Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
     "v_proj",
-    "o_proj"
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_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 sha256:8b30bd98f15060ed92abf4158479223f0d73b1e72a5d028f4d7dec78331983ce
+oid sha256:e38fe68111215c4ea0bacd4063ae8bc94b83e0fe5033d4495310c971adf34369
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b50fb9dffe419320cdd4a7b39884e11ef4e9bcbead980fab52298bf9b4fa22
+oid sha256:c4423e02c58000f5b4bcc1b2f8c35a615a80c3f3c8e6d65a735c7dce849fd062
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e82640d554ec21cf908f2cef82fa3879600d0d433c42646fd70b99ce875835
+oid sha256:534ce4aa0bf19f942c8fdb2c560920336f7a9e3abdfd0a3e25924b6b64b9bd8f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a37891a114150222678cdf8ae9c4cd98e3c329c1d0b85be797f4ff77d3594b
+oid sha256:3a4605ae3988d236e50132a8c5a5710439e239440b8e0450b03c26c8c1f78817
 size 14512

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

@@ -1,49 +1,78 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008108108108108109,
+  "epoch": 0.032432432432432434,
   "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": 0.002702702702702703,
-      "grad_norm": 0.22516648471355438,
+      "epoch": 0.005405405405405406,
+      "grad_norm": 0.2000586837530136,
       "learning_rate": 2e-05,
-      "loss": 2.4235,
+      "loss": 2.3204,
       "step": 1
     },
     {
-      "epoch": 0.002702702702702703,
-      "eval_loss": 2.200819492340088,
-      "eval_runtime": 8.0954,
-      "eval_samples_per_second": 9.635,
-      "eval_steps_per_second": 9.635,
+      "epoch": 0.005405405405405406,
+      "eval_loss": 2.2008719444274902,
+      "eval_runtime": 9.7979,
+      "eval_samples_per_second": 7.961,
+      "eval_steps_per_second": 3.98,
       "step": 1
     },
     {
-      "epoch": 0.005405405405405406,
-      "grad_norm": 0.2626628577709198,
+      "epoch": 0.010810810810810811,
+      "grad_norm": 0.17591507732868195,
       "learning_rate": 4e-05,
-      "loss": 2.2166,
+      "loss": 2.6394,
       "step": 2
     },
     {
-      "epoch": 0.008108108108108109,
-      "grad_norm": 0.21446576714515686,
+      "epoch": 0.016216216216216217,
+      "grad_norm": 0.19049879908561707,
       "learning_rate": 6e-05,
-      "loss": 2.6546,
+      "loss": 2.2241,
       "step": 3
     },
     {
-      "epoch": 0.008108108108108109,
-      "eval_loss": 2.199615955352783,
-      "eval_runtime": 8.2871,
-      "eval_samples_per_second": 9.412,
-      "eval_steps_per_second": 9.412,
+      "epoch": 0.016216216216216217,
+      "eval_loss": 2.1992404460906982,
+      "eval_runtime": 9.8906,
+      "eval_samples_per_second": 7.886,
+      "eval_steps_per_second": 3.943,
       "step": 3
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 0.21317099034786224,
+      "learning_rate": 8e-05,
+      "loss": 2.0634,
+      "step": 4
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 0.16591224074363708,
+      "learning_rate": 0.0001,
+      "loss": 2.2234,
+      "step": 5
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "grad_norm": 0.22719058394432068,
+      "learning_rate": 0.00012,
+      "loss": 2.4093,
+      "step": 6
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "eval_loss": 2.1915857791900635,
+      "eval_runtime": 9.9284,
+      "eval_samples_per_second": 7.856,
+      "eval_steps_per_second": 3.928,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1017260336480256.0,
+  "total_flos": 4161519642214400.0,
   "train_batch_size": 1,
   "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:d5b80978b6cdcc9339ecc7931db757328a1ca9deca5507d6af70e88c187855a9
+oid sha256:46bccd6964f4291101ddc4731a06bfcf4544fcbb608a5a0128bc2068c8364f7b
 size 6776