Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
+    "down_proj",
     "gate_proj",
-    "up_proj",
     "v_proj",
-    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d696d8ddf999541bb6fe1f01cb716e18986bf4cdd0b7ffabb572bb96cf1562fe
+oid sha256:c96d04e6bc6c2d2f48a785ecf4c9ca556a61bd2abdfc1e428d1d657300b9d7c4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615676cc01206ee1c753c3772c3f33aba9a146a4589bc9d30ea6017182e352a3
+oid sha256:b7717be7d58a64362ff692a330e286f0df90e88ce8b872a754b49be3983f3544
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:43f0afd2a6da0fca19f600fb0b6d301534483f4096658807dd63f0bc368c2a3d
 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": 8.437928488556059e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0010969307035122878,
+  "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": 8.437928488556059e-05,
       "eval_loss": 1.3113551139831543,
-      "eval_runtime": 412.2111,
-      "eval_samples_per_second": 12.105,
-      "eval_steps_per_second": 6.053,
+      "eval_runtime": 412.6536,
+      "eval_samples_per_second": 12.092,
+      "eval_steps_per_second": 6.046,
       "step": 1
+    },
+    {
+      "epoch": 0.00042189642442780296,
+      "grad_norm": 26.7180233001709,
+      "learning_rate": 5e-05,
+      "loss": 4.9078,
+      "step": 5
+    },
+    {
+      "epoch": 0.0008437928488556059,
+      "grad_norm": 17.810115814208984,
+      "learning_rate": 0.0001,
+      "loss": 4.0347,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008437928488556059,
+      "eval_loss": 0.662794291973114,
+      "eval_runtime": 415.9268,
+      "eval_samples_per_second": 11.997,
+      "eval_steps_per_second": 5.999,
+      "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": 219083723243520.0,
+  "total_flos": 2760454912868352.0,
   "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 sha256:1d8c38d3c908d1745b15ef42a87b6231e599541c5f1985584b95934b7e30af80
+oid sha256:ce6065828f0085e256495ce64ac3500b12a729aef0fef902df1082ef9933277f
 size 6776