Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense",
     "dense_4h_to_h",
-    "dense_h_to_4h"
+    "dense",
+    "dense_h_to_4h",
+    "query_key_value"
   ],
   "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 sha256:4e659e8f96d4534638d9c8f118183eb4994604e4593b8d1e4b41c3ee6d38b3ab
+oid sha256:82a654e96b010c3a2be8169c1e857fbca22ea205df98b7cebebf100e69e9eb78
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9e9a3d0d7b948f62a5472cccedc01bdb6542d59354c1112a0e38ec47e3c59a
+oid sha256:7380ff77765287018df367aea82c2bfe9e21ec456241470c1a0ed37e318222e5
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290cd5970960df539004a3f4f2a74cc24e581c07b91f0ff8a5c0aa5cbea47a81
+oid sha256:3ce221d53a442117f9147149ec42c8fa0ba9579c6b7df054d39c79e8298d258c
 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": 0.0018700327255726976,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02431042543244507,
+  "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": 0.0018700327255726976,
       "eval_loss": 8.971555709838867,
-      "eval_runtime": 1.7056,
-      "eval_samples_per_second": 132.502,
-      "eval_steps_per_second": 66.251,
+      "eval_runtime": 1.7009,
+      "eval_samples_per_second": 132.868,
+      "eval_steps_per_second": 66.434,
       "step": 1
+    },
+    {
+      "epoch": 0.009350163627863487,
+      "grad_norm": 4966.99365234375,
+      "learning_rate": 5e-05,
+      "loss": 36.5428,
+      "step": 5
+    },
+    {
+      "epoch": 0.018700327255726974,
+      "grad_norm": 5415.12353515625,
+      "learning_rate": 0.0001,
+      "loss": 36.8309,
+      "step": 10
+    },
+    {
+      "epoch": 0.018700327255726974,
+      "eval_loss": 8.972297668457031,
+      "eval_runtime": 1.3627,
+      "eval_samples_per_second": 165.841,
+      "eval_steps_per_second": 82.921,
+      "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": 189901307904.0,
+  "total_flos": 2468717002752.0,
   "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:a0677aef8369aed455f3290a15482bfde76a105b2651cf48b8348da72dfeb79a
+oid sha256:60b84c78f04d65b61611c0cc62a8b1e38afe5307ce529e617ed51630eff1759b
 size 6776