Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
     "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_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:a034e4d3dab16d8b1bef60f7c994da1a2d9f30181d41857c253989292b1e20d9
+oid sha256:cbe214c6aaf6fed97284f88da304bdde2b4e5c801787fad0f68994be4f58112f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af53aa8b7d750003df9f9cee7ce6834dc9527ea98250a64636e0dbd7dd4a08db
+oid sha256:822aae55e393e64e4071c08b34aae48fcb17bf111fd374a1ae0280a8a85a66fe
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:7ef568c15d3a92fad74ef5f86ffe7330da3a1446a29e6310725eb6a237745116
 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": 1.748618591312863e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00022732041687067216,
+  "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": 1.748618591312863e-05,
       "eval_loss": 4.204365253448486,
-      "eval_runtime": 3167.0362,
-      "eval_samples_per_second": 7.603,
-      "eval_steps_per_second": 3.802,
+      "eval_runtime": 3167.971,
+      "eval_samples_per_second": 7.601,
+      "eval_steps_per_second": 3.801,
       "step": 1
+    },
+    {
+      "epoch": 8.743092956564314e-05,
+      "grad_norm": 5.006407737731934,
+      "learning_rate": 5e-05,
+      "loss": 4.6136,
+      "step": 5
+    },
+    {
+      "epoch": 0.00017486185913128627,
+      "grad_norm": 3.7020463943481445,
+      "learning_rate": 0.0001,
+      "loss": 3.1002,
+      "step": 10
+    },
+    {
+      "epoch": 0.00017486185913128627,
+      "eval_loss": 3.6543192863464355,
+      "eval_runtime": 3212.9216,
+      "eval_samples_per_second": 7.495,
+      "eval_steps_per_second": 3.747,
+      "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": 184956424814592.0,
+  "total_flos": 3514172071477248.0,
   "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:b37aa612c347d046ec73b94ec5f4084cfd368294aa6daf87ee5b964d6a1dc5dd
+oid sha256:e2ae85d327c5d9838032c8c4fce26f3e43ea7181fab130cc63731ff673e7867e
 size 6776