Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
     "dense_4h_to_h",
-    "dense_h_to_4h",
-    "dense"
+    "dense",
+    "query_key_value",
+    "dense_h_to_4h"
   ],
   "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:c041e0407cc9bca7c5e109737763a218f7373078bb8f1d21ebb3aa93f7be7122
+oid sha256:2244b7c1aa4355aa7ef3d6c78652296b8aeaf6e193d2e3a47a949e537a77c797
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f769496b83780843c802c38dc7a768aad195f2ec4a0e52afb4cc4525788aee0e
+oid sha256:ccd31d8b42a3fddcd7617f35764a2ed3555d880cf4d5254e276a08042d699659
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97b60998d53c1d797db53e375383a7d6d6df4606d2b68d39abea77130b5c637
+oid sha256:b43d6e631c7fcf3d1b5fdc0f052c49bbc432caae7f34a3e087fbd36696bfbbed
 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": 0.0023781212841854932,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.030915576694411414,
+  "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": 0.0023781212841854932,
       "eval_loss": 2.7670791149139404,
-      "eval_runtime": 5.1371,
-      "eval_samples_per_second": 34.65,
-      "eval_steps_per_second": 17.325,
+      "eval_runtime": 5.2365,
+      "eval_samples_per_second": 33.992,
+      "eval_steps_per_second": 16.996,
       "step": 1
+    },
+    {
+      "epoch": 0.011890606420927468,
+      "grad_norm": 25.248817443847656,
+      "learning_rate": 5e-05,
+      "loss": 11.273,
+      "step": 5
+    },
+    {
+      "epoch": 0.023781212841854936,
+      "grad_norm": 31.11591148376465,
+      "learning_rate": 0.0001,
+      "loss": 10.8987,
+      "step": 10
+    },
+    {
+      "epoch": 0.023781212841854936,
+      "eval_loss": 2.7416107654571533,
+      "eval_runtime": 3.8611,
+      "eval_samples_per_second": 46.101,
+      "eval_steps_per_second": 23.051,
+      "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": 8772856578048.0,
+  "total_flos": 135979276959744.0,
   "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:b463029491549914c47a0a2a0fedf5648cff524fe5663747f00d03712e560715
+oid sha256:e83d32b2d50780c006f1e9a93b926f15ef458115556abea139695d3192245d6d
 size 6776