Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "w2",
+    "v_proj",
     "w3",
-    "q_proj",
+    "o_proj",
     "k_proj",
-    "v_proj",
-    "gate",
+    "q_proj",
     "w1",
-    "w2"
+    "gate"
   ],
   "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:a356c2b4e4c9077429733e4ff61d75f96adc20bb7483ff21efd03e684bbde589
+oid sha256:33c226fdcbc9ffc2d2dff86f9e53300ca9a3cd6240c6ba49d4ce2cafcf6e61bd
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b2335f8144ad2dfdf932938de12928af243478a1051ab954d7123186581ba8
+oid sha256:0ecc9700960334617b0b947f87ebfa51d5076ee8f732b72714c3f05e33fd8eea
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0a98e757f2914ec18f19072f14e8a4f3ea6aec106c5f370a34ef74532e154b
+oid sha256:244572e920d4037637c527b6e37fa1608a341cc2df3c8bee2f11df8e9f8b09fc
 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": 0.0004550625711035267,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005915813424345847,
+  "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": 0.0004550625711035267,
       "eval_loss": 8.276806831359863,
-      "eval_runtime": 196.5474,
-      "eval_samples_per_second": 4.711,
-      "eval_steps_per_second": 2.356,
+      "eval_runtime": 191.4525,
+      "eval_samples_per_second": 4.837,
+      "eval_steps_per_second": 2.418,
       "step": 1
+    },
+    {
+      "epoch": 0.0022753128555176336,
+      "grad_norm": 18.482772827148438,
+      "learning_rate": 5e-05,
+      "loss": 7.6,
+      "step": 5
+    },
+    {
+      "epoch": 0.004550625711035267,
+      "grad_norm": 16.873130798339844,
+      "learning_rate": 0.0001,
+      "loss": 4.5357,
+      "step": 10
+    },
+    {
+      "epoch": 0.004550625711035267,
+      "eval_loss": 1.0215221643447876,
+      "eval_runtime": 193.2723,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 2.396,
+      "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": 323875007102976.0,
+  "total_flos": 4210375092338688.0,
   "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:b983642393302223bcec482fdbf98feeb3787c1fd95aa5ed3ceb6489427e97a0
+oid sha256:0402bbbde2a264d18059ee3e4ff89eaf30959f76d2ae92fb9f3ab7ae4ccee756
 size 6776