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",
-    "o_proj",
-    "k_proj",
-    "q_proj",
     "down_proj",
-    "up_proj"
+    "q_proj",
+    "k_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:cc065d6de910664c903aa386529c5741d95ffa1749d5b613907988723c9eeb16
+oid sha256:31379bc017258580f5a678caeb7388539843daa1dd2641cb7f88ba9382a034bb
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a50c2bd9bc739b957e66c5bb462d85925bc420399ef05d69db2bd22003d34ee
+oid sha256:08096e299bdd6926d59e94c759cfccaca38e46957da1541b0e8e64a0b234a90b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:3dfaa76e23b5ee2e9cd9f372437b6e2eeffe609e58ae8d131d3303166f82dc47
 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": 4.610844706750277e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000599409811877536,
+  "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": 4.610844706750277e-05,
       "eval_loss": 7.478056907653809,
-      "eval_runtime": 641.932,
-      "eval_samples_per_second": 14.226,
-      "eval_steps_per_second": 7.113,
+      "eval_runtime": 646.3745,
+      "eval_samples_per_second": 14.128,
+      "eval_steps_per_second": 7.064,
       "step": 1
+    },
+    {
+      "epoch": 0.00023054223533751383,
+      "grad_norm": 235.5802001953125,
+      "learning_rate": 5e-05,
+      "loss": 30.1518,
+      "step": 5
+    },
+    {
+      "epoch": 0.00046108447067502766,
+      "grad_norm": 107.33450317382812,
+      "learning_rate": 0.0001,
+      "loss": 8.7946,
+      "step": 10
+    },
+    {
+      "epoch": 0.00046108447067502766,
+      "eval_loss": 0.8460701107978821,
+      "eval_runtime": 649.6744,
+      "eval_samples_per_second": 14.056,
+      "eval_steps_per_second": 7.028,
+      "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": 262900769882112.0,
+  "total_flos": 2453740518899712.0,
   "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 sha256:880a514bfa9ffcb652b982a02c1485c48fa1c9df956c2f69c1fd44f97df7265f
+oid sha256:4a00715ef0a89f6f95eac1620884acfdf5fffe37b1b49e368c2811bee9d778ac
 size 6776