Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "w3",
     "w1",
-    "w2",
-    "q_proj",
-    "k_proj",
+    "o_proj",
     "v_proj",
     "gate",
-    "w3"
+    "w2",
+    "k_proj",
+    "q_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 sha256:6def88c3027f3c21ccaf2940794f25011699cca96ea2433cbcc549f360e43976
+oid sha256:f1c07d87b0903972090dc7c59675be444b55a5abc60fa7f3280cbea60bfc0b93
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5aac2ec72f95aa52c94f7960ed6bde5ceb91257890adec5aad6344b5888d2d9
+oid sha256:b363b9b390e735a53ddcd7def622c18769e4fa75b84857f7e051279a6b07f73a
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be738ec501de067c43591362c96ef6576dcee12b8605bd581601f96f79f1119
+oid sha256:1f87458b56b81341706d06a4ede04bec93a0e13eb8ba6069748b3bb4cddc346b
 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": 0.0005717552887364208,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007432818753573471,
+  "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": 0.0005717552887364208,
       "eval_loss": 8.388371467590332,
-      "eval_runtime": 100.8533,
-      "eval_samples_per_second": 7.308,
-      "eval_steps_per_second": 3.659,
+      "eval_runtime": 101.2069,
+      "eval_samples_per_second": 7.282,
+      "eval_steps_per_second": 3.646,
       "step": 1
+    },
+    {
+      "epoch": 0.002858776443682104,
+      "grad_norm": 7.614388942718506,
+      "learning_rate": 5e-05,
+      "loss": 7.9936,
+      "step": 5
+    },
+    {
+      "epoch": 0.005717552887364208,
+      "grad_norm": 10.528021812438965,
+      "learning_rate": 0.0001,
+      "loss": 6.6528,
+      "step": 10
+    },
+    {
+      "epoch": 0.005717552887364208,
+      "eval_loss": 5.3022379875183105,
+      "eval_runtime": 107.0555,
+      "eval_samples_per_second": 6.884,
+      "eval_steps_per_second": 3.447,
+      "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": 323875007102976.0,
+  "total_flos": 4210375092338688.0,
   "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:a8d9ff475ff7194f50032d2cb46a3f04cb38d3ac825ffe8b82890740081bfbd8
+oid sha256:9b9041c1ebc0d02fefdca718099d9a5a3c190e80ae06c1c0d68e60711b365379
 size 6776