Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
+    "q_proj",
+    "down_proj",
     "gate_proj",
-    "up_proj",
     "k_proj",
-    "q_proj",
     "o_proj",
-    "down_proj"
+    "up_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:a05bd6809b6de392ee9b89cbacc7c8a023bd5fd6926b9b130ba587df171bb496
+oid sha256:0a9d077ef5d389aa16311ff1f2795224c939dd080956d121188f50c99ae819df
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:021389217012b0f25fdd20a98c5206b15b999a7a2d8abbae905c19e65808e8e7
+oid sha256:b9fddaec9223c2cd539163a4982107ecd8225db3118b235405349bf4ebe957d6
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e9f2b474228bb5f2a84d2dc166fe6d2193ce7ff94ac2784a09add5a63a3017
+oid sha256:0a4f0069edb1e06dc358b4ff190f10113fb1ddd26ae17efb126b43600cdb989c
 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": 0.000250501002004008,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.003256513026052104,
+  "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": 0.000250501002004008,
       "eval_loss": 3.7049801349639893,
-      "eval_runtime": 28.5824,
-      "eval_samples_per_second": 58.812,
-      "eval_steps_per_second": 29.424,
+      "eval_runtime": 29.0877,
+      "eval_samples_per_second": 57.791,
+      "eval_steps_per_second": 28.913,
       "step": 1
+    },
+    {
+      "epoch": 0.00125250501002004,
+      "grad_norm": 0.952879011631012,
+      "learning_rate": 5e-05,
+      "loss": 3.6862,
+      "step": 5
+    },
+    {
+      "epoch": 0.00250501002004008,
+      "grad_norm": 1.4141132831573486,
+      "learning_rate": 0.0001,
+      "loss": 3.5779,
+      "step": 10
+    },
+    {
+      "epoch": 0.00250501002004008,
+      "eval_loss": 3.6573493480682373,
+      "eval_runtime": 29.0311,
+      "eval_samples_per_second": 57.903,
+      "eval_steps_per_second": 28.969,
+      "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": 3429265047552.0,
+  "total_flos": 44580445618176.0,
   "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 sha256:1385c513e2aa58fec460ca4bc2e8a805a701118c94a8bce4bf1b410a2ea3e527
+oid sha256:823ad2771f62c2e48d0859ba73c5b48f5098e10e4576051a804aedc892996272
 size 6776