Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "o_proj",
-    "gate_proj",
-    "k_proj",
-    "q_proj",
     "v_proj",
-    "down_proj"
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj"
   ],
   "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:f612b0333705ae9e3454ee0efd319fa42d36375bab9381936f9fed4fec052de5
+oid sha256:58dad5cb07e01c6c53bbe30571977b8f2b932829110c7c841c71d4915da5621f
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44bc1709f11f83fde6de3a73a60f1e131d06029fe74ada90c8a892e23816de1b
+oid sha256:b6fe9a18d1cfa740ef9e45774168947a4a74f5d14849d04e9f0040152a46ce50
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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

@@ -1,27 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2932595313227458e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00016812373907195696,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.2932595313227458e-05,
-      "eval_loss": 1.2712392807006836,
-      "eval_runtime": 2435.2191,
-      "eval_samples_per_second": 13.37,
-      "eval_steps_per_second": 6.685,
+      "eval_loss": 1.2712680101394653,
+      "eval_runtime": 2436.9276,
+      "eval_samples_per_second": 13.36,
+      "eval_steps_per_second": 6.68,
       "step": 1
+    },
+    {
+      "epoch": 6.46629765661373e-05,
+      "grad_norm": 1.2175859212875366,
+      "learning_rate": 5e-05,
+      "loss": 1.1907,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001293259531322746,
+      "grad_norm": 1.4099855422973633,
+      "learning_rate": 0.0001,
+      "loss": 0.9698,
+      "step": 10
+    },
+    {
+      "epoch": 0.0001293259531322746,
+      "eval_loss": 0.6086933016777039,
+      "eval_runtime": 2466.1818,
+      "eval_samples_per_second": 13.202,
+      "eval_steps_per_second": 6.601,
+      "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": 162873414254592.0,
+  "total_flos": 2117354385309696.0,
   "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 sha256:25417aeacaf3b345a0b0e0c37df15a458e2d42f8a85c83dfd95707676998c92c
+oid sha256:35b253b313659bbb2193980fe403d429ee0c01f925a390f4c7d9465ebfb1aef3
 size 6776