Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,13 +21,13 @@
   "revision": null,
   "target_modules": [
     "v_proj",
+    "gate",
     "w3",
-    "q_proj",
+    "o_proj",
     "w1",
     "w2",
-    "gate",
-    "k_proj",
-    "o_proj"
+    "q_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 sha256:10f2080484f5d123cf362a20d00d95bf1df212d5ea01b5c3477b20c9c6025b0d
+oid sha256:bc66c5adf5900f6c4f18d59bea100e368739c8ac50a9408bf9ed71168c6c6deb
 size 7586384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a70333b765ade3f0fa861aeefe44b9c4fc06b289c56b5f7379e257dd23e5a20
+oid sha256:e91d47a69ae003b4db840302a1e6d2c09a5003466af613248ec3e50a3ec8c0a4
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:730a63a565431e4462dc726998a882a8cdbf6f6195a103213ecf5faed8bc707c
+oid sha256:4411ffe8899205693871ed40a600072b927e10f6fadb042eef166b8cbf61cd40
 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": 7.171929069621502e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009323507790507952,
+  "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": 7.171929069621502e-05,
       "eval_loss": NaN,
-      "eval_runtime": 54.5447,
-      "eval_samples_per_second": 107.637,
-      "eval_steps_per_second": 53.827,
+      "eval_runtime": 56.2144,
+      "eval_samples_per_second": 104.439,
+      "eval_steps_per_second": 52.229,
       "step": 1
+    },
+    {
+      "epoch": 0.00035859645348107505,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007171929069621501,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007171929069621501,
+      "eval_loss": NaN,
+      "eval_runtime": 55.1052,
+      "eval_samples_per_second": 106.542,
+      "eval_steps_per_second": 53.28,
+      "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": 5310520492032.0,
+  "total_flos": 69036766396416.0,
   "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 sha256:6124a9c1315cf58df6bf23f8c08f701ea097da37d288f8ee792eb07bc2a9b5a1
+oid sha256:65259a3f957a27815aefd106a582a64f933c1874daa7861967d773fe02a93cfc
 size 6776