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:f57c160d2b922a54d88f536012a2d24ac47dbef1acb1f8c8d63487761fb4be25
+oid sha256:e2373407f411bdefcd1c1619d4337dc75c28545aecea714e87ab0192268b19c0
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6238a76200c39daf0fbb9f6649698d4cf14657fb4c51378657eb5dfe22a277e4
+oid sha256:8045b3960c09346b96cc68600f0bdf0804cab1858372d8860af22c20ef37d7a5
 size 323298107

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85af476a78ba5ced6159a0a73d339182472e654d41949a6de3c8a75963047363
+oid sha256:9fd9ac6b4a5aea74e8d8f24c3e96e1af47905735c7dc53e6854b8615703b8ae3
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac969061fcfa6580058d9dd98ea17f8a5629238d68c550370289b84d4767462
+oid sha256:c86ebf50ac9f9127531a301e6ae85c1c8d9423c1122d72f8eafb77301bb870e2
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab8f7fae8c5bc945ba8d0476887328f81726abcc0550ee4572fa2d3eac0adcb
+oid sha256:09b104d11e23c43fff8ed10992448da9d6b5482113779cdd276876818600dad4
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3f4b44496cb1177f3335737fdd4d6fd3a0beda7544091b0e32c12d83e6cc56
+oid sha256:4b2bd53166d581902513a9666139854e88807312a6b89c8ab8f4eaed17fb5e63
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 100,
-  "best_metric": 0.344037264585495,
-  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-100",
-  "epoch": 0.2359882005899705,
+  "best_global_step": 150,
+  "best_metric": 0.32990705966949463,
+  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-150",
+  "epoch": 0.35398230088495575,
   "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": 3.139,
       "eval_steps_per_second": 0.785,
       "step": 100
+    },
+    {
+      "epoch": 0.25958702064896755,
+      "grad_norm": 3.625964403152466,
+      "learning_rate": 1.695853242428357e-05,
+      "loss": 0.2473,
+      "step": 110
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 1.9131460189819336,
+      "learning_rate": 1.6916845061292673e-05,
+      "loss": 0.2083,
+      "step": 120
+    },
+    {
+      "epoch": 0.30678466076696165,
+      "grad_norm": 3.0459189414978027,
+      "learning_rate": 1.6860890501703082e-05,
+      "loss": 0.2358,
+      "step": 130
+    },
+    {
+      "epoch": 0.3303834808259587,
+      "grad_norm": 4.418868541717529,
+      "learning_rate": 1.6790763592776032e-05,
+      "loss": 0.2745,
+      "step": 140
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 2.294529438018799,
+      "learning_rate": 1.670658320498962e-05,
+      "loss": 0.2016,
+      "step": 150
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "eval_loss": 0.32990705966949463,
+      "eval_runtime": 375.8551,
+      "eval_samples_per_second": 3.14,
+      "eval_steps_per_second": 0.785,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -113,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.40043843125248e+16,
+  "total_flos": 3.620038096243917e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null