Training in progress, step 6, 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 sha256:917486b70d5f44a55614b8ed9dbae56d882ce12fa77e74b3188a97599150ac4a
+oid sha256:dffc7c91f2e0f3c9b8cac9bde625c461f6abe144c439357f18c2ba216b302c14
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7feafb3353f1f06b854a718e0947b39032bb46c78f5a3f4cac357fa6bfa44ba6
+oid sha256:4bf8945539674cf888aa52070f472421d589d3fef11606149f89b6d1aae04d10
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe474c19ed55a700df6d0f4840ca2274d4f5b8c39547d46aa2909b1442c2b257
+oid sha256:5eb3140e11f0d5833c00e9f4928bfeb27b734066b93311a0b98886e275b02212
 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

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.449767685045443e-05,
+  "epoch": 8.899535370090886e-05,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "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
@@ -18,32 +18,61 @@
     {
       "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": 1352.6219482421875,
+      "learning_rate": 8e-05,
+      "loss": 93.8438,
+      "step": 4
+    },
+    {
+      "epoch": 7.416279475075739e-05,
+      "grad_norm": 1339.363037109375,
+      "learning_rate": 0.0001,
+      "loss": 95.0979,
+      "step": 5
+    },
+    {
+      "epoch": 8.899535370090886e-05,
+      "grad_norm": 1209.0018310546875,
+      "learning_rate": 0.00012,
+      "loss": 94.5627,
+      "step": 6
+    },
+    {
+      "epoch": 8.899535370090886e-05,
+      "eval_loss": 23.490365982055664,
+      "eval_runtime": 1965.3434,
+      "eval_samples_per_second": 14.444,
+      "eval_steps_per_second": 7.222,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26811870216192.0,
+  "total_flos": 53623740432384.0,
   "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