Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93bf71a760035c71d1b148cf65981fe0fc030d6387985c2ade567a183829017
+oid sha256:e8355842eaaea4ad648b1185be8e59943fbef2b5c148636242e862a9bbd6be82
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769111fa0dc3d688fcf5f98fb267b81d82ea48debed66b28c9407d3eb7cfcc07
+oid sha256:9abc5be02d6818ada0a46267e1ad7acb6ec38aef01cc20ce9268dfc145060865
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:8eabc4c6534ef93123c1386a68bfedd2b9d4f40032f88ace4c9615f83893ae17
 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": 4.37120251781265e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005682563273156445,
+  "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": 4.37120251781265e-05,
       "eval_loss": 0.6611042618751526,
-      "eval_runtime": 1067.6545,
-      "eval_samples_per_second": 9.023,
-      "eval_steps_per_second": 4.512,
+      "eval_runtime": 1067.3576,
+      "eval_samples_per_second": 9.025,
+      "eval_steps_per_second": 4.513,
       "step": 1
+    },
+    {
+      "epoch": 0.00021856012589063252,
+      "grad_norm": 8.553230285644531,
+      "learning_rate": 5e-05,
+      "loss": 2.5339,
+      "step": 5
+    },
+    {
+      "epoch": 0.00043712025178126504,
+      "grad_norm": 4.837798595428467,
+      "learning_rate": 0.0001,
+      "loss": 2.2083,
+      "step": 10
+    },
+    {
+      "epoch": 0.00043712025178126504,
+      "eval_loss": 0.5364651679992676,
+      "eval_runtime": 1071.4511,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 4.496,
+      "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": 4162595523133440.0,
   "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 sha256:9a8f010ae1e07d3fcfa71380137e331610a8651425efb941944a2bf6a5e14fbf
+oid sha256:de7d95dd0cf3b2ad3de60d50b3549a2dc57d385a2f95497a3f494dea79edebb5
 size 6776