Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "o_proj",
-    "v_proj",
-    "down_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "up_proj"
+    "o_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6d6e0d3f0aea4ef2af090f5f5f26dabd55220a9df6463d0bd7ded58f3488c5
+oid sha256:c360edff80728fafd8cfc09751d999c00b0be881df81017d54ddde2bf224869a
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b1bcbcd35002a18c670a66a3eb2e2d03e38e395a112f56a0e195efc8f298f3
+oid sha256:957cf9cc03cb6f6f33ad0d9ba529ac55ed46a849e31be8980dd4652a4513c48b
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8285489f68000ec4600333ccee281bca8dd48450423899eaa09a26dab85569a3
+oid sha256:27035ea1efd96357598ccd3bea9cecacd80035eaa6d3792153213c56e73abd54
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0332409972299169,
+  "epoch": 0.04986149584487535,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.00554016620498615,
       "eval_loss": 10.876238822937012,
-      "eval_runtime": 1.1366,
-      "eval_samples_per_second": 66.868,
-      "eval_steps_per_second": 33.434,
+      "eval_runtime": 1.1301,
+      "eval_samples_per_second": 67.253,
+      "eval_steps_per_second": 33.627,
       "step": 1
     },
     {
@@ -40,39 +40,68 @@
     {
       "epoch": 0.01662049861495845,
       "eval_loss": 10.876238822937012,
-      "eval_runtime": 1.1359,
-      "eval_samples_per_second": 66.907,
-      "eval_steps_per_second": 33.453,
+      "eval_runtime": 1.0865,
+      "eval_samples_per_second": 69.949,
+      "eval_steps_per_second": 34.975,
       "step": 3
     },
     {
       "epoch": 0.0221606648199446,
-      "grad_norm": 17.855396270751953,
+      "grad_norm": 17.566349029541016,
       "learning_rate": 2e-05,
       "loss": 11.1469,
       "step": 4
     },
     {
       "epoch": 0.027700831024930747,
-      "grad_norm": 17.642831802368164,
+      "grad_norm": 17.940860748291016,
       "learning_rate": 4e-05,
       "loss": 10.8969,
       "step": 5
     },
     {
       "epoch": 0.0332409972299169,
-      "grad_norm": 21.13235855102539,
+      "grad_norm": 20.539535522460938,
       "learning_rate": 6e-05,
-      "loss": 10.8178,
+      "loss": 10.8141,
       "step": 6
     },
     {
       "epoch": 0.0332409972299169,
-      "eval_loss": 10.794831275939941,
-      "eval_runtime": 1.1175,
-      "eval_samples_per_second": 68.007,
-      "eval_steps_per_second": 34.004,
+      "eval_loss": 10.789344787597656,
+      "eval_runtime": 1.1219,
+      "eval_samples_per_second": 67.744,
+      "eval_steps_per_second": 33.872,
       "step": 6
+    },
+    {
+      "epoch": 0.038781163434903045,
+      "grad_norm": 23.39402961730957,
+      "learning_rate": 8e-05,
+      "loss": 10.8841,
+      "step": 7
+    },
+    {
+      "epoch": 0.0443213296398892,
+      "grad_norm": 17.9848690032959,
+      "learning_rate": 0.0001,
+      "loss": 10.4167,
+      "step": 8
+    },
+    {
+      "epoch": 0.04986149584487535,
+      "grad_norm": 16.139219284057617,
+      "learning_rate": 0.00012,
+      "loss": 10.8235,
+      "step": 9
+    },
+    {
+      "epoch": 0.04986149584487535,
+      "eval_loss": 10.459603309631348,
+      "eval_runtime": 1.1553,
+      "eval_samples_per_second": 65.786,
+      "eval_steps_per_second": 32.893,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257942409216.0,
+  "total_flos": 4886913613824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdcc855d0f57473d8bd7ab766a229753c5c71be0fbef544d11bf2fb79cc11ff
+oid sha256:a9bb8d12ab7d3707b6887bbd0a3831cfac8994e15c07c849a86e5da758026626
 size 6712