.0019540951761720174,
+      "loss": 3.67,
+      "step": 7100
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.18498213589191437,
+      "learning_rate": 0.0019520934424834247,
+      "loss": 3.675,
+      "step": 7200
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 0.13697299361228943,
+      "learning_rate": 0.0019500500611433025,
+      "loss": 3.6497,
+      "step": 7300
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.13290269672870636,
+      "learning_rate": 0.0019479651215357707,
+      "loss": 3.662,
+      "step": 7400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.12744054198265076,
+      "learning_rate": 0.0019458387148628417,
+      "loss": 3.6645,
+      "step": 7500
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.13697493076324463,
+      "learning_rate": 0.001943670934140432,
+      "loss": 3.6374,
+      "step": 7600
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 0.14067181944847107,
+      "learning_rate": 0.0019414618741942936,
+      "loss": 3.6453,
+      "step": 7700
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.1316055953502655,
+      "learning_rate": 0.0019392116316558638,
+      "loss": 3.6679,
+      "step": 7800
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 0.1261526495218277,
+      "learning_rate": 0.001936920304958042,
+      "loss": 3.6343,
+      "step": 7900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.13644501566886902,
+      "learning_rate": 0.0019345879943308804,
+      "loss": 3.6365,
+      "step": 8000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.35229158512720155,
+      "eval_loss": 3.5980424880981445,
+      "eval_runtime": 17.6098,
+      "eval_samples_per_second": 56.787,
+      "eval_steps_per_second": 0.454,
+      "step": 8000
     }
   ],
   "logging_steps": 100,