Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a6fe2d4b3225fd2a69dde200b394c96d6cf4eca02bc329d2419c8c1466f332
+oid sha256:abdb2545f9019d29f61988b8a09742663e67a63341580409226d2612798d0fc8
 size 335605144

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22d4a12b719d135438b26a2f413193a9867d93caceb92688f5f079f11cfd624
+oid sha256:8ed045fa093c5ae70ae74f492d0e33f9815ab0e226e9c5722e35870555dacb18
 size 671467026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4bb882287d6976c062c089a7686086b15f0601112a612821d81ac9776ae1a44
+oid sha256:1cde1dbeca87b8886d230bcbb3959e729dd182805853193f2cbf0d353f9854d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5106a3d40df1efd273b9eb04f3299504d470352eb1b64d92b1e010e88c8900
+oid sha256:6147aa819d0724d4684abe10cb4115061f11ff38b3b907539ff0d777b30ae06f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.011125968769192696,
   "best_model_checkpoint": "./mistral-magyar-portas-results/checkpoint-2500",
-  "epoch": 2.3510971786833856,
+  "epoch": 2.7429467084639496,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,84 @@
       "eval_samples_per_second": 2.587,
       "eval_steps_per_second": 1.295,
       "step": 3000
+    },
+    {
+      "epoch": 2.3902821316614418,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.073311662395764e-05,
+      "loss": 0.0064,
+      "step": 3050
+    },
+    {
+      "epoch": 2.4294670846394983,
+      "grad_norm": 0.0546875,
+      "learning_rate": 1.8235453705295848e-05,
+      "loss": 0.0063,
+      "step": 3100
+    },
+    {
+      "epoch": 2.468652037617555,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 1.5882931323214713e-05,
+      "loss": 0.0065,
+      "step": 3150
+    },
+    {
+      "epoch": 2.507836990595611,
+      "grad_norm": 0.072265625,
+      "learning_rate": 1.3679725448551451e-05,
+      "loss": 0.0062,
+      "step": 3200
+    },
+    {
+      "epoch": 2.5470219435736676,
+      "grad_norm": 0.078125,
+      "learning_rate": 1.1629746999880697e-05,
+      "loss": 0.0065,
+      "step": 3250
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.0625,
+      "learning_rate": 9.736634901228814e-06,
+      "loss": 0.0064,
+      "step": 3300
+    },
+    {
+      "epoch": 2.6253918495297803,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 8.00374962260706e-06,
+      "loss": 0.0062,
+      "step": 3350
+    },
+    {
+      "epoch": 2.664576802507837,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 6.434167214829267e-06,
+      "loss": 0.0062,
+      "step": 3400
+    },
+    {
+      "epoch": 2.7037617554858935,
+      "grad_norm": 0.251953125,
+      "learning_rate": 5.030673849203082e-06,
+      "loss": 0.007,
+      "step": 3450
+    },
+    {
+      "epoch": 2.7429467084639496,
+      "grad_norm": 0.11572265625,
+      "learning_rate": 3.7957608717875015e-06,
+      "loss": 0.0064,
+      "step": 3500
+    },
+    {
+      "epoch": 2.7429467084639496,
+      "eval_loss": 0.011658398434519768,
+      "eval_runtime": 438.6997,
+      "eval_samples_per_second": 2.587,
+      "eval_steps_per_second": 1.295,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -482,7 +560,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 3.3539015835648e+18,
+  "total_flos": 3.9128851808256e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null