Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662d28fc642488648c4015c30610ece07676ff41830e2ffdf39626d9e095dabc
+oid sha256:86d2b058479ec094b3f0ec2ba970f1d0149bf5d7e8eada8e66ea9fd1671f3af9
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb9526c7a87722797383efe33f635fa1e3384a2375ee52858c2644ff7f211bb
+oid sha256:cbaef359af55e3317c61dad894aa9d403423475ef32438f3e27289b6ba7514f5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:c5d58a77b7e7abf4f99c2b253ea7d0012eb34f29163a114391e783f09fc5bd6f
 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": 0.00039769337840524953,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005170013919268244,
+  "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": 0.00039769337840524953,
       "eval_loss": 10.654695510864258,
-      "eval_runtime": 65.1562,
-      "eval_samples_per_second": 16.253,
-      "eval_steps_per_second": 8.134,
+      "eval_runtime": 65.1814,
+      "eval_samples_per_second": 16.247,
+      "eval_steps_per_second": 8.131,
       "step": 1
+    },
+    {
+      "epoch": 0.001988466892026248,
+      "grad_norm": 6.9008917808532715,
+      "learning_rate": 5e-05,
+      "loss": 10.7859,
+      "step": 5
+    },
+    {
+      "epoch": 0.003976933784052496,
+      "grad_norm": 18.198335647583008,
+      "learning_rate": 0.0001,
+      "loss": 10.4823,
+      "step": 10
+    },
+    {
+      "epoch": 0.003976933784052496,
+      "eval_loss": 9.707829475402832,
+      "eval_runtime": 65.5872,
+      "eval_samples_per_second": 16.146,
+      "eval_steps_per_second": 8.081,
+      "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": 162874924204032.0,
+  "total_flos": 2198811476754432.0,
   "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:f4d2f83fcec44b58584987693f5e9fa889069d7406fbc6635c33e5df1aa001ea
+oid sha256:a94cc36c8971606b16ebe27bde28df8076261a07e6149c868baf545ce1fb3016
 size 6776