Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "q_proj",
-    "up_proj",
     "v_proj",
+    "gate_proj",
+    "k_proj",
     "o_proj",
-    "k_proj"
+    "down_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 sha256:63746b00672ff9eca129b534319e055f2846edf53448a0ab3f55187fd4685c38
+oid sha256:252efd3c2b6b81507ba571e987ec8fc57619490683dcb2b333bf54a1da6b0fd9
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4145d7985d4c9dff053da7f374da6a2e1d2555ad3119f7faa070a57d981672b
+oid sha256:6189b3bfb6ede1d5c2409e46c45132d7126ba6b9357e8a3373512e73f85a1bf6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edc2e21c3cada6c05c007d88e7484a359240cd9d5addf9bb175b2cbecaf9090
+oid sha256:7a2043fcab6393039914b1ae1d41f0b06c9cc65053e1770339d2cdf1b4d4fcd1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08695652173913043,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2608695652173913,
+  "eval_steps": 3,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.08695652173913043,
       "eval_loss": 8.65756607055664,
-      "eval_runtime": 0.7639,
-      "eval_samples_per_second": 6.545,
-      "eval_steps_per_second": 3.927,
+      "eval_runtime": 0.7568,
+      "eval_samples_per_second": 6.607,
+      "eval_steps_per_second": 3.964,
       "step": 1
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "eval_loss": 8.638962745666504,
+      "eval_runtime": 0.7572,
+      "eval_samples_per_second": 6.603,
+      "eval_steps_per_second": 3.962,
+      "step": 3
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 12,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 3,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 395778038169600.0,
+  "total_flos": 1187334114508800.0,
   "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 sha256:3e60663ffe957a14c5a6b5bbf2bfefdfe56fb44773c6f76a378aee0b83078c9f
+oid sha256:57a26d4da273fc83337ade24e7db24d112f8463a892cf93f8ea3330a07464a7a
 size 6776