Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "target_modules": [
     "query_key_value",
     "dense_4h_to_h",
-    "dense",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "dense"
   ],
   "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 sha256:78512645282583338c4dc9e5ede6801dd992183b5e805ce6710cd2759612279b
+oid sha256:3f942aba4483a84f276c2ec27d555213e022d60da22987fd3e4c80707ddc2830
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5033be84d3195cca530aab64658926c26a219e2d275b7ff4ceb9a2c12d4ae3e6
+oid sha256:995dc70b5919ef7339deff602b1ce12af038cecfa9022bcb4af0842c8fa8e906
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac46b1c0bebd1db47da381c44ecf11d3611edab0c5abc4ef70acf5948a0b4e23
+oid sha256:2a5fedbc5bbf423a75d433c87d6481c2c61bc0c628368aa55379c00c043929f7
 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": 1.6595237996456916e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0002157380939539399,
+  "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": 1.6595237996456916e-05,
       "eval_loss": 0.9319517016410828,
-      "eval_runtime": 685.1079,
-      "eval_samples_per_second": 37.034,
-      "eval_steps_per_second": 18.517,
+      "eval_runtime": 684.835,
+      "eval_samples_per_second": 37.048,
+      "eval_steps_per_second": 18.524,
       "step": 1
+    },
+    {
+      "epoch": 8.297618998228458e-05,
+      "grad_norm": 3.183830499649048,
+      "learning_rate": 5e-05,
+      "loss": 3.624,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016595237996456917,
+      "grad_norm": 4.00230598449707,
+      "learning_rate": 0.0001,
+      "loss": 3.7706,
+      "step": 10
+    },
+    {
+      "epoch": 0.00016595237996456917,
+      "eval_loss": 0.7170787453651428,
+      "eval_runtime": 692.7042,
+      "eval_samples_per_second": 36.627,
+      "eval_steps_per_second": 18.314,
+      "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": 37321546137600.0,
+  "total_flos": 395608389058560.0,
   "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 sha256:6bea6a98b839a4b83f57a77347cf47524e7f868be4e3b1bf9f4f5594c007df8a
+oid sha256:a76217191b6cc51a4b23997a11c422a4373952461810ace23fe6a01daa8a7668
 size 6776