Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "down_proj",
-    "v_proj",
     "q_proj",
+    "o_proj",
     "gate_proj",
-    "up_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_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 sha256:008c8b6b01c6c1292416d9a30ee16a0a69de5d28f1677d3af036d5662b5edf00
+oid sha256:c53582c818cded47f3e70a98c54259ad214e3d056714c6e85f0ad4909ae94f74
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a78240cec802de698d97677f97a67c5b59435132baf6539832249c3ec0e28a
+oid sha256:be5ccdb8a10d082f220c6238d6fa4b0282f15c5ce8de3983d411dd11e01371f2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8ef222641ce7e54c4b1d49b5a2e66fce7ea5b5f86a8130c3ee2866221fbc5a
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 3.96067054152268e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005148871703979484,
+  "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": 3.96067054152268e-05,
       "eval_loss": 0.2887181341648102,
-      "eval_runtime": 1257.8676,
-      "eval_samples_per_second": 8.452,
-      "eval_steps_per_second": 4.226,
+      "eval_runtime": 1261.1036,
+      "eval_samples_per_second": 8.43,
+      "eval_steps_per_second": 4.215,
       "step": 1
+    },
+    {
+      "epoch": 0.00019803352707613398,
+      "grad_norm": 1.734922170639038,
+      "learning_rate": 5e-05,
+      "loss": 1.1269,
+      "step": 5
+    },
+    {
+      "epoch": 0.00039606705415226796,
+      "grad_norm": 1.451378345489502,
+      "learning_rate": 0.0001,
+      "loss": 0.9029,
+      "step": 10
+    },
+    {
+      "epoch": 0.00039606705415226796,
+      "eval_loss": 0.2597455680370331,
+      "eval_runtime": 1258.0453,
+      "eval_samples_per_second": 8.45,
+      "eval_steps_per_second": 4.226,
+      "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": 350533957189632.0,
+  "total_flos": 4556941443465216.0,
   "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 sha256:2bd1d6c6de07c87e958e9a6e1f207aa879effa5e519fb30e25ad8170c3001d14
+oid sha256:f0c8044ff7b02de96a23b002e443da4c56f73141e2906d261e69303ff95943f4
 size 6776