Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
     "q_proj",
-    "o_proj",
+    "gate_proj",
     "v_proj",
+    "k_proj",
+    "o_proj",
     "down_proj",
     "up_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bffc59bef4f50458fc27c4a0d43812fc75cc21b133c530ca1f41f8fb0a41323
+oid sha256:84053879b7577cb26994e1ec713b37c6bd8eb4ea6814243b75a2aff8a3f654ba
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671fde63ab3e95e5f6a3bc0dcb847fc5ea2e5137347f6151bd811e749ce8e496
+oid sha256:e76d704d9bedc21f92ad5f3623857c6424d88c040469fae87764b9129aac10f7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18244246c196872e6e9828dc23e91824da5df2d97755e843f437b6cd16498bf6
+oid sha256:0372018a4be5540bc5abe6dc6460517fafa00663177aa4622b9d278e34d5efdc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003423997945601233,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0044511973292816025,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.0003423997945601233,
       "eval_loss": 2.646597146987915,
-      "eval_runtime": 990.9412,
-      "eval_samples_per_second": 19.856,
-      "eval_steps_per_second": 2.482,
+      "eval_runtime": 988.545,
+      "eval_samples_per_second": 19.904,
+      "eval_steps_per_second": 2.489,
       "step": 1
+    },
+    {
+      "epoch": 0.0034239979456012325,
+      "grad_norm": 2.6664435863494873,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.7919,
+      "step": 10
+    },
+    {
+      "epoch": 0.0034239979456012325,
+      "eval_loss": 0.45232027769088745,
+      "eval_runtime": 990.8876,
+      "eval_samples_per_second": 19.857,
+      "eval_steps_per_second": 2.483,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2636516677386240.0,
+  "total_flos": 3.443949909835776e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd663b3a96f4833a1d2c2e36dbef9493c5332fec061c6c0dd7afe234080ed5c
+oid sha256:3155e034e31b25117ab86282dee0a694a4f5128212ce5cdb0348c4ccf1bc88d0
 size 6776