Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "gate_proj",
+    "down_proj",
     "v_proj",
     "k_proj",
-    "q_proj",
     "up_proj",
-    "down_proj"
+    "o_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 sha256:0189df33ec0df7e6fc37ebbe6762069abfb9c4899a75825327dfcfa4e6ce7646
+oid sha256:ca54dff7b11a5c1072bcaa4d00c6cd636e78f6c075739710b4e3c7d28e6a398b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e289cd040dfb2b06ecd8896ed5a4d6943ce2f15d6094df73781c7227052f3170
+oid sha256:b9104d59f0693dfd7e87ed440eb48ed9377bb5b20e205207a3498abc2ba6d663
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:c682b407b21541d71a29dc7003999c781bae916db960904cb9bf02cf91709a8b
 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": 0.00012580990123922753,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0016355287161099578,
+  "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": 0.00012580990123922753,
       "eval_loss": 1.046350121498108,
-      "eval_runtime": 461.3562,
-      "eval_samples_per_second": 7.255,
-      "eval_steps_per_second": 3.628,
+      "eval_runtime": 460.9411,
+      "eval_samples_per_second": 7.261,
+      "eval_steps_per_second": 3.632,
       "step": 1
+    },
+    {
+      "epoch": 0.0006290495061961376,
+      "grad_norm": 3.190112829208374,
+      "learning_rate": 5e-05,
+      "loss": 0.9941,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012580990123922753,
+      "grad_norm": 0.6102684140205383,
+      "learning_rate": 0.0001,
+      "loss": 0.8414,
+      "step": 10
+    },
+    {
+      "epoch": 0.0012580990123922753,
+      "eval_loss": 1.001396894454956,
+      "eval_runtime": 474.1232,
+      "eval_samples_per_second": 7.059,
+      "eval_steps_per_second": 3.531,
+      "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": 231195531018240.0,
+  "total_flos": 3652889390088192.0,
   "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 sha256:09c231e20a3c738c0a3530d1c35ce971c887a37d59a40385efc05d1f875d9a4e
+oid sha256:0002f31f639d8d06a9c6a9729495672281fca57de2fd670a3eb61304db59c7ec
 size 6776