Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "q_proj",
     "k_proj",
-    "o_proj",
-    "down_proj",
     "up_proj",
-    "v_proj"
+    "o_proj",
+    "q_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 sha256:263fd145f9d4a8cc92633f09f4d371ba3c8ea07ba192efe903a1d1388ff141ae
+oid sha256:f0b35f1ad8abedf90a7761e5213c07d8f0840775ede50eb2b838396b70e738f1
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da11275397d1998826f5a00f063dd2f6acf8f2793cbb157f959f32a964e0b5f
+oid sha256:9f62a2dd4e1ba5e22ab327a321b398887f37dbb08db36321fadf0c1311784854
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fae2f082bc2b8a4f93f074fb88d1c6113a4081d21b0babdad2ac6534f83080
+oid sha256:24df05627e2e86925ca37683e21f902381144a8ad40105a0738461c44ce5f2e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.042105263157894736,
+  "epoch": 0.021052631578947368,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004210526315789474,
-      "grad_norm": 1.2002450227737427,
+      "grad_norm": 1.1962615251541138,
       "learning_rate": 2e-05,
       "loss": 1.3218,
       "step": 1
@@ -18,97 +18,46 @@
     {
       "epoch": 0.004210526315789474,
       "eval_loss": 1.2625290155410767,
-      "eval_runtime": 14.4894,
-      "eval_samples_per_second": 6.902,
-      "eval_steps_per_second": 3.451,
+      "eval_runtime": 14.4612,
+      "eval_samples_per_second": 6.915,
+      "eval_steps_per_second": 3.458,
       "step": 1
     },
     {
       "epoch": 0.008421052631578947,
-      "grad_norm": 1.12186598777771,
+      "grad_norm": 1.1140599250793457,
       "learning_rate": 4e-05,
       "loss": 1.3312,
       "step": 2
     },
     {
       "epoch": 0.01263157894736842,
-      "grad_norm": 1.1297404766082764,
+      "grad_norm": 1.1057511568069458,
       "learning_rate": 6e-05,
-      "loss": 1.3092,
+      "loss": 1.3071,
       "step": 3
     },
     {
       "epoch": 0.01263157894736842,
-      "eval_loss": 1.2572206258773804,
-      "eval_runtime": 14.4812,
-      "eval_samples_per_second": 6.906,
-      "eval_steps_per_second": 3.453,
+      "eval_loss": 1.2579314708709717,
+      "eval_runtime": 14.457,
+      "eval_samples_per_second": 6.917,
+      "eval_steps_per_second": 3.459,
       "step": 3
     },
     {
       "epoch": 0.016842105263157894,
-      "grad_norm": 2.104468584060669,
+      "grad_norm": 2.108193874359131,
       "learning_rate": 8e-05,
-      "loss": 1.0379,
+      "loss": 1.04,
       "step": 4
     },
     {
       "epoch": 0.021052631578947368,
-      "grad_norm": 2.024552345275879,
+      "grad_norm": 1.9758830070495605,
       "learning_rate": 0.0001,
-      "loss": 1.2307,
+      "loss": 1.2265,
       "step": 5
-    },
-    {
-      "epoch": 0.02526315789473684,
-      "grad_norm": 1.7949090003967285,
-      "learning_rate": 0.00012,
-      "loss": 1.4991,
-      "step": 6
-    },
-    {
-      "epoch": 0.02526315789473684,
-      "eval_loss": 1.2118092775344849,
-      "eval_runtime": 14.4705,
-      "eval_samples_per_second": 6.911,
-      "eval_steps_per_second": 3.455,
-      "step": 6
-    },
-    {
-      "epoch": 0.029473684210526315,
-      "grad_norm": 1.0950462818145752,
-      "learning_rate": 0.00014,
-      "loss": 1.2985,
-      "step": 7
-    },
-    {
-      "epoch": 0.03368421052631579,
-      "grad_norm": 1.1956337690353394,
-      "learning_rate": 0.00016,
-      "loss": 1.6124,
-      "step": 8
-    },
-    {
-      "epoch": 0.037894736842105266,
-      "grad_norm": 1.4636006355285645,
-      "learning_rate": 0.00018,
-      "loss": 1.2957,
-      "step": 9
-    },
-    {
-      "epoch": 0.037894736842105266,
-      "eval_loss": 1.2200713157653809,
-      "eval_runtime": 14.5087,
-      "eval_samples_per_second": 6.892,
-      "eval_steps_per_second": 3.446,
-      "step": 9
-    },
-    {
-      "epoch": 0.042105263157894736,
-      "grad_norm": 1.0541019439697266,
-      "learning_rate": 0.0002,
-      "loss": 1.4803,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +72,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1935445139128320.0,
+  "total_flos": 967722569564160.0,
   "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:e7a897c74062ad0670db765ef6b2920e10bd22dd8d512079ea68469ca89ea4e6
+oid sha256:4f3fba08eeeb586587427cc2d5f17808d9e4f299ce6f2dc52ed4d0f7fb28b25a
 size 6648