Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7a9efb55a7cc3b4432f226863fe6ef1c9292f3ad0f7c0ca92fab5349a572f5
+oid sha256:8760cf4fd71ffe55ac2b4376681bd1ece98f92647b8a0d7884a6bdb84448e4ac
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4464c4cbdf59560aaae68cbe3fba5acc3e81f456f12b51fda7e20de6eb07052a
+oid sha256:80a5647b5f60dde4cc65574d3b50f39a981867a2f21becb1ebd54b5014687f04
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a7a87e66fdab18edc7df0621c2a005fd54541ab1c68bc3e038e8b969d2fabe
+oid sha256:9bb1461e40c7e08171c25a0bc2bf64964397ea8cc712bb88016a59954d83db2d
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cf98a8cde877f1e49a9e4b884c4dce3d51bb4035429d464e74acc35ddca024
+oid sha256:eb2a89a85e1c8ac7ee9b5678d857a4d99090faa37a24489f44839e0801dfe16a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.12,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 81.117,
       "eval_steps_per_second": 0.649,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.1560104936361313,
+      "learning_rate": 0.0019944130517800893,
+      "loss": 3.8258,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.15086719393730164,
+      "learning_rate": 0.001993693153591457,
+      "loss": 3.8246,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.1565793752670288,
+      "learning_rate": 0.0019929297880451674,
+      "loss": 3.8036,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.16023847460746765,
+      "learning_rate": 0.0019921229885333023,
+      "loss": 3.7936,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16122952103614807,
+      "learning_rate": 0.001991272790347886,
+      "loss": 3.8071,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.1704457700252533,
+      "learning_rate": 0.0019903792306793415,
+      "loss": 3.7761,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.14904244244098663,
+      "learning_rate": 0.001989442348614863,
+      "loss": 3.7839,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.15502023696899414,
+      "learning_rate": 0.0019884621851367075,
+      "loss": 3.7759,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.14749225974082947,
+      "learning_rate": 0.001987438783120401,
+      "loss": 3.7718,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.15654946863651276,
+      "learning_rate": 0.001986372187332862,
+      "loss": 3.7804,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.3406477495107632,
+      "eval_loss": 3.7244012355804443,
+      "eval_runtime": 12.2821,
+      "eval_samples_per_second": 81.419,
+      "eval_steps_per_second": 0.651,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 0.15231221914291382,
+      "learning_rate": 0.0019852624444304467,
+      "loss": 3.7449,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.15843184292316437,
+      "learning_rate": 0.0019841096029569044,
+      "loss": 3.7559,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.14371678233146667,
+      "learning_rate": 0.0019829137133412556,
+      "loss": 3.7536,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.1501024067401886,
+      "learning_rate": 0.001981674827895587,
+      "loss": 3.7346,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.1276807337999344,
+      "learning_rate": 0.00198039300081276,
+      "loss": 3.7387,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.13706138730049133,
+      "learning_rate": 0.0019790682881640448,
+      "loss": 3.738,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.14035683870315552,
+      "learning_rate": 0.001977700747896664,
+      "loss": 3.7224,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.1608739197254181,
+      "learning_rate": 0.001976290439831259,
+      "loss": 3.7252,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 0.130873903632164,
+      "learning_rate": 0.0019748374256592736,
+      "loss": 3.7179,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.13922768831253052,
+      "learning_rate": 0.0019733417689402543,
+      "loss": 3.712,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.3451976516634051,
+      "eval_loss": 3.6720173358917236,
+      "eval_runtime": 12.3084,
+      "eval_samples_per_second": 81.245,
+      "eval_steps_per_second": 0.65,
+      "step": 6000
     }
   ],
   "logging_steps": 100,