Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "out_proj",
     "k_proj",
     "fc_out",
-    "q_proj",
     "fc_in",
-    "v_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:a7bead406585b4cb9d35f1680da9b7149794874ccf19750bcf215ba47668ed95
+oid sha256:84c959ae8fe0a0d3255c4092675323c253c0efef72d1bf642550308543fbc76c
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1558d984e98faf19735fc404907c4254d7644a624a7898281b2ba60b07d062
+oid sha256:1f54f6ea853d9a930fb3c634f218ff8384644ff63390c094670ec50f4b15cc9d
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772c12aea0055e16597749ef8f0cf5d107fb6f555f61b38319bdf80a27064f18
+oid sha256:eb12fff2d181bb704e9ae3d3eed5cbb3107ae52ed85ee581a26ccc048676b3ec
 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": 0.0002116066232873089,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0027508861027350155,
+  "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": 0.0002116066232873089,
       "eval_loss": 3.1842007637023926,
-      "eval_runtime": 167.9134,
-      "eval_samples_per_second": 11.851,
-      "eval_steps_per_second": 5.926,
+      "eval_runtime": 168.1217,
+      "eval_samples_per_second": 11.837,
+      "eval_steps_per_second": 5.918,
       "step": 1
+    },
+    {
+      "epoch": 0.0010580331164365445,
+      "grad_norm": 3.979726552963257,
+      "learning_rate": 5e-05,
+      "loss": 14.4595,
+      "step": 5
+    },
+    {
+      "epoch": 0.002116066232873089,
+      "grad_norm": 5.464813232421875,
+      "learning_rate": 0.0001,
+      "loss": 13.1041,
+      "step": 10
+    },
+    {
+      "epoch": 0.002116066232873089,
+      "eval_loss": 2.936410665512085,
+      "eval_runtime": 175.2718,
+      "eval_samples_per_second": 11.354,
+      "eval_steps_per_second": 5.677,
+      "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": 144039040278528.0,
+  "total_flos": 1944527043760128.0,
   "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 sha256:4b44b1ef83f18f06731a95968a2fd0bc7622dea6a05e8405994a03bb8d003922
+oid sha256:277a31828187811e35bcdc8138b3a3dfcbc4c8ff0da5b08232eefc69b4552b96
 size 6776