Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
+    "v_proj",
     "q_proj",
-    "o_proj",
+    "up_proj",
     "k_proj",
-    "v_proj",
-    "gate_proj",
-    "down_proj"
+    "down_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 sha256:14daf186a0e42d864c0d49a0c3a335e59f5e3c83ee0a9d13d01d0529594262fe
+oid sha256:c03a46d152b726cf80f20e9b93c8d0765199ae65984e874ba26fbf6d87478f7c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41e618bc05e83e9caef0927432ef73b63023ac3a5b59e8971348d4b2c2f3a24
+oid sha256:2d5665c23e76809bc9fe3b70a06e46c4ee1ecb7e02eff18786e8e444f5531b36
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 0.0006167129201356768,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.008017267961763799,
+  "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": 0.0006167129201356768,
       "eval_loss": 3.380432605743408,
-      "eval_runtime": 45.6889,
-      "eval_samples_per_second": 14.949,
-      "eval_steps_per_second": 7.485,
+      "eval_runtime": 45.8939,
+      "eval_samples_per_second": 14.882,
+      "eval_steps_per_second": 7.452,
       "step": 1
+    },
+    {
+      "epoch": 0.003083564600678384,
+      "grad_norm": 2.203003406524658,
+      "learning_rate": 5e-05,
+      "loss": 3.3405,
+      "step": 5
+    },
+    {
+      "epoch": 0.006167129201356768,
+      "grad_norm": 4.0459771156311035,
+      "learning_rate": 0.0001,
+      "loss": 3.1342,
+      "step": 10
+    },
+    {
+      "epoch": 0.006167129201356768,
+      "eval_loss": 2.608520746231079,
+      "eval_runtime": 46.1545,
+      "eval_samples_per_second": 14.798,
+      "eval_steps_per_second": 7.41,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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:f1f1cffdc63f6b98ce03eb0de8a2b0f1bd62baa5daaa5c79ecb5a9da568661dc
+oid sha256:f1f2f1ee0412b7ff4c53cb7960681b43ca1483c486f02ece5c65fe1e2aa707c4
 size 6776