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",
     "gate_proj",
+    "v_proj",
     "up_proj",
-    "down_proj",
+    "o_proj",
     "q_proj",
-    "v_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 sha256:512ca9b6360c968a943698297ddf21189337ad369d86453a536b1733bd72abc5
+oid sha256:1c22a3e93177ed0c3f1f81dbd1458c7cce5a31952ef6ed62288d9ba2f0254e74
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562bbdd2774b9982f6e8c1b43e52d90af265fafaaed836cfb9ae5e6743c9a273
+oid sha256:290f1d689f9a2aeeaf83c0d12c42534ae1e3953d2beff34eb7c9cd64074a4e9e
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cee1d2f68de4a719aea4937b4c7c41801f3222b38c7d482b730834b7290e765
+oid sha256:d29accfb5adac83d5b9df422d9bb143810bbb3a15382228817b7ba29703dee92
 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": 0.0008592910848549946,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01117078410311493,
+  "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": 0.0008592910848549946,
       "eval_loss": NaN,
-      "eval_runtime": 92.0521,
-      "eval_samples_per_second": 5.323,
-      "eval_steps_per_second": 2.662,
+      "eval_runtime": 97.4223,
+      "eval_samples_per_second": 5.03,
+      "eval_steps_per_second": 2.515,
       "step": 1
+    },
+    {
+      "epoch": 0.004296455424274973,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "eval_loss": NaN,
+      "eval_runtime": 96.9809,
+      "eval_samples_per_second": 5.053,
+      "eval_steps_per_second": 2.526,
+      "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": 285209442385920.0,
+  "total_flos": 3707722751016960.0,
   "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 sha256:13bca8464e31a52192909cef13c42ecd757f3f29957c429d7118d86f0bbb42bf
+oid sha256:b49150b67cfa301b9ca3d48cd81f9c96183fa43dcd933dabbfbf9cd0332cfe5c
 size 6776