Upload checkpoint-600

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2471ba3abe3d3fa5eab5d1ec36a5139ec3204056d368c04a27e7b764540983
+oid sha256:7c0eb8256abd61f22bcffbcec610d3c210e32ec6939a01419fa52e72abc831c3
 size 4966315264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ed888f60f8c8b74a774618c12d20ab334d9e71673855e95692aa9fda355ca2
+oid sha256:61bb1d2426ffeffdb7b41bb9f8ad70de7b954c8d105546b657b0ecd82e90e083
 size 1183919744

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadc2e24275e7bf4c4229d8b1707a21d7ae592cb695965691eb66374fcef8d92
+oid sha256:da32da7f2111b60955ad152993e4e09f5ff9ef40ee4fc472e1a78a637e27a28b
 size 12300683155

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7
+oid sha256:236304ae89e49aae8260113165ee63419b9b745f79120014328a7fa31ed79b42
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72544eaaaca4b1790853dfcc172732f6c7f2ccdcf51bea7b6ec949c193251661
+oid sha256:23756909803a9fdd0e1e0f7083cd1a77d433834eb7dafbf07ba536044bccc4fc
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 550,
-  "best_metric": 3.166327953338623,
-  "best_model_checkpoint": "KBayoud/SmolLM3-3B-bs-16-lr-0.0001-ep-2-wp-0.1-gacc-32-gnm-1.0-FP16-mx-2048-v0.1/checkpoint-550",
-  "epoch": 0.08961622868432174,
+  "best_global_step": 600,
+  "best_metric": 3.139875650405884,
+  "best_model_checkpoint": "KBayoud/SmolLM3-3B-bs-16-lr-0.0001-ep-2-wp-0.1-gacc-32-gnm-1.0-FP16-mx-2048-v0.1/checkpoint-600",
+  "epoch": 0.09776315856471463,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -481,6 +481,49 @@
       "eval_samples_per_second": 13.051,
       "eval_steps_per_second": 0.816,
       "step": 550
+    },
+    {
+      "epoch": 0.09124561466040032,
+      "grad_norm": 2.625,
+      "learning_rate": 4.5521172638436485e-05,
+      "loss": 2.9931,
+      "step": 560
+    },
+    {
+      "epoch": 0.0928750006364789,
+      "grad_norm": 2.859375,
+      "learning_rate": 4.633550488599348e-05,
+      "loss": 3.0269,
+      "step": 570
+    },
+    {
+      "epoch": 0.09450438661255747,
+      "grad_norm": 2.53125,
+      "learning_rate": 4.714983713355049e-05,
+      "loss": 3.0161,
+      "step": 580
+    },
+    {
+      "epoch": 0.09613377258863605,
+      "grad_norm": 2.453125,
+      "learning_rate": 4.796416938110749e-05,
+      "loss": 2.9851,
+      "step": 590
+    },
+    {
+      "epoch": 0.09776315856471463,
+      "grad_norm": 2.6875,
+      "learning_rate": 4.8778501628664496e-05,
+      "loss": 2.9918,
+      "step": 600
+    },
+    {
+      "epoch": 0.09776315856471463,
+      "eval_loss": 3.139875650405884,
+      "eval_runtime": 59897.1239,
+      "eval_samples_per_second": 13.115,
+      "eval_steps_per_second": 0.82,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -500,7 +543,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.731854941605069e+18,
+  "total_flos": 1.061656902720553e+19,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null