Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
+    "gate_proj",
     "k_proj",
-    "down_proj",
-    "up_proj",
-    "q_proj",
     "o_proj",
-    "gate_proj"
+    "q_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 sha256:920e75aef95846c26df47c8994f03fd57f550b8b77844bb3663ae48edf7815c8
+oid sha256:ed2b2df6a6b4d29c84454ef59206c6d6efbf0d69cb4cb565151bc14ae4378a11
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a3e5bd80263c15cc2515f7d2c5984242c05eace940a7d968f20f14d7030453
+oid sha256:1837e980bcde92f822e400383197de2d0f88fb16a4a139acdd71410fe9ea930b
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb5535922cb1f8053375cf4f0b5607ee0a1812e8ed130523ebe0c6cd11317ef
+oid sha256:dc3231eed61bca66024c3cc6045d9ebe8a23049e0e228243789fa6b15f4c52be
 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": 0.00035232978067471153,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00458028714877125,
+  "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": 0.00035232978067471153,
       "eval_loss": 13.593902587890625,
-      "eval_runtime": 299.0649,
-      "eval_samples_per_second": 3.996,
-      "eval_steps_per_second": 2.0,
+      "eval_runtime": 302.0833,
+      "eval_samples_per_second": 3.956,
+      "eval_steps_per_second": 1.98,
       "step": 1
+    },
+    {
+      "epoch": 0.0017616489033735576,
+      "grad_norm": 25.966815948486328,
+      "learning_rate": 5e-05,
+      "loss": 13.434,
+      "step": 5
+    },
+    {
+      "epoch": 0.003523297806747115,
+      "grad_norm": 34.9310188293457,
+      "learning_rate": 0.0001,
+      "loss": 11.1127,
+      "step": 10
+    },
+    {
+      "epoch": 0.003523297806747115,
+      "eval_loss": 8.07764720916748,
+      "eval_runtime": 352.0198,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 1.699,
+      "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": 191109141626880.0,
+  "total_flos": 2579973411962880.0,
   "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 sha256:38cb9161e3953b8e0ed917bba3e551e390c109379bca7b04a2fc8428e613cbbd
+oid sha256:4990ec510722c1687b109d5f73313a2f4c9dc1d0bc2db354d47032b089e1caad
 size 6776