Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67d8d40ccd059830aa09e47c262874407e5a1f0abf374dec76f8c94925ee01e
+oid sha256:00e86a0299b19346ff15d2fe0fae3dc80394649e1b7bd924d6d84a3b0dc67a49
 size 87361592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf255e7a8b3081904c36115a4363ca1c22d7562c5b86ffa55cba869d161ee585
-size 89256453
+oid sha256:d5e66fdc75dc783c8500339a5622eb420a0bb1a37440cc184551c39bd993e02b
+size 89256965

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57739c021082da51ed2723d3a0065648e8d26fa8bb17a237e8421e7490ec212
+oid sha256:a3041132d027ee07d43a67456dbd178f2f9a31cf6b130d97869dc3cf45899db5
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31f8f4c4585764dcc07488c9354aff14b217f0b6f3a7a53679ab604a0e5622e
+oid sha256:695a90790e7f7bcc6fd389a350feb6a91e68c7bad26131ed75e6cfed010521a8
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": Infinity,
   "best_model_checkpoint": null,
-  "epoch": 0.3048780487804878,
+  "epoch": 0.6097560975609756,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -129,6 +129,117 @@
       "eval_samples_per_second": 2.483,
       "eval_steps_per_second": 1.241,
       "step": 200
+    },
+    {
+      "entropy": 1.209118977189064,
+      "epoch": 0.3353658536585366,
+      "grad_norm": 0.166015625,
+      "learning_rate": 9.521739130434784e-06,
+      "loss": 0.8307,
+      "mean_token_accuracy": 0.7851326018571854,
+      "num_tokens": 6638022.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.2081195436418057,
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.154296875,
+      "learning_rate": 1.0391304347826088e-05,
+      "loss": 0.8054,
+      "mean_token_accuracy": 0.775788264721632,
+      "num_tokens": 7242603.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.218064185231924,
+      "epoch": 0.39634146341463417,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1.1260869565217392e-05,
+      "loss": 0.8023,
+      "mean_token_accuracy": 0.7786701653152704,
+      "num_tokens": 7854134.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.222281923890114,
+      "epoch": 0.4268292682926829,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.2130434782608698e-05,
+      "loss": 0.7419,
+      "mean_token_accuracy": 0.7926970385015011,
+      "num_tokens": 8456300.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.1952788300812245,
+      "epoch": 0.4573170731707317,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.7198,
+      "mean_token_accuracy": 0.800191256031394,
+      "num_tokens": 9058721.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.2105496317148208,
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.228515625,
+      "learning_rate": 1.3869565217391305e-05,
+      "loss": 0.6962,
+      "mean_token_accuracy": 0.8068932801485061,
+      "num_tokens": 9662758.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.2259060773998498,
+      "epoch": 0.5182926829268293,
+      "grad_norm": 0.189453125,
+      "learning_rate": 1.473913043478261e-05,
+      "loss": 0.7312,
+      "mean_token_accuracy": 0.8055971477180719,
+      "num_tokens": 10271738.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.2056082211434842,
+      "epoch": 0.5487804878048781,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.5608695652173914e-05,
+      "loss": 0.6527,
+      "mean_token_accuracy": 0.7986662428826093,
+      "num_tokens": 10879740.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.225981270521879,
+      "epoch": 0.5792682926829268,
+      "grad_norm": 0.259765625,
+      "learning_rate": 1.6478260869565218e-05,
+      "loss": 0.682,
+      "mean_token_accuracy": 0.7959255930036306,
+      "num_tokens": 11483336.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.1928005013614893,
+      "epoch": 0.6097560975609756,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.7347826086956522e-05,
+      "loss": 0.6594,
+      "mean_token_accuracy": 0.8185551591217518,
+      "num_tokens": 12085058.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "eval_entropy": 1.1817513504910724,
+      "eval_loss": NaN,
+      "eval_mean_token_accuracy": 0.806651482590577,
+      "eval_num_tokens": 12085058.0,
+      "eval_runtime": 229.1412,
+      "eval_samples_per_second": 2.453,
+      "eval_steps_per_second": 1.226,
+      "step": 400
     }
   ],
   "logging_steps": 20,
@@ -148,7 +259,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7575034621782016e+17,
+  "total_flos": 5.5195257431906304e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null