Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5506a1cbeaa3c5b86bf9c2f0e28f3f73c9a1ee5c201eec0d798e473d4cfae96b
+oid sha256:7552b59cade905907515cce71d90a83e0802ff7863d50dd6992cb8215c4b06c6
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfb4e7883453f45cd339e02947e7503b630da4cc3a43c372daa9fdc9b8e25f2
+oid sha256:32ca82749fee11872970d47130cbd649c4a938c09e67673f303741a5f614c549
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17cd0b5f1e33bd6dba2461570a653efdaf1fb902096b4df09992935b3fc24a4
+oid sha256:dc12b3ebfd598da93336aea3b9e623a1adcbdea90c1ade145e09bc2a56a621b5
 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": 0.0006026819346090101,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00783486514991713,
+  "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": 0.0006026819346090101,
       "eval_loss": 5.079477310180664,
-      "eval_runtime": 24.5555,
-      "eval_samples_per_second": 28.466,
-      "eval_steps_per_second": 14.253,
+      "eval_runtime": 24.8869,
+      "eval_samples_per_second": 28.087,
+      "eval_steps_per_second": 14.064,
       "step": 1
+    },
+    {
+      "epoch": 0.0030134096730450506,
+      "grad_norm": 1.770930290222168,
+      "learning_rate": 5e-05,
+      "loss": 4.6092,
+      "step": 5
+    },
+    {
+      "epoch": 0.006026819346090101,
+      "grad_norm": 3.8804337978363037,
+      "learning_rate": 0.0001,
+      "loss": 4.7694,
+      "step": 10
+    },
+    {
+      "epoch": 0.006026819346090101,
+      "eval_loss": 4.817326068878174,
+      "eval_runtime": 23.2427,
+      "eval_samples_per_second": 30.074,
+      "eval_steps_per_second": 15.058,
+      "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": 8903816380416.0,
+  "total_flos": 115749612945408.0,
   "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 sha256:6aa1577be013c7c495e4bdf66e036402636e893426fe726fd48bca720be5cd92
+oid sha256:630a1f98bf8d88f5c562e23f1d2c5a8b5cce05146173ce6a247ce5b0bf350c70
 size 6776