Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "v_proj",
+    "down_proj",
     "k_proj",
-    "gate_proj",
-    "q_proj",
     "up_proj",
-    "down_proj"
+    "gate_proj",
+    "v_proj",
+    "q_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 sha256:1b26f21b0d2fed1834f20aeb788d5d144631945d3814c31fac607ee34262a7a9
+oid sha256:f9e2089b2e30ad6859754b24758f03e91742d71261883a793835007878188185
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6f9632972d4f71eddae40a22917f36ff80599551df9960db717b04a479dc72
+oid sha256:0edd418e512fdbd5725473818dda0e5641c4eb5010aaedb30f44f443970bc139
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c72baa8023c8324ff07b50f0b1e712615f39ed81df7102ee89528b084800c44
+oid sha256:6f26bf35ad8eb7e080cee4694910f00e12470da2b11743719b54383456fc7708
 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": 0.000598175564528189,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007776282338866457,
+  "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": 0.000598175564528189,
       "eval_loss": 1.5591797828674316,
-      "eval_runtime": 48.3718,
-      "eval_samples_per_second": 14.554,
-      "eval_steps_per_second": 7.277,
+      "eval_runtime": 48.3156,
+      "eval_samples_per_second": 14.571,
+      "eval_steps_per_second": 7.285,
       "step": 1
+    },
+    {
+      "epoch": 0.0029908778226409452,
+      "grad_norm": 1.9048610925674438,
+      "learning_rate": 5e-05,
+      "loss": 1.5192,
+      "step": 5
+    },
+    {
+      "epoch": 0.0059817556452818905,
+      "grad_norm": 2.2331185340881348,
+      "learning_rate": 0.0001,
+      "loss": 1.2524,
+      "step": 10
+    },
+    {
+      "epoch": 0.0059817556452818905,
+      "eval_loss": 0.9609334468841553,
+      "eval_runtime": 48.5419,
+      "eval_samples_per_second": 14.503,
+      "eval_steps_per_second": 7.251,
+      "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": 50009733070848.0,
+  "total_flos": 662628963188736.0,
   "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 sha256:7ca8336c5e77fcbe9b684bc421bb1e6135ef87ba038c1b325df19066ca343ae5
+oid sha256:d6a31424daeae884062002268cd35197faee643c5a8313f782bb6215a407ef78
 size 6776