Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a95a9f8b7fcf070707492d0022f4160abddf649685c62bd0acb0b2191db9f5e
+oid sha256:2439e9d102dd0282d5be625a5206ace7cb88705000d6860c90b7dd6e87479dda
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89b0e30ab40bd6b04823383a4786638df8d21340402e1007a60c2792997f10f
+oid sha256:c7e6893629af82f9fee403650d1001e8491330b5ba33f3da9b1fb841e78e5625
 size 323298107

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a57f5c296f52913583d889b2b838ab564aea78743337131e3f761d182b38830
+oid sha256:d0508ea4bdd39a5b7fea7db06c94302ab81c11bf628134ea211975658de537b4
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260ec53777947eef3f02712019ac0cb83b4c23f3edf0a8e24296a881ab7c1aa6
+oid sha256:465843e6fd6c63a8484074f7251981a985fb35e33f610f0fb99145df1ac998bc
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e56cd39bf95ce68a94b21421aa9b66e0b651c8e26272987fddafbf9f0a90ff
+oid sha256:f3f2fe62185040eb3e7aa577bdc5ab136376cdc8488f5c2c0e5ad1f929361d62
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeaf5d2be120879c36c1f532c4608c5e2ddaf2ba45ca3f2b9987ec0786c20625
+oid sha256:b9a3a7f4dfbdc75f44961641f4d80fe3f960908acd6fd5ff2a8c33e958c30dc5
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 200,
-  "best_metric": 0.3187030255794525,
-  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-200",
-  "epoch": 0.471976401179941,
+  "best_global_step": 250,
+  "best_metric": 0.3116294741630554,
+  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-250",
+  "epoch": 0.5899705014749262,
   "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": 3.138,
       "eval_steps_per_second": 0.785,
       "step": 200
+    },
+    {
+      "epoch": 0.49557522123893805,
+      "grad_norm": 5.596831798553467,
+      "learning_rate": 1.5916002290209964e-05,
+      "loss": 0.2322,
+      "step": 210
+    },
+    {
+      "epoch": 0.5191740412979351,
+      "grad_norm": 2.483771562576294,
+      "learning_rate": 1.5738741478676192e-05,
+      "loss": 0.2322,
+      "step": 220
+    },
+    {
+      "epoch": 0.5427728613569321,
+      "grad_norm": 2.2052314281463623,
+      "learning_rate": 1.5549210446287542e-05,
+      "loss": 0.2337,
+      "step": 230
+    },
+    {
+      "epoch": 0.5663716814159292,
+      "grad_norm": 4.261275768280029,
+      "learning_rate": 1.534773046265049e-05,
+      "loss": 0.2147,
+      "step": 240
+    },
+    {
+      "epoch": 0.5899705014749262,
+      "grad_norm": 2.935073137283325,
+      "learning_rate": 1.5134643051758448e-05,
+      "loss": 0.2523,
+      "step": 250
+    },
+    {
+      "epoch": 0.5899705014749262,
+      "eval_loss": 0.3116294741630554,
+      "eval_runtime": 375.6346,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 0.785,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -199,7 +242,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.822198368652493e+16,
+  "total_flos": 6.021815188271923e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null