Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da116f06d0ddb3d465ca02c5370c75d0379d8493b0aecb16af4dcae1e9d0b3f1
+oid sha256:cc93f530b246f4903ef588357bb34b3a8d4d8786f14a47d4e6089dc3dcffc33f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d22a9ea20a65494643675eef162e2aab98cbffa8abe0f11b3414238ce31768
+oid sha256:603074d5354eb81974ae3a78680e0941cc1e3e0bf23de0113967078ef3f8d734
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5312ddb8f626229a291c72b544634e2d97dd8ec4ceca4550f1b24f37a77647
+oid sha256:b5bd860944d413c69d316becfd45176fb3ebfdcbdedd07e6e5cbb141dc35e71d
 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": 0.0020855057351407717,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.027111574556830033,
+  "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": 0.0020855057351407717,
       "eval_loss": 2.006255865097046,
-      "eval_runtime": 11.7519,
-      "eval_samples_per_second": 17.189,
-      "eval_steps_per_second": 8.594,
+      "eval_runtime": 11.3423,
+      "eval_samples_per_second": 17.809,
+      "eval_steps_per_second": 8.905,
       "step": 1
+    },
+    {
+      "epoch": 0.010427528675703858,
+      "grad_norm": 0.7133792042732239,
+      "learning_rate": 5e-05,
+      "loss": 1.8714,
+      "step": 5
+    },
+    {
+      "epoch": 0.020855057351407715,
+      "grad_norm": 0.760151743888855,
+      "learning_rate": 0.0001,
+      "loss": 1.696,
+      "step": 10
+    },
+    {
+      "epoch": 0.020855057351407715,
+      "eval_loss": 1.9778136014938354,
+      "eval_runtime": 11.2809,
+      "eval_samples_per_second": 17.906,
+      "eval_steps_per_second": 8.953,
+      "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": 50009733070848.0,
+  "total_flos": 725141129527296.0,
   "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:c2a6bb261fffd73764f0ea7acdb38ea88e9aa7886d28273d070011fdc2c5aa7a
+oid sha256:a3e0c59a675e02345ce10ecf9766a95fab82d589f2ca9a8ab0912beee341235b
 size 6776