Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5115a33042e3fd397dd32d66d32a19c0c16be57ac770db5f8d1d1f33faa5fc9
+oid sha256:2e17770550e37ccffda5d4c371ab23c9caad0cd64689cd3920a328e73f94d70a
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec98cd6c428dfc7f63b47f4b24f7c520934f5445ba14cb6244683725a7da0cd
+oid sha256:85d87bfbeb25a2d5d6903439a58c6c0bf6b0605315d864d3576a4b824d65597b
 size 323298107

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7b75229400998a7d66acd1bde59e0297fb4e980d83e44d61fd3bb4d4fabf86
+oid sha256:463cc4e2c97e8820b6917e788a6c95f26664f4d17ba5035a9615f62c9ee0f832
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acdc4719af55e3178da4e7dfea565c4d31664a72cb7973326a772c14ba81cc93
+oid sha256:e8e50f7b224ddd417ca47967d83455b5a08633364092fdd8a3c00972c467fb5a
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3defd38fd8f62a7a3f6971d154c9135f2e1818e83bbd2a48dbbd5417f2bd284
+oid sha256:f27a079959aa5883ea71dac3ba33abff79e6d154d750da742db42eaf52c70774
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca282f4652e04d966ebc751281f63a231106b830e64c0934d14aac4688fe840
+oid sha256:bc8846b2992a31542db3dae79145db19837cace4fb75fe91f7d7a5ca9416e965
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 450,
   "best_metric": 0.29345282912254333,
   "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-450",
-  "epoch": 1.0613569321533922,
+  "epoch": 1.1793510324483776,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -395,6 +395,49 @@
       "eval_samples_per_second": 3.136,
       "eval_steps_per_second": 0.784,
       "step": 450
+    },
+    {
+      "epoch": 1.0849557522123894,
+      "grad_norm": 2.420490026473999,
+      "learning_rate": 8.762443908332387e-06,
+      "loss": 0.1673,
+      "step": 460
+    },
+    {
+      "epoch": 1.1085545722713865,
+      "grad_norm": 2.7378032207489014,
+      "learning_rate": 8.412506336874943e-06,
+      "loss": 0.1962,
+      "step": 470
+    },
+    {
+      "epoch": 1.1321533923303835,
+      "grad_norm": 3.4118051528930664,
+      "learning_rate": 8.062717073873204e-06,
+      "loss": 0.1875,
+      "step": 480
+    },
+    {
+      "epoch": 1.1557522123893804,
+      "grad_norm": 1.5541094541549683,
+      "learning_rate": 7.713669038900597e-06,
+      "loss": 0.1828,
+      "step": 490
+    },
+    {
+      "epoch": 1.1793510324483776,
+      "grad_norm": 1.0582072734832764,
+      "learning_rate": 7.36595389509231e-06,
+      "loss": 0.1189,
+      "step": 500
+    },
+    {
+      "epoch": 1.1793510324483776,
+      "eval_loss": 0.29354554414749146,
+      "eval_runtime": 375.7093,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 0.785,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -414,7 +457,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0824644623440282e+17,
+  "total_flos": 1.2035561475171942e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null