Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "k_proj",
     "o_proj",
-    "q_proj",
-    "v_proj",
     "gate_proj",
     "up_proj",
-    "down_proj"
+    "down_proj",
+    "v_proj",
+    "q_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 sha256:1a09f46db3f40cf49c73a4577a9df5e551abe4875fcfb87d518f62770e36d859
+oid sha256:f419290ce554dfd97cad9342e0c4958138ba78e34b1f7cd2b46e584b39bc671a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a6355cfa4c80ee20366ae507e590fd39b5a1b4bcdea658d95360b2482b6b9d
+oid sha256:2588b164845f367ad8a9e2f3565ebf62aef372d96030d414b86de82714c9b5e2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:3dfaa76e23b5ee2e9cd9f372437b6e2eeffe609e58ae8d131d3303166f82dc47
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.711258730551335e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0006124636349716736,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 4.711258730551335e-05,
       "eval_loss": 2.255336046218872,
-      "eval_runtime": 663.6577,
-      "eval_samples_per_second": 13.468,
-      "eval_steps_per_second": 6.734,
+      "eval_runtime": 666.5702,
+      "eval_samples_per_second": 13.409,
+      "eval_steps_per_second": 6.704,
       "step": 1
+    },
+    {
+      "epoch": 0.00023556293652756677,
+      "grad_norm": 1.0586025714874268,
+      "learning_rate": 5e-05,
+      "loss": 2.1781,
+      "step": 5
+    },
+    {
+      "epoch": 0.00047112587305513353,
+      "grad_norm": 1.62703537940979,
+      "learning_rate": 0.0001,
+      "loss": 2.082,
+      "step": 10
+    },
+    {
+      "epoch": 0.00047112587305513353,
+      "eval_loss": 2.0847971439361572,
+      "eval_runtime": 667.4768,
+      "eval_samples_per_second": 13.391,
+      "eval_steps_per_second": 6.695,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 184956424814592.0,
+  "total_flos": 2589389947404288.0,
   "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 sha256:49ae5f768428893369afcbdb3c59add7b2725598e6ad74dd699a5bd1034725c8
+oid sha256:61332e230c62cc6317f3f74e42211c104ff6ecbf093db6a265caf18fb0861ec5
 size 6776