Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
-    "o_proj",
     "k_proj",
     "up_proj",
     "down_proj",
+    "o_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7b3d5ae62344178c67e4898346548eb76a6fc5c953b6f405f3b826e8bb78b9
+oid sha256:8e06cd923bbfabeb6c1318906f2907166e0fea44b99eadbfc1b63aa6f7a43dde
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2c212719777714f3a02b1dabb450a3bf7283b9c18b602c69fb991238aec9c2
+oid sha256:4c08a8ec320b565a4cee486813d7c400c4af9bcbca303f87c3f5fea2fc9f2ac5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:0c18e2d973c15966914a734e2b0996d2f74791d59f2ac714dbf7b437b16553d1
 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": 0.0002463661000246366,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.003202759300320276,
+  "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": 0.0002463661000246366,
       "eval_loss": 0.8827053308486938,
-      "eval_runtime": 185.1415,
-      "eval_samples_per_second": 9.231,
-      "eval_steps_per_second": 4.618,
+      "eval_runtime": 185.0064,
+      "eval_samples_per_second": 9.238,
+      "eval_steps_per_second": 4.621,
       "step": 1
+    },
+    {
+      "epoch": 0.001231830500123183,
+      "grad_norm": 0.343232125043869,
+      "learning_rate": 5e-05,
+      "loss": 0.6546,
+      "step": 5
+    },
+    {
+      "epoch": 0.002463661000246366,
+      "grad_norm": 0.4824935495853424,
+      "learning_rate": 0.0001,
+      "loss": 0.7633,
+      "step": 10
+    },
+    {
+      "epoch": 0.002463661000246366,
+      "eval_loss": 0.7920751571655273,
+      "eval_runtime": 186.2524,
+      "eval_samples_per_second": 9.176,
+      "eval_steps_per_second": 4.591,
+      "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": 277434637221888.0,
+  "total_flos": 4069041345921024.0,
   "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:a4bf0435af950a993bc17ff62f694abf0c8d10d78b5a6ca4321689c4f48f451a
+oid sha256:e6643ab4b369a7b01e1a855a5f1b9a7f9041b8b7bb9c5449640e3c04a50c9956
 size 6776