Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84dc836f2b1b5602a93d4ee69fd8c515014c68f990cb5b5e3e2933ce7261f375
+oid sha256:6b3ab9d79f758b1cf36da40ebc10dd39505b4af6777d77914431988eb341586d
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eb2e8adf30d386835e0fe366ddc50830c3cd011603a1e85b80ac1a78666237
+oid sha256:5967707ef516c6af5a9a79a6d22a458778bd3f20190646baf46987bd6709bb44
 size 323298107

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668f9990419e35ec4a06821473917599448e847ecb9d6127185dcab3d36b7f09
+oid sha256:b425af18a2a7387f67276e6ad47132c560bca7d6152923030ec10a78ab62cd5a
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfec9b994bc2cde55bb3e0b6edc74b91ca86e618b82d5694d471c1e27aac728
+oid sha256:5579b0608747a8975a2f5367e10db785cf3e460d8ef25d32ac5861d9be1eac1d
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8849200ab201085ca6ed3af3cd6f832415916a84b1e68395125ecc5ecd39e8
+oid sha256:40d357189e199670591cf6d2a70f829467949ed94a3470bf9e28f0ae93fa2a38
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8617759b1b576dfacc91c94650c69557c79f01a12ba9c0dd19758e487759177f
+oid sha256:f15c7a1009fd51f697d26577e887e44ff87ae5a687efd4d9321b568e1dfc643a
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 200,
-  "best_metric": 0.666141152381897,
-  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-200",
-  "epoch": 0.5055292259083728,
+  "best_global_step": 250,
+  "best_metric": 0.652662992477417,
+  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-250",
+  "epoch": 0.631911532385466,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,6 +180,49 @@
       "eval_samples_per_second": 3.402,
       "eval_steps_per_second": 0.851,
       "step": 200
+    },
+    {
+      "epoch": 0.5308056872037915,
+      "grad_norm": 5.043293476104736,
+      "learning_rate": 1.0793388145500199e-05,
+      "loss": 0.6594,
+      "step": 210
+    },
+    {
+      "epoch": 0.5560821484992101,
+      "grad_norm": 5.2453203201293945,
+      "learning_rate": 9.911754160720924e-06,
+      "loss": 0.6347,
+      "step": 220
+    },
+    {
+      "epoch": 0.5813586097946287,
+      "grad_norm": 6.464652061462402,
+      "learning_rate": 9.030806947227607e-06,
+      "loss": 0.6543,
+      "step": 230
+    },
+    {
+      "epoch": 0.6066350710900474,
+      "grad_norm": 5.646970272064209,
+      "learning_rate": 8.157402457160539e-06,
+      "loss": 0.6667,
+      "step": 240
+    },
+    {
+      "epoch": 0.631911532385466,
+      "grad_norm": 5.6440534591674805,
+      "learning_rate": 7.298337941582314e-06,
+      "loss": 0.6349,
+      "step": 250
+    },
+    {
+      "epoch": 0.631911532385466,
+      "eval_loss": 0.652662992477417,
+      "eval_runtime": 413.1161,
+      "eval_samples_per_second": 3.406,
+      "eval_steps_per_second": 0.852,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -199,7 +242,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.598754198316646e+16,
+  "total_flos": 5.75145354681385e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null