Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "k_proj",
-    "up_proj",
-    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
     "gate_proj",
-    "v_proj"
+    "up_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 sha256:97550b89a5aa3c1648669dfa780477ffb24068ec17d8eccb10d5c752fc6c4a4d
+oid sha256:05a53b0702fde05fddf69c30f88ae2c7ae658d14bfe988cc5cb22186ad23834b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0eda1ba2303c1065eefb23c251bd86d3373f6adb0749db5a9658f1218dc10c
+oid sha256:271fc9177462639f525651bafcdbece9d881ced31c065c4068ba8f105c02b6e5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:99c6874540ab7284054ee4e661d01f877ef78b58f8fb1147d1017f763361b191
 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": 0.0011695906432748538,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0152046783625731,
+  "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": 0.0011695906432748538,
       "eval_loss": 1.673849105834961,
-      "eval_runtime": 25.7204,
-      "eval_samples_per_second": 14.036,
-      "eval_steps_per_second": 7.037,
+      "eval_runtime": 25.7736,
+      "eval_samples_per_second": 14.007,
+      "eval_steps_per_second": 7.023,
       "step": 1
+    },
+    {
+      "epoch": 0.005847953216374269,
+      "grad_norm": 14.895322799682617,
+      "learning_rate": 5e-05,
+      "loss": 6.3817,
+      "step": 5
+    },
+    {
+      "epoch": 0.011695906432748537,
+      "grad_norm": 25.017160415649414,
+      "learning_rate": 0.0001,
+      "loss": 7.1895,
+      "step": 10
+    },
+    {
+      "epoch": 0.011695906432748537,
+      "eval_loss": 1.5868688821792603,
+      "eval_runtime": 25.9777,
+      "eval_samples_per_second": 13.897,
+      "eval_steps_per_second": 6.968,
+      "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": 219083974901760.0,
+  "total_flos": 2497557313880064.0,
   "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:e6e9da4c9b5ff78b59d6adc2307e01cb85918b29bf54f75cd29d1363da3a2196
+oid sha256:d59e75d1738676ddb5dbd52d84c0fc6d95a160b4d36410480432ff5e7acce682
 size 6776