Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "gate_proj",
     "o_proj",
+    "q_proj",
+    "v_proj",
     "down_proj",
     "k_proj",
     "up_proj"

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dda7d02d4dc12d4ca048f065b33cf2612049e7d4355471bc6fbc0155c314b67
+oid sha256:515f2e4f7d85cf7cd6835ca320ad6ddf7d8b6ae4969c9cd0cf77ec639532fdc0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e19f9820f6fe23136c90d7e4814a4b6891ee7c28d8f8eefd4d1813a139663f
+oid sha256:d099abbb36a243f4369b8eae48cb16c97b847c98449104bd100ad8a41bf6dda4
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638af6f593094a558f5283bf1669c955a044e33851610e2150ab691bd43844c0
+oid sha256:7d41e780f6f8db2d84292a4579c83fc105cfc0f4ebc331ae11cd9a51338da323
 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": 0.00020930354246245618,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0027209460520119305,
+  "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": 0.00020930354246245618,
       "eval_loss": 1.8958899974822998,
-      "eval_runtime": 207.8474,
-      "eval_samples_per_second": 9.68,
-      "eval_steps_per_second": 4.84,
+      "eval_runtime": 207.7108,
+      "eval_samples_per_second": 9.687,
+      "eval_steps_per_second": 4.843,
       "step": 1
+    },
+    {
+      "epoch": 0.0010465177123122808,
+      "grad_norm": 0.45888450741767883,
+      "learning_rate": 5e-05,
+      "loss": 1.9233,
+      "step": 5
+    },
+    {
+      "epoch": 0.0020930354246245617,
+      "grad_norm": 0.573957085609436,
+      "learning_rate": 0.0001,
+      "loss": 1.8975,
+      "step": 10
+    },
+    {
+      "epoch": 0.0020930354246245617,
+      "eval_loss": 1.7665126323699951,
+      "eval_runtime": 208.423,
+      "eval_samples_per_second": 9.653,
+      "eval_steps_per_second": 4.827,
+      "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": 288369011589120.0,
+  "total_flos": 4119557308416000.0,
   "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 sha256:792aac31c917eabb0eacde19c9ba2fc1d4ebf930fd71262a227ed956e906e343
+oid sha256:e0884f7841970e5d206b57f7b66d995dd296645d51a08a941ff57414b0921702
 size 6776