Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
-    "q_proj",
     "gate_proj",
-    "o_proj",
+    "v_proj",
     "down_proj",
+    "o_proj",
+    "q_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2744f7a534fc10d72e364f4d7e30baf61e27876de77f27a1d8a1d5765435810e
+oid sha256:e4cbb509a6463f9685210cee85b5669daff6dec56cc19e4d39920b53a268c059
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f1bee63507933e7f744c13b0be8f33f31f56f5902f6520a358fc2a42c6c2c8
+oid sha256:420fef1eca1cd6316fa1ea88d24f86bcebae971313775b6b7571604d5e6df834
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 2.1329920546045965e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00027728896709859754,
+  "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": 2.1329920546045965e-05,
       "eval_loss": 10.375789642333984,
-      "eval_runtime": 128.9458,
-      "eval_samples_per_second": 153.088,
-      "eval_steps_per_second": 76.544,
+      "eval_runtime": 130.1755,
+      "eval_samples_per_second": 151.641,
+      "eval_steps_per_second": 75.821,
       "step": 1
+    },
+    {
+      "epoch": 0.00010664960273022984,
+      "grad_norm": 0.030153265222907066,
+      "learning_rate": 5e-05,
+      "loss": 10.3759,
+      "step": 5
+    },
+    {
+      "epoch": 0.00021329920546045967,
+      "grad_norm": 0.025994563475251198,
+      "learning_rate": 0.0001,
+      "loss": 10.373,
+      "step": 10
+    },
+    {
+      "epoch": 0.00021329920546045967,
+      "eval_loss": 10.375554084777832,
+      "eval_runtime": 130.2698,
+      "eval_samples_per_second": 151.532,
+      "eval_steps_per_second": 75.766,
+      "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": 25861816320.0,
+  "total_flos": 329738158080.0,
   "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 sha256:87b86da9857fef020b8d8847f76eb9832b28cedd62c854ff7dca9483f2fa50c4
+oid sha256:c56a220473feaef9bec9ae7a262e3b45e449ca0634bcb47bf82b9d523b11dde8
 size 6776