Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "down_proj",
-    "k_proj",
     "q_proj",
+    "k_proj",
     "v_proj",
     "gate_proj",
-    "up_proj"
+    "up_proj",
+    "o_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:f1d7958c6ac37159112d86960490f0fe347b177d450e4398d30de1021671e13e
+oid sha256:8a966cf10c84aa4a7e80b0775b6cdc149da8909cd9f44cf54ace1ef0c8e41bfb
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb84f97e969acec3fd5dee18a46fc5ebe3b0ef5d9265989284c8d9eedd2b0488
+oid sha256:f429d7faddde2086f1ae058ab3059a0f5dfdd208b3984bf077faefd14482f7b8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8ef222641ce7e54c4b1d49b5a2e66fce7ea5b5f86a8130c3ee2866221fbc5a
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 4.379961675335341e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005693950177935943,
+  "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": 4.379961675335341e-05,
       "eval_loss": 0.3729982376098633,
-      "eval_runtime": 1201.5413,
-      "eval_samples_per_second": 8.001,
-      "eval_steps_per_second": 4.001,
+      "eval_runtime": 1205.9931,
+      "eval_samples_per_second": 7.972,
+      "eval_steps_per_second": 3.986,
       "step": 1
+    },
+    {
+      "epoch": 0.00021899808376676705,
+      "grad_norm": 0.3186088800430298,
+      "learning_rate": 5e-05,
+      "loss": 0.3378,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004379961675335341,
+      "grad_norm": 0.2965073585510254,
+      "learning_rate": 0.0001,
+      "loss": 0.4345,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004379961675335341,
+      "eval_loss": 0.33912086486816406,
+      "eval_runtime": 1202.4718,
+      "eval_samples_per_second": 7.995,
+      "eval_steps_per_second": 3.998,
+      "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": 369912849629184.0,
+  "total_flos": 4808867045179392.0,
   "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:bf1c80166ecc7e09e01f674a887f7d28a3616e5eb5f65ffa0c8add5020fa51c0
+oid sha256:de1d5889f1071477df9bba987d1ac8b80b95cededb0206760f58692994313c9f
 size 6776