Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "q_proj",
     "k_proj",
+    "v_proj",
     "fc1",
-    "fc2",
-    "v_proj"
+    "dense",
+    "q_proj",
+    "fc2"
   ],
   "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:f1556b2aee3285bf155c33250a1a6344ace14fc35068578b973b9694e558cd6e
+oid sha256:7aeae40df2a41d01426f95a28e9affecc07bfed517f95ce6bc7e9f7080eea4b7
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882113b95af75dc4a4bfb861013df89f515f4b5c170e90794193165fec84a618
+oid sha256:42d030f98f0b106c134f5da049847e30789e35f83c6dad72848639e64412c8f9
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7fc8844aec33ac39a8d418b0bd207d733e4fe0c75f9ba828fd5cf8e97fb4e8
+oid sha256:872c1161ac0d8b2e9f04a948a3b27a13cec6f9ed82cefc1f06cd5658419b5833
 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

@@ -1,27 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.693200529971766e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00022011606889632958,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.693200529971766e-05,
-      "eval_loss": 6.939455986022949,
-      "eval_runtime": 358.9149,
-      "eval_samples_per_second": 69.287,
-      "eval_steps_per_second": 34.643,
+      "eval_loss": 6.939432144165039,
+      "eval_runtime": 384.3868,
+      "eval_samples_per_second": 64.695,
+      "eval_steps_per_second": 32.348,
       "step": 1
+    },
+    {
+      "epoch": 8.46600264985883e-05,
+      "grad_norm": 0.2929963171482086,
+      "learning_rate": 5e-05,
+      "loss": 6.9387,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001693200529971766,
+      "grad_norm": 0.27149704098701477,
+      "learning_rate": 0.0001,
+      "loss": 6.9377,
+      "step": 10
+    },
+    {
+      "epoch": 0.0001693200529971766,
+      "eval_loss": 6.936197280883789,
+      "eval_runtime": 402.4358,
+      "eval_samples_per_second": 61.794,
+      "eval_steps_per_second": 30.897,
+      "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": 1647912960.0,
+  "total_flos": 22082033664.0,
   "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:d88d9d6821d32407393b1a37351d7d3e795ae322ba38aeb84f113403c5d28e59
+oid sha256:19b66a93b280346322af36e66f45d0ca86fe2c637f4e12fe58eb0b5c88fd07d2
 size 6776