Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
+    "query_key_value",
     "dense",
     "dense_4h_to_h",
-    "query_key_value"
+    "dense_h_to_4h"
   ],
   "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 sha256:7454f33ee6fea44d31e59b443e34ae161b1772b4a53617e2fb375f5b224e5152
+oid sha256:3121f7dff93404f964b38f8e2c7ea3d3eb93db306357d4254118ed0f3f5d852d
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9f791685c5219a22390a5dc22871394dfdf2f1a382febaf510212b69835b35
+oid sha256:1c278a57ae5a779753e99b13c600fc354a60765232cf996b228182997fad9a88
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b367b3e9d37cf71573bf88c375c76ae6cfcee3c2fe025f9a39fc33da8562fc
+oid sha256:19e49dc0c844aa951832d7a63efb8642f706a1446e0152e18ee6d0ed486fe4f0
 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": 0.002489110143123833,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03235843186060983,
+  "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": 0.002489110143123833,
       "eval_loss": 0.8763667345046997,
-      "eval_runtime": 47.0155,
-      "eval_samples_per_second": 3.616,
-      "eval_steps_per_second": 1.808,
+      "eval_runtime": 46.8857,
+      "eval_samples_per_second": 3.626,
+      "eval_steps_per_second": 1.813,
       "step": 1
+    },
+    {
+      "epoch": 0.012445550715619166,
+      "grad_norm": 1.0315775871276855,
+      "learning_rate": 5e-05,
+      "loss": 3.4604,
+      "step": 5
+    },
+    {
+      "epoch": 0.024891101431238332,
+      "grad_norm": 1.3416284322738647,
+      "learning_rate": 0.0001,
+      "loss": 3.4396,
+      "step": 10
+    },
+    {
+      "epoch": 0.024891101431238332,
+      "eval_loss": 0.8357529640197754,
+      "eval_runtime": 49.2871,
+      "eval_samples_per_second": 3.449,
+      "eval_steps_per_second": 1.725,
+      "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": 570561071677440.0,
+  "total_flos": 7417293931806720.0,
   "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 sha256:5d82ec646e2cd42a6e275962652a43a35287e0a1e2ae37d006c840b45f009357
+oid sha256:9369c03ff61c6305dc99a3d35aee86fecfd0a0d977e59dfb91aae848e6d2d712
 size 6776