Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
     "up_proj",
-    "v_proj",
     "down_proj",
+    "q_proj",
+    "v_proj",
     "o_proj",
     "k_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a7c7437d32ffd5e7ede7b6e2cf8d3cacb96d1e70095d8a74445d65c09262b5
+oid sha256:73d92e5886afb6cdbdd26510ab74256e2b80f49cea8bf8bd36c1c335d36be46d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636f47c615dfe6a98ee6ada8677582fbb245516f20023aa7e9f96e24ab3d64d1
+oid sha256:9b9b891c53b23d67a22917f951d25e40a7182ed3ae78ad54ea8e6ad44a634c0c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:905c1c46256d800c5d3ce8a0b649857b46d21f468bc576b13489acede58dd384
 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": 0.0004074564530915758,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005296933890190486,
+  "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": 0.0004074564530915758,
       "eval_loss": 2.328631639480591,
-      "eval_runtime": 73.5342,
-      "eval_samples_per_second": 14.061,
-      "eval_steps_per_second": 7.031,
+      "eval_runtime": 72.9398,
+      "eval_samples_per_second": 14.176,
+      "eval_steps_per_second": 7.088,
       "step": 1
+    },
+    {
+      "epoch": 0.0020372822654578793,
+      "grad_norm": 31.550853729248047,
+      "learning_rate": 5e-05,
+      "loss": 8.5512,
+      "step": 5
+    },
+    {
+      "epoch": 0.0040745645309157585,
+      "grad_norm": 14.368852615356445,
+      "learning_rate": 0.0001,
+      "loss": 6.4378,
+      "step": 10
+    },
+    {
+      "epoch": 0.0040745645309157585,
+      "eval_loss": 1.3571594953536987,
+      "eval_runtime": 73.9923,
+      "eval_samples_per_second": 13.974,
+      "eval_steps_per_second": 6.987,
+      "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": 219083723243520.0,
+  "total_flos": 2629004678922240.0,
   "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 sha256:0a813adab0848e51df506d854db1641ce123774bf60938a2442f69c965834099
+oid sha256:e71580071bc02b39bc48b1b2af0f5fc90cadf660153269ac7b96cd94aa74d04f
 size 6776