Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "up_proj",
-    "k_proj",
     "gate_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
     "down_proj",
-    "v_proj"
+    "k_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:d46ff4eaacf938a0807fe0df01e5803ab4e42e591de6aff260d75fe84517b850
+oid sha256:d7f97d658b74bd0fc3a9fde11b9de4552cadfa7ba902286027f1b2ba96b93a59
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62d64634c198de35102db69454c2be8110e5727009ff33293229299208a54621
+oid sha256:fb18cdfa9d9fcba500c34526c38715f980dc91bad3d3e8af9585db60be806db7
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bc92371de2dc48fc3204fa3557c31d40e6fd4491378f9e7a4c4fa05636082a
+oid sha256:0a4f0069edb1e06dc358b4ff190f10113fb1ddd26ae17efb126b43600cdb989c
 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": 1.2771228975364299e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0001660259766797359,
+  "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": 1.2771228975364299e-05,
       "eval_loss": 3.492058038711548,
-      "eval_runtime": 524.3108,
-      "eval_samples_per_second": 62.881,
-      "eval_steps_per_second": 31.441,
+      "eval_runtime": 514.169,
+      "eval_samples_per_second": 64.121,
+      "eval_steps_per_second": 32.061,
       "step": 1
+    },
+    {
+      "epoch": 6.38561448768215e-05,
+      "grad_norm": 1.112701416015625,
+      "learning_rate": 5e-05,
+      "loss": 3.3946,
+      "step": 5
+    },
+    {
+      "epoch": 0.000127712289753643,
+      "grad_norm": 0.9742205739021301,
+      "learning_rate": 0.0001,
+      "loss": 3.5179,
+      "step": 10
+    },
+    {
+      "epoch": 0.000127712289753643,
+      "eval_loss": 3.4140679836273193,
+      "eval_runtime": 512.3057,
+      "eval_samples_per_second": 64.354,
+      "eval_steps_per_second": 32.178,
+      "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": 3429265047552.0,
+  "total_flos": 44580445618176.0,
   "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 sha256:72718766856fd4642541bd7c7791fcf4385038aa1d709d93a83e34c57c453bdc
+oid sha256:80adb1043b24932a008b3c06d10f53aee21e88791f05fb3c19e8a64a369c8535
 size 6776