Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate",
+    "k_proj",
+    "w3",
     "o_proj",
     "q_proj",
     "v_proj",
-    "w2",
-    "gate",
-    "w3",
     "w1",
-    "k_proj"
+    "w2"
   ],
   "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 sha256:61f3024defefdd7a27dae67a7d454a0196933a11f6cb6029819cdd59a99d5c26
+oid sha256:2a8f7d312e1273cd34e0c36e163bf1b7bfbeddca922b4ef72abb961f2f2d4f9e
 size 7586384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a70333b765ade3f0fa861aeefe44b9c4fc06b289c56b5f7379e257dd23e5a20
+oid sha256:e91d47a69ae003b4db840302a1e6d2c09a5003466af613248ec3e50a3ec8c0a4
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 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": 0.00010654733365297533,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0013851153374886793,
+  "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": 0.00010654733365297533,
       "eval_loss": NaN,
-      "eval_runtime": 36.84,
-      "eval_samples_per_second": 107.275,
-      "eval_steps_per_second": 53.637,
+      "eval_runtime": 36.3551,
+      "eval_samples_per_second": 108.706,
+      "eval_steps_per_second": 54.353,
       "step": 1
+    },
+    {
+      "epoch": 0.0005327366682648767,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010654733365297534,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010654733365297534,
+      "eval_loss": NaN,
+      "eval_runtime": 35.3678,
+      "eval_samples_per_second": 111.74,
+      "eval_steps_per_second": 55.87,
+      "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": 5310520492032.0,
+  "total_flos": 69036766396416.0,
   "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:d4446ccc8f6324f6bc79e0b59e3325570c65d44a8dda246b38299177169de348
+oid sha256:a2162c5d5d98c4a6f0db6a5426e66fe3a7a4051f0d4ac6fa6df632e9729e2132
 size 6776