Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
     "query_key_value",
-    "dense_h_to_4h",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "dense",
+    "dense_h_to_4h"
   ],
   "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 sha256:1483d19dcca2096e96a8bbc7dcd813774e26bf2316711d890249ef2317b67a0a
+oid sha256:d0f9de012dc4a31b7e5e90a158c56f71ca066bea5122355bef8bee314b913fe4
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e3716edcb4a7b14cac52509504cfd791a1695a6bf9cbddb103c8b3a48555974
+oid sha256:3999ae8c49626f50db658437bb9ad4d482733206a6d07fe996bcc1d14e2b741f
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb3140e11f0d5833c00e9f4928bfeb27b734066b93311a0b98886e275b02212
+oid sha256:8fd9a273afce6245b47c12202ac7b282edb77ae2a41fe12118524eef3d6863ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.899535370090886e-05,
+  "epoch": 0.0001334930305513633,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.4832558950151478e-05,
-      "grad_norm": 1032.5780029296875,
+      "grad_norm": 1106.373779296875,
       "learning_rate": 2e-05,
       "loss": 95.6979,
       "step": 1
@@ -18,61 +18,90 @@
     {
       "epoch": 1.4832558950151478e-05,
       "eval_loss": 23.534069061279297,
-      "eval_runtime": 1979.9599,
-      "eval_samples_per_second": 14.337,
-      "eval_steps_per_second": 7.169,
+      "eval_runtime": 1949.8674,
+      "eval_samples_per_second": 14.558,
+      "eval_steps_per_second": 7.279,
       "step": 1
     },
     {
       "epoch": 2.9665117900302956e-05,
-      "grad_norm": 1325.1285400390625,
+      "grad_norm": 1290.805908203125,
       "learning_rate": 4e-05,
       "loss": 96.301,
       "step": 2
     },
     {
       "epoch": 4.449767685045443e-05,
-      "grad_norm": 1420.2266845703125,
+      "grad_norm": 1336.470458984375,
       "learning_rate": 6e-05,
-      "loss": 95.2096,
+      "loss": 94.7096,
       "step": 3
     },
     {
       "epoch": 4.449767685045443e-05,
-      "eval_loss": 23.52667999267578,
-      "eval_runtime": 1953.433,
-      "eval_samples_per_second": 14.532,
-      "eval_steps_per_second": 7.266,
+      "eval_loss": 23.524295806884766,
+      "eval_runtime": 1952.0732,
+      "eval_samples_per_second": 14.542,
+      "eval_steps_per_second": 7.271,
       "step": 3
     },
     {
       "epoch": 5.933023580060591e-05,
-      "grad_norm": 1357.5682373046875,
+      "grad_norm": 1352.6219482421875,
       "learning_rate": 8e-05,
-      "loss": 93.3733,
+      "loss": 93.8438,
       "step": 4
     },
     {
       "epoch": 7.416279475075739e-05,
-      "grad_norm": 1045.089599609375,
+      "grad_norm": 1339.363037109375,
       "learning_rate": 0.0001,
-      "loss": 94.556,
+      "loss": 95.0979,
       "step": 5
     },
     {
       "epoch": 8.899535370090886e-05,
-      "grad_norm": 1248.4478759765625,
+      "grad_norm": 1209.0018310546875,
       "learning_rate": 0.00012,
-      "loss": 94.1798,
+      "loss": 94.5627,
       "step": 6
     },
     {
       "epoch": 8.899535370090886e-05,
-      "eval_loss": 23.505847930908203,
-      "eval_runtime": 2012.6089,
-      "eval_samples_per_second": 14.105,
-      "eval_steps_per_second": 7.053,
+      "eval_loss": 23.490365982055664,
+      "eval_runtime": 1965.3434,
+      "eval_samples_per_second": 14.444,
+      "eval_steps_per_second": 7.222,
       "step": 6
+    },
+    {
+      "epoch": 0.00010382791265106034,
+      "grad_norm": 1945.038330078125,
+      "learning_rate": 0.00014,
+      "loss": 92.7226,
+      "step": 7
+    },
+    {
+      "epoch": 0.00011866047160121182,
+      "grad_norm": 976.50830078125,
+      "learning_rate": 0.00016,
+      "loss": 92.8456,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001334930305513633,
+      "grad_norm": 1855.9024658203125,
+      "learning_rate": 0.00018,
+      "loss": 94.9168,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001334930305513633,
+      "eval_loss": 23.42270278930664,
+      "eval_runtime": 1955.5745,
+      "eval_samples_per_second": 14.516,
+      "eval_steps_per_second": 7.258,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53623740432384.0,
+  "total_flos": 80435610648576.0,
   "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:a5d1a4c4f62778001e2235adc1fcdfcba8e80da1a2496854cc7a72e5b2c2f1ca
+oid sha256:48d86c51d2ca2d99a14e4584b069fa4439ceac2ad5a3d3e4ab990e6fdef6302e
 size 6776