Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14bf7eebdd663b3ea19c21140d09049a942ca2805a3a516c668495cbc89da99d
+oid sha256:7727ddcda81ef4af053f0028ba65de665ef0d03f9b03688d230a65191a2f484c
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa53890b641def633cae2d9fc63c7ef423990e1fb2b0825a66bf6eac654360a9
+oid sha256:3a5f4c788147cbf77121ec6171fbd0b2b46c8555425bc8d1c64d8f02c14682c8
 size 323298107

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7acfecdfbc302e5cfb683c010fb2d33cce2dba28a902ba94b209ca4f49e592af
+oid sha256:a66c2a768f8209fe849e9eba93fe6dc2a0e7b9b72434220c6173918e2206bde6
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed56eb42e65a7e4c00a66c230edb0d550fdfb3482a6cd447834e719d0dc9b35
+oid sha256:f7d06d589659970c843ee8bda33ac65b1103f445a5ebaf1e5d85ca1a884f938f
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40f87368a5d34bd9167ba22f37c5593e2e47132180dfaf5ec6d25e4f0170e1d
+oid sha256:bd41ef3a25cc97fee0fbbd5b42d6f6855cae1ed20b73ba10e4ac2591bfa3c9e3
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88606a1ece45772e81873bd7d0d345f95ef0ba0f0959f30a5f19a783b7b6d5e
+oid sha256:7a15e434a307874a0f7324b4bcce16f24e420fcd331b609bbbc1a5591082bc2c
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 100,
-  "best_metric": 0.7142078876495361,
-  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-100",
-  "epoch": 0.2527646129541864,
+  "best_global_step": 150,
+  "best_metric": 0.6856361031532288,
+  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-150",
+  "epoch": 0.3791469194312796,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,49 @@
       "eval_samples_per_second": 3.404,
       "eval_steps_per_second": 0.852,
       "step": 100
+    },
+    {
+      "epoch": 0.27804107424960506,
+      "grad_norm": 6.488720893859863,
+      "learning_rate": 1.820275277152846e-05,
+      "loss": 0.6861,
+      "step": 110
+    },
+    {
+      "epoch": 0.3033175355450237,
+      "grad_norm": 6.127718448638916,
+      "learning_rate": 1.7666743421972986e-05,
+      "loss": 0.681,
+      "step": 120
+    },
+    {
+      "epoch": 0.3285939968404423,
+      "grad_norm": 5.501866340637207,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.6915,
+      "step": 130
+    },
+    {
+      "epoch": 0.353870458135861,
+      "grad_norm": 5.910053730010986,
+      "learning_rate": 1.6420361773423205e-05,
+      "loss": 0.677,
+      "step": 140
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 6.499867916107178,
+      "learning_rate": 1.571968941195081e-05,
+      "loss": 0.7094,
+      "step": 150
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "eval_loss": 0.6856361031532288,
+      "eval_runtime": 413.5831,
+      "eval_samples_per_second": 3.402,
+      "eval_steps_per_second": 0.851,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -113,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2953173215870976e+16,
+  "total_flos": 3.4537036362809344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null