Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
+    "v_proj",
     "q_proj",
+    "o_proj",
+    "down_proj",
     "up_proj",
-    "v_proj",
-    "k_proj",
-    "o_proj"
+    "gate_proj",
+    "k_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:b8a83f06d75585ed31093d7a5aa0c0e349d487fc5eaca7bc7fccdc6b5a15ff3e
+oid sha256:ce143c93cbf3c57b5d24ef72f791c9898746110620dce01296d88f3bbe40c01c
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95539ba855f91eb40e4dc2d2466d165686c431e4d7193450e9446911871a5a1e
+oid sha256:3be55418bd6e0948225c01ed6b56800621835abfdac90382dc9fd672bda76aeb
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:2b18069b57791b3ae2b5099cd170b1de564d9d383b48678ee518b571e7209716
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002398081534772182,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03117505995203837,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.002398081534772182,
       "eval_loss": 10.374227523803711,
-      "eval_runtime": 4.4989,
-      "eval_samples_per_second": 624.591,
-      "eval_steps_per_second": 78.241,
+      "eval_runtime": 4.7315,
+      "eval_samples_per_second": 593.897,
+      "eval_steps_per_second": 74.396,
       "step": 1
+    },
+    {
+      "epoch": 0.023980815347721823,
+      "grad_norm": 0.027691999450325966,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 10.3744,
+      "step": 10
+    },
+    {
+      "epoch": 0.023980815347721823,
+      "eval_loss": 10.373770713806152,
+      "eval_runtime": 4.4671,
+      "eval_samples_per_second": 629.048,
+      "eval_steps_per_second": 78.799,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 206894530560.0,
+  "total_flos": 2689628897280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3503c5c7935aa8a306938bffc1b8d3d7fd4b53be28d14b1ad425b93a16aad569
+oid sha256:85d13ad1de46976a07e81f340cc79426d8dc81765cc5c16ca7e6bbc33f1d04eb
 size 6776